This dataset encompasses extensive information on crop production in India, spanning multiple years and offering insights into agricultural trends and patterns. The dataset consists of over 246,000 records, capturing a wide array of variables related to crop production, and is intended to facilitate advanced analyses such as predictive modeling and the extraction of key insights for stakeholders in the agri-food sector.

Temporal Coverage: - The dataset covers multiple years, providing a longitudinal view of crop production trends in India. This temporal dimension is crucial for analyzing changes over time and understanding long-term patterns.

Geographical Scope: - Data is collected across various states and regions of India, reflecting the diverse agricultural landscape of the country. Regional variations in crop production can be analyzed to identify local factors affecting yields.

Crop Types: - The dataset includes information on various crop types grown across different regions. This classification allows for detailed analysis of specific crops, their production levels, and their sensitivity to various factors.

Production Metrics: - Metrics related to crop production such as yield (e.g., tons per hectare), total production volume, and harvested area are included. These metrics are essential for evaluating productivity and efficiency.

Data Quality and Completeness: - The dataset is likely to include a mix of structured and unstructured data. Data quality may vary, and preprocessing steps such as cleaning and normalization may be necessary to ensure accurate analyses.

Applications and Objectives:

Predictive Modeling: - The primary goal of analyzing this dataset is to develop predictive models for crop production. By leveraging historical data, machine learning algorithms can forecast future production levels and identify potential risks.

Insight Extraction: - The dataset provides an opportunity to uncover key indicators and metrics that significantly influence crop production. Insights can help stakeholders make informed decisions regarding crop management, resource allocation, and policy formulation.

Trend Analysis: - Longitudinal analysis of the data can reveal trends and patterns in crop production, helping to understand how factors such as technological advancements, policy changes, and environmental conditions affect agriculture.

Stakeholder Collaboration: - The dataset supports the development of collaboration platforms that connect various stakeholders in the agri-food sector. By integrating data from multiple sources, stakeholders can collaborate more effectively to address challenges and optimize production.

Key Features: 1. State_Name: Represents the name of the state in India where the crop data was recorded. 2. District_Name: Specifies the district within the state where the crop data was collected. 3. Crop_Year: Indicates the year in which the crop was harvested. 4. Season: Denotes the agricultural season (e.g., Kharif, Rabi) during which the crop was grown. 5. Crop: Identifies the type of crop that was cultivated. 6. Area: Represents the total land area used for cultivating the crop. 7. Production: Indicates the total quantity of the crop produced from the specified area.

Abstract

Syngenta is committed to increasing crop productivity and to using limited resources such as land, water and inputs more efficiently. Since 2014, Syngenta has been measuring trends in agricultural input efficiency on a global network of real farms. The Good Growth Plan dataset shows aggregated productivity and resource efficiency indicators by harvest year. The data has been collected from more than 4,000 farms and covers more than 20 different crops in 46 countries. The data (except USA data and for Barley in UK, Germany, Poland, Czech Republic, France and Spain) was collected, consolidated and reported by Kynetec (previously Market Probe), an independent market research agency. It can be used as benchmarks for crop yield and input efficiency.

Geographic coverage

National coverage

Analysis unit

Agricultural holdings

Kind of data

Sample survey data [ssd]

Sampling procedure

A. Sample design Farms are grouped in clusters, which represent a crop grown in an area with homogenous agro- ecological conditions and include comparable types of farms. The sample includes reference and benchmark farms. The reference farms were selected by Syngenta and the benchmark farms were randomly selected by Kynetec within the same cluster.

B. Sample size Sample sizes for each cluster are determined with the aim to measure statistically significant increases in crop efficiency over time. This is done by Kynetec based on target productivity increases and assumptions regarding the variability of farm metrics in each cluster. The smaller the expected increase, the larger the sample size needed to measure significant differences over time. Variability within clusters is assumed based on public research and expert opinion. In addition, growers are also grouped in clusters as a means of keeping variances under control, as well as distinguishing between growers in terms of crop size, region and technological level. A minimum sample size of 20 interviews per cluster is needed. The minimum number of reference farms is 5 of 20. The optimal number of reference farms is 10 of 20 (balanced sample).

C. Selection procedure The respondents were picked randomly using a “quota based random sampling” procedure. Growers were first randomly selected and then checked if they complied with the quotas for crops, region, farm size etc. To avoid clustering high number of interviews at one sampling point, interviewers were instructed to do a maximum of 5 interviews in one village.

BF Screened from Japan were selected based on the following criterion: Location: Hokkaido Tokachi (JA Memuro, JA Otofuke, JA Tokachi Shimizu, JA Obihiro Taisho) --> initially focus on Memuro, Otofuke, Tokachi Shimizu, Obihiro Taisho // Added locations in GGP 2015 due to change of RF: Obhiro, Kamikawa, Abashiri
BF: no use of in furrow application (Amigo) - no use of Amistar

Contract farmers of snacks and other food companies --> screening question: 'Do you have quality contracts in place with snack and food companies for your potato production? Y/N --> if no, screen out

Increase of marketable yield --> screening question: 'Are you interested in growing branded potatoes (premium potatoes for processing industry)? Y/N --> if no, screen out

Potato growers for process use
Background info: No mention of Syngenta Background info: - Labor cost is very serious issue: In general, labor cost in Japan is very high. Growers try to reduce labor cost by mechanization. Percentage of labor cost in production cost. They would like to manage cost of labor - Quality and yield driven

Mode of data collection

Face-to-face [f2f]

Research instrument

Data collection tool for 2019 covered the following information:

(A) PRE- HARVEST INFORMATION

PART I: Screening PART II: Contact Information PART III: Farm Characteristics a. Biodiversity conservation b. Soil conservation c. Soil erosion d. Description of growing area e. Training on crop cultivation and safety measures PART IV: Farming Practices - Before Harvest a. Planting and fruit development - Field crops b. Planting and fruit development - Tree crops c. Planting and fruit development - Sugarcane d. Planting and fruit development - Cauliflower e. Seed treatment

(B) HARVEST INFORMATION

PART V: Farming Practices - After Harvest a. Fertilizer usage b. Crop protection products c. Harvest timing & quality per crop - Field crops d. Harvest timing & quality per crop - Tree crops e. Harvest timing & quality per crop - Sugarcane f. Harvest timing & quality per crop - Banana g. After harvest PART VI - Other inputs - After Harvest a. Input costs b. Abiotic stress c. Irrigation

See all questionnaires in external materials tab

Cleaning operations

Data processing:

Kynetec uses SPSS (Statistical Package for the Social Sciences) for data entry, cleaning, analysis, and reporting. After collection, the farm data is entered into a local database, reviewed, and quality-checked by the local Kynetec agency. In the case of missing values or inconsistencies, farmers are re-contacted. In some cases, grower data is verified with local experts (e.g. retailers) to ensure data accuracy and validity. After country-level cleaning, the farm-level data is submitted to the global Kynetec headquarters for processing. In the case of missing values or inconsistences, the local Kynetec office was re-contacted to clarify and solve issues.

Quality assurance Various consistency checks and internal controls are implemented throughout the entire data collection and reporting process in order to ensure unbiased, high quality data.

• Screening: Each grower is screened and selected by Kynetec based on cluster-specific criteria to ensure a comparable group of growers within each cluster. This helps keeping variability low.

• Evaluation of the questionnaire: The questionnaire aligns with the global objective of the project and is adapted to the local context (e.g. interviewers and growers should understand what is asked). Each year the questionnaire is evaluated based on several criteria, and updated where needed.

• Briefing of interviewers: Each year, local interviewers - familiar with the local context of farming -are thoroughly briefed to fully comprehend the questionnaire to obtain unbiased, accurate answers from respondents.

• Cross-validation of the answers: o Kynetec captures all growers' responses through a digital data-entry tool. Various logical and consistency checks are automated in this tool (e.g. total crop size in hectares cannot be larger than farm size) o Kynetec cross validates the answers of the growers in three different ways: 1. Within the grower (check if growers respond consistently during the interview) 2. Across years (check if growers respond consistently throughout the years) 3. Within cluster (compare a grower's responses with those of others in the group) o All the above mentioned inconsistencies are followed up by contacting the growers and asking them to verify their answers. The data is updated after verification. All updates are tracked.

• Check and discuss evolutions and patterns: Global evolutions are calculated, discussed and reviewed on a monthly basis jointly by Kynetec and Syngenta.

• Sensitivity analysis: sensitivity analysis is conducted to evaluate the global results in terms of outliers, retention rates and overall statistical robustness. The results of the sensitivity analysis are discussed jointly by Kynetec and Syngenta.

• It is recommended that users interested in using the administrative level 1 variable in the location dataset use this variable with care and crosscheck it with the postal code variable.

Data appraisal

Due to the above mentioned checks, irregularities in fertilizer usage data were discovered which had to be corrected:

For data collection wave 2014, respondents were asked to give a total estimate of the fertilizer NPK-rates that were applied in the fields. From 2015 onwards, the questionnaire was redesigned to be more precise and obtain data by individual fertilizer products. The new method of measuring fertilizer inputs leads to more accurate results, but also makes a year-on-year comparison difficult. After evaluating several solutions to this problems, 2014 fertilizer usage (NPK input) was re-estimated by calculating a weighted average of fertilizer usage in the following years.

Globally, there has been an explosion of data generation in agriculture. With such a deluge of data available, it has become essential to create solutions that organize, analyze, and visualize it to gain actionable insights, which can guide farmers, scientists, or policy makers to take better decisions that lead to transformative actions for agriculture. There is a plethora of digital innovations in agriculture that implement big data techniques to harness solutions from large amounts of data, however, there is also a significant gap in access to these innovations among stakeholders of the value chains, with smallholder's farmers facing higher risks. Open data platforms have emerged as an important source of information for this group of producers but are still far from reaching their full potential. While the growing number of such initiatives has improved the availability and reach of data, it has also made the collection and processing of this information more difficult, widening the gap between those who can process and interpret this information and those who cannot. The Crop Observatories are presented in this article as an initiative that aims to harmonize large amounts of crop-specific data from various open access sources to build relevant indicators for decision making. Observatories are being developed for rice, cassava, beans, plantain and banana, and tropical forages, containing information on production, prices, policies, breeding, agronomy, and socioeconomic variables of interest. The Observatories are expected to become a lighthouse that attracts multi-stakeholders to avoid “not see the forest for the trees” and to advance research and strengthen crop economic systems. The process of developing the Observatories, as well as the methods for data collection, analysis, and display, is described. The main results obtained by the recently launched Rice Observatory (www.riceobservatory.org), and the about to be launched Cassava Observatory are presented, contextualizing their potential use and importance for multi-stakeholders of both crops. The article concludes with a list of lessons learned and next steps for the Observatories, which are also expected to guide the development of similar initiatives. Observatories, beyond presenting themselves as an alternative for improving data-driven decision making, can become platforms for collaboration on data issues and digital innovations within each sector.

Technology infusion in agriculture has been progressing steadily, touching up on various spheres of agriculture such as crop identification, soil classification, yield prediction, disease detection, and weed-crop discrimination. On-demand detection of crop type, often realized as crop mapping, is a primary requirement in agriculture. Hyperspectral remote sensing has emerged as the most versatile technique for the mapping and prediction of various parameters of interest in agriculture. Thanks to the readily availability of a host of machine leaning models and frameworks, the prospect of automatic identification of crop is perceived a realistic goal achievable in the near-future. The ongoing developments in the methods and algorithms of remote sensing data analyses for crop mapping requires the availability of curated, multi-site hyperspectral datasets, under various cases of variations by type and number of crops, geographic site and verifiable ground truth data. The availability of high-resolution airborne hyperspectral datasets across multiple sites with compositions of different types of crops is scare in remote sensing literature. Aimed at enabling the development of knowledge-transfer and potentially automatic approaches for multi-crop mapping using hyperspectral remote sensing, we present a comprehensive high-resolution airborne hyperspectral datasets acquired using AVIRIS-NG for five different sites encompassing different types of crops and agro-climatic regions with associated growth truth data. Though the acquired over sites in India, the diversity in terms of types and number of crops and geographic and agro-climatic diversity maintained by the hyperspectral imaging settings enable the study, implementation and validation of a host of methods and algorithms for agriculture studies using hyperspectral imaging datasets. This is the first of its kind datasets acquisition in which the sensor-imaging and acquisition geometry are maintained consistently similar across different sites and the composting and diversity of crop types maintained for undertaking multi-pronged studies on precision crop mapping suing remote sensing.

Abstract

Agriculture is the predominant activity in the Kingdom of Tonga's economy, contributing more than 17% to the Gross Domestic Product (GDP) in 2012 - 2013. The first ever Agriculture Census of the Kingdom was conducted in 1985. The second Census was conducted in 2001, focusing on land tenure, land utilization, area and production of principal crops, livestock, agricultural implements and equipment, use of fertilizers, etc. including the various agricultural activities in which most of the households were engaged in. Although agriculture is the main factor in the economy of the Kingdom of Tonga, the database in this sector seems to be inadequate. There were quite several surveys conducted for this sector, however, an updated frame (list of holdings/parcels and its characteristics) is needed so these surveys will obtain more reliable estimates. There were important developments in agriculture within the fourteen-year period from the last census that should be captured like the use of forest trees within the farming system to enhance productivity and information on fisheries, which is becoming a very important sector of the Kingdom's economy. Considering the above issues, there is a great need to update the statistics on agriculture in order to determine its present situation and to use it for economic planning and policy-making.

In support of the strategic plans and programmes of the Kingdom of Tonga on agriculture, the Government has decided to conduct the Agriculture Census (AC). This census is envisioned to:

a) Provide benchmark or basic data on structure of agricultural holdings and their main characteristics; b) Use this information to develop a regular system of agricultural statistics; c) Build up some important village level statistics; d) Establish a technical and organizational foundation on which to build up a comprehensive and integrated system of food and agricultural statistics; and e) Provide a frame from which samples can be drawn to study certain aspects of agricultural activities in greater depth. f) Provide information on community (village) statistics.

Geographic coverage

National coverage

Analysis unit

Households

Universe

The Census covered all individuals and households.

Kind of data

Census/enumeration data [cen]

Mode of data collection

Face-to-face paper [f2f]

Research instrument

The questionnaire was designed in collaboration between FAO, Ministry of Agriculture and the TNSO. It was designed in such a way that data items were efficiently encoded and processed using the software package CSPro.

The questionnaire was developed in English, but enumerators were specifically trained to be able to clearly translate these questions to other languages and dialect used in the country.

The questionnaires were designed in 13 sub-sections which are:

A. Identification particulars B. Household demographic and economic information C. Household engagement in agricultural subsectors D. Usage of land E. Food crops F. Agricultural practices G. Livestock H. Fisheries I. Forestry J. Handicrafts K. Labour L. Machinery and equipment M. Agricultural income and loan for all subsectors

Information collected for each sub-sections:

Section A: This section basically include the IDs for the households and include: - Village number - Census block - Household number - Sample - Type of holding

Section B: - name - relationship - sex - age - economic activity - educational attainment

Section D: - Bush allotment - Town allotment

Section E: - Exisiting crops - Crops harvested

Section F: - Fertilizer - Pesticides - Irrigation - Community farming

Section G: - Beef cattle - Dairy cattle - Pig - Horse - Sheep - Goat - Chicken - Duck - Dog / Cat - Veterinary services

Section H: - Fishing type - Fish income / sales - Purpose of fishing

Section I: - Number of trees - uses of trees

Section J: - Handicraft materials - Handicrafts sold - Value of handicrafts

Section K / L - Number of laborers - Days worked - Hours worked - Machinery used

Section M: - Income from agriculture - Loans - Drawbacks

Cleaning operations

VERIFICATION AND CODING

The data editing process begins when the completed questionnaires were returned to the national statistics office (NSO) for checking by the coders. This include checking that all fields are correctly filled, skipped pattern are properly followed, missing fields and so forth. Once the questionnaires are verified to be correct, then coding begins where certain variables are coded to their respective codes for capturing in the data entry screen - codes include Village code, Crops and Trees codes.

IN-BUILT EDITING

The data entry application for the 2015 Agriculture Census was designed using the software package CSPro where all necessary checks were incorporated to allow the Data Entry Operators (DEO) to verify data while doing data entry. With all the in-built checks, this ensures capturing good quality data efficiently and effectively. The in-built checks include range checks, skip and filtering questions and consistent and logic checks. With these in-built checks ensures good quality data is captured while entering and this greatly helps in the final batch editing.

SECONDARY EDITING

After the completion of the data entry, the final editing process was done. This include verification of questionnaires that all are captured and the actual running of the batch editing program on the whole data. Since most of the checks were done during the data entry phase, the batch editing process mostly involves verifying those errors that were missed or could not be solved during data entry, checking on those responses which have been coded 'missing' and trying to impute or verify by referring to the respective questionnaire and fixing 'outliers' responses. Frequencies on each variable were also checked to verify any inconsistencies between variables. The batch editing logic program was ren twice when it was decided to finalize the data. Some missing values were not fixed as they were not able to be verified, examples of these are mostly on money values and number of crops/trees.

Response rate

The final national response rate was 89% with 16,122 households enumerated out of the 18,043 total households.

Data appraisal

There were 12 data entry operators, 7 computers and a server used for data entry. The 12 operators took turns in doing data entry as well as coding and verification of questionnaires before they were entered. The data entry was done manually was done in the head office to allow for easy access to the books.

The data entry screen was designed using the CSPro software.

The data entry application was well designed and efficient during the actual data entry as a lot of testing was done during the pilot census. Questionnaires from the pilot census was used to test the application and relevant modifications were done, hence, by the time the actual data processing commences, the application was fully developed and ready. This ensures the capturing of good quality and reliable data from the questionnaires.

TECHNICAL NOTES AND DEFINITIONS 1. Agriculture active household is a household that is active in any of the agriculture activities: cropping; livestock; fisheries; forestry and handicraft. A household is active in any of these agriculture activities if it can be classified into either: subsistence, semi subsistence or commercial. 2. A household is non active in agriculture if it cannot be classified into any of the agriculture activities: cropping; livestock; fishery; forestry or handicraft. 3. Subsistence is a type of agriculture activities (cropping; livestock; fishing; forestry or handicraft making) in which most of the produce is consumed by the farmer and his family, leaving nothing to be marketed. 4. Semi-subsistence is a type of agriculture activities in which some of the produces are to be consumed by the farmer and his family and some of them are to be marketed. 5. Commercial is a type of agriculture activities in which most of the produces are to be marketed. 6. For the 2015 Agricultural Census, the following definition was used to classify the levels of agriculture activities whether it was subsistence; semi-subsistence or commercial.

Crop was based on total cultivated land area a) Subsistence: 0 < and <= 1 acres Semi Subsistence: 1 acres < and <= 8 acres Commercial: > 8 acres

Livestock was based on type and number of livestock kept a) Subsistence: If Milk Cattle or Beef Cattle =1 or Sow = 1 b) Semi Subsistence: If Milk Cattle or Beef Cattle = 2 - 100 or Sow = 2 - 25 c) Commercial: If Milk Cattle or Beef Cattle > 100 or Sow > 25 or Egg layer > 0 or Broiler > 0

Fishery was based households or organizations' response to the question on purpose of their fishing activities; whether it was for subsistence; semi-subsistence or commercial.

Forestry was based on number of high value trees and timber trees that households have grown at the time of the census a) Subsistence: number of trees 1 - 4 b) Semi Subsistence: number of trees 5 - 100 c) Commercial: number of trees 101 - 999

Handicraft was based on proportion of handicraft being sold a) Subsistence: no handicraft sold b) Semi Subsistence: 1% - 75 % sold c) Commercial: 76% - 100% sold

LIMITATIONS A Pilot Census was conducted which the questionnaires received were used to test the data entry application. This allowed to redefine the questionnaires as well as the data entry application to ensure that it everything was efficiently designed to capture reliable data. Like any other census, the 2015 Agriculture Census (AGC) has its own limitations. These are summarized as follows:

-

This dataset simulates real-world smart farming operations powered by IoT sensors and satellite data. It captures environmental and operational variables that affect crop yield across 500 farms located in regions like India, the USA, and Africa.

Designed to reflect modern agritech systems, the data is ideal for: - Predictive modeling using ML/AI - Time-series analysis - Sensor-based optimization - Environmental data visualizations - Crop health analytics

🧠 Ideal For

• Supervised ML models (regression, classification)
• Yield prediction and optimization
• Agricultural decision support systems
• Smart irrigation strategy analysis
• Data visualization of regional farm efficiency

📌 Columns Description

📫 Let's Collaborate!

If you build a notebook, model, or dashboard using this dataset — feel free to tag me or leave a comment. Happy growing! 🌱🚜

The Agricultural Statistics of the People's Republic of China, 1949-1990 is an historical collection of agricultural statistical data compiled by China's State Statistical Bureau (SSB). The collection contains 297 variables covering social and economic indicators, commodities, price index, production, trade, and consumption. The data are provided at the national level (1949-1990) and the provincial level (1979-1990). This data set is produced in collaboration with the United States Department of Agriculture (USDA), SSB, and the Center for International Earth Science Information Network (CIESIN).

Snapshot img

Crop Production Software Market Size 2024-2028

The crop production software market size is forecast to increase by USD 2.22 billion at a CAGR of 17.59% between 2023 and 2028.

The agricultural market is experiencing substantial growth due to several notable trends and challenges. One notable trend is the increasing use of precision farming, which employs advanced technologies to optimize crop yields and reduce waste. Another significant development is the integration of artificial intelligence (AI) and machine learning (ML) into crop production software. This innovation enables predictive analytics and the automation of farming processes, leading to improved efficiency and productivity. However, the substantial upfront capital investments required by farmers pose a significant barrier to market expansion. Despite this obstacle, the potential benefits of these technologies are compelling, making the agricultural sector an intriguing and dynamic area to monitor.

What will the size of the market be during the forecast period?

Request Free Sample

The agribusiness sector is witnessing significant advancements in crop production, driven by the global population's increasing demand for food and the challenges of urbanization, climate change, and the depletion of arable land. Sustainable agriculture solutions, such as precision farming, real-time data collection and analysis, predictive modeling, monitoring, and control, are becoming essential for optimizing food production.



Companies are pioneering the use of Satellite IoT (SatIoT) and sensors, actuators, and devices to create greenhouses and monitor microclimates. Government investments in satellite imaging, in-field sensors, artificial intelligence, and machine learning are also playing a crucial role in developing regions. The integration of drones and Internet of Things (IoT) devices into crop production software is revolutionizing planting schedules and enhancing overall productivity in the agricultural sector.

How is this market segmented and which is the largest segment?

The market research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2024-2028, as well as historical data from 2018-2022 for the following segments.

Deployment

  On-premises
  Cloud


Type

  Small
  Medium
  Large


Geography

  North America

    US


  Europe

    Germany
    UK


  APAC

    China


  South America



  Middle East and Africa

By Deployment Insights

The on-premises segment is estimated to witness significant growth during the forecast period.

Agribusinesses, farmers, ranchers, and growers worldwide are increasingly adopting crop production software to optimize food production in the face of global population growth, urbanization, climate change, and the need for sustainable agriculture. On-premises deployment of these solutions requires farmers to invest in hardware (servers, network equipment, security devices) and software, making it a significant upfront cost. However, the benefits include enhanced data security, real-time data collection and analysis, predictive modeling, monitoring, and control. Smart greenhouses utilize sensors, actuators, and devices to optimize microclimates, while Satellite IoT (SatIoT) and drones provide valuable data for precision farming.

Furthermore, in-field sensors, satellite imaging, and artificial intelligence enable advanced analytics and automation capabilities. Government investments in agriculture technology and cloud services facilitate the integration of mobile applications and data analysis tools. Despite the advantages, the high deployment costs may limit the adoption of on-premises crop production software, particularly in developing regions. However, the potential for increased efficiency, productivity, and profitability makes it an attractive option for agribusinesses and farmers alike.

Get a glance at the market report of share of various segments Request Free Sample

The on-premises segment was valued at USD 465.49 million in 2018 and showed a gradual increase during the forecast period.

Regional Analysis

North America is estimated to contribute 43% to the growth of the global market during the forecast period.

Technavio's analysts have elaborately explained the regional trends and drivers that shape the market during the forecast period.

For more insights on the market share of various regions, Request Free Sample

The market is experiencing significant growth due to the integration of advanced technologies in agriculture. High-speed imagery services are becoming increasingly crucial for farmers to monitor crop quality and resource use, leading to improved precision in agriculture. This, in turn, helps in reducing input costs and enhancing food security. Sustainability is a key focus area, with weather conditions, t

Geographic coverage

National coverage

Analysis unit

Households

Universe

Statistical unit The statistical unit was the agricultural holding, defined as an economic unit engaged in agricultural production under a single management, which includes all livestock and all land used in whole or in part for agricultural production, regardless of legal status and legal form.

Four main types of agricultural production units were distinguished in the AC 2006/2007:

(i) agricultural enterprises and their separate subdivisions (legal entities); (ii) "peasant farms" and "individual entrepreneurs; (iii) households in rural and urban areas; and (iv) "horticultural and cottage farms".

Kind of data

Census/enumeration data [cen]

Sampling procedure

(a) Frame The list of agricultural enterprises and their separate subdivisions (legal entities) was established on the basis of the Statistical Agricultural Register. The lists of individual entrepreneurs were based on the Statistical Business Register. The lists of peasant farms and households in rural areas were formed on the basis of the household registers held by local authorities. The lists of households, horticultural and cottage farms that have land and livestock (including poultry) in urban areas were formed on the basis of various data sources, such as data of land management agencies, land title registration authorities, taxpayer registries and other administrative sources.

Mode of data collection

Face-to-face [f2f]

Research instrument

Specific questionnaires for each of the four main types of units were used in the AC:

(i) three questionnaires for collecting information on crop production (in stage I); (ii) three questionnaires for collecting information on animal husbandry (in stage II).

In addition, one census questionnaire was applied to legal units and peasant farms engaged in support activities (services) to agriculture (in stage II).

The AC 2006/2007 covered 111 out of the 16 core items recommended in the WCA 2010. The core items not covered in the AC are:

(i) "Sex of agricultural holder"; (ii) "Age of agricultural holder presence of aquaculture on the holding"; (iii) "Household size"; (iv) "Presence of aquaculture on the holding"; (v) "Other economic production activities of the holding's enterprise".

See questionnaire in external materials tab.

Cleaning operations

Data entry was carried out manually. The paper census forms are kept in the territorial bodies and the electronic database is stored on the server of the AS (CS). For quality assurance, a 10-percent selective check was conducted during the entire census data collection by the supervisors. After the census enumeration was completed, a field quality control was carried out to check the quality of census data, covering 5 percent of the census units.

Data appraisal

The AC results were disseminated through printed reports, CD-ROMs and institutions' website. The preliminary census data (related to the first census stage) were disseminated in six volumes in 2007 (at the national and regional level). The final census results were disseminated in nine volumes in 2008.

Abstract

Food security has become a burring issue in Ethiopia since it is an absolute prerequisite for political and social stability. It received national prominence in the aftermath of the recurring drought and famine and obviously became an immediate domestic policy concern. The gap between the dire need for food supply is compounded by rapidly increasing population, depletion of natural resources and the existing traditional way of farming. It even requires sacrifice to provide adequate supply of food in such a situation where natural and human factors have negatively impacted in the agricultural production and resulted in recurrent droughts and sometimes in catastrophe. Pressed by these problems and other economic factors, the Ethiopian government has centered its agricultural policy on ensuring food security by allocating more resources to increase agricultural production so as to ward off food shortage and ensure continuous adequate supply of food. To monitor and evaluate the performance of the policy and the trends in the charging patterns in agricultural, statistical information on agriculture is required as an input since agriculture is a primary activity connected with food availability. The Central Statistical Agency (CSA) has been generating statistical information used as inputs in the formulation of agricultural policies by collecting processing and summarizing reliable, comprehensive and timely data on the country's agriculture. As part of this mission the 2003-2004 (1996 E.C) Annual Agricultural Sample Survey was conducted to furnish data on cropland area and production of crops within the private peasant holdings for Main (“Meher”) season of the quoted year.

The general objective of CSA's annual Agricultural Sample Survey (AgSS) is to collect basic quantitative information on the country's agriculture that is essential for planning, policy formulation, food security, etc. The survey is composed of four components: Crop production forecast survey. Main (“Meher”) season survey, Livestock survey and “Belg” season survey.

The specific objectives of Main (“Meher”) season survey are: - To estimate the total cultivated area, production and yield of crops. - To estimate the total volume of inputs used, inputs applied area and number of holders using inputs. - To estimate the total cultivated area and other forms of land use.

Geographic coverage

The 2003-2004 annual Agricultural Sample Survey covered the entire rural parts of the country except all zones of Gambella region, and the non-sedentary population of three zones of Afar and six zones of Somali regions.

Note: The crop cutting exercise part of the survey from November 2003 up to January 2004 was not done in Gambela regional state, therefore no production estimates for the region was computed for Meher (main) season.

Analysis unit

Agricultural household/ Holder/ Crop

Universe

Agricultural households

Kind of data

Sample survey data [ssd]

Sampling procedure

Sampling Frame: The list containing EAs of all regions and their respective agricultural households obtained from the 2001/02 Ethiopian Agricultural Sample Enumeration (EASE) was used as the sampling frame in order to select the primary sampling units (EAs). Consequently, all sample EAs were selected from this frame based on the design proposed for the survey. Sample Design A stratified two-stage cluster sample design was used to select the sample. Enumeration Areas (EAs) were taken to be the primary sampling units (PSUs) and the secondary sampling units (SSUs) were agricultural households. Sample enumeration areas from each stratum were sub-samples of the 2001/02 (1994 E.C) Ethiopian Agricultural Sample Enumeration. They were selected using probability proportional to size systematic sampling; size being number of agricultural households obtained from the 1994 Population & Housing Census and adjusted for the sub-sampling effect. Within each sample EA a fresh list of households was prepared and 25 agricultural households from each sample EA were systematically selected at the second stage. The survey questionnaire was finally administered to the 25 agricultural households selected at the second stage. Information on area under crops and Meher season production of crops was obtained from the 25 households that were ultimately selected. It is important to note, however, that data on crop cutting were obtained only from fifteen sampled households (the 11th - 25th households selected).

The sample size for the 2003-04 agricultural sample survey was determined by taking into account both the required level of precision for the most important estimates within each domain and the amount of resources allocated to the survey. In order to reduce non- sampling errors, manageability of the survey in terms of quality and operational capability was also considered. Except Harari, Addis Ababa and Dire Dawa, where each region as a whole was taken to be the domain of estimation; each zone of a region / special wereda was adopted as a stratum for which major findings of the survey are reported.

Mode of data collection

Face-to-face [f2f]

Research instrument

The 2003-2004 annual Agricultural Sample Survey used structured questionnaires to collect agricultural information from selected sample households. List of forms in the questionnaires: - AgSS Form 96/0: Used to list all households and agricultural holders in the sample enumeration areas. - AgSS Form 96/1: Used to list selected households and agricultural holders in the sample enumeration areas. - AgSS Form 96/3A: Used to list fields under temporary crops and farm management practice. - AgSS Form 96/3B: Used to list fields under permanent crops and farm management practice. - AgSS Form 96/3C: Used to list fields under mixed crops and farm management practice. - AgSS Form 96/3D: Used to collect information about other land use type and area and other agricultural related questions. - AgSS Form 96/5: Used to list temporary crop fields for selecting crop fields for crop cutting. - AgSS Form 96/6: Used to collect information about temporary crop cutting results.

Cleaning operations

Editing, Coding and Verification: Statistical data editing plays an important role in ensuring the quality of the collected survey data. It minimizes the effects of errors introduced while collecting data in the field , hence the need for data editing, and verification. An editing, coding and verification instruction manual was perpared and reproduced. Then 65 editors-coders and verifiers were trained for two days in editing , coding and.verification using the aforementioned manual as a reference and teaching aid. The completed questionnaires were edited, coded and later verified on a 1OO % basis before the questioners were passed over to the data entry unit. The editlng, coding and verification exercise of all questionnaires took 40 days.

Data Entry, Cleaning and Tabulation: Before data entry, the Natural resource and Agricultural Statistics Department prepared edit specification for the survey for use on personal computers for data consistency checking purposes . The data on the edited and coded questionnaires were then entered into personal computers. The data were then checked and cleaned using the edit specification prepared earlier for this purpose. The data entry operation involved about 64 data encoders and it took 50 days to finsh the job. Finally, tabulation was done on personal computers to produce statistical tables as per the tabulation plan.

Response rate

A total of 2,072 enumeration areas were initially selected to be covered by the survey, however, due to various reasons 16 EA's were not covered and the survey was successfully carried out in 2,056 (99.23 %) EAs. As regards the ultimate sampling unit, it was planned to conduct the survey on 51,800 agricultural households and 51,300 (99.03 %) households were actually covered by the Meher season Agricultural Sample Survey.

Sampling error estimates

Estimation procedure of totals, ratios, sampling error and the measurement of precision of estimates (CV) are given in Appendix I and II of 2003-2004 Agricultural Sample Survey, Volume I report.

Data appraisal

As it was explained in the response rate under sampling section, the non response rate was minimal. There is no testing for bias made in this survey.

Abstract

The purpose of the Crop Forecast Survey is to obtain information from farmers on the anticipated estimates of the area under major crops,production and sales during the season.This information is used to assess the expected food security situation in the country and aslo provide the national food balance sheet which is used to dertermine the surplus or deficit of major cereals and tubers in the country. The information is vital to the government, NGOs, private sector particularly traders as well as well as donors for strategic planning and decision making purposes. Such strategic decisions may relate to local marketing and import/export.

The estimates obtained are on area planted to crops, expected crop production, quantity and variety of seed, quantity and type of fertilizer used, expected crop sales, area under cassava, area under mature cassava and carryover stocks. Except otherwise stated, the reference period for this information is the agricultural season starting 1st October 2007 ending 30th September 2008.

Geographic coverage

National coverage

The survey was conducted in the same 680 SEAs that were covered for the 2006/2007 CFS.

Analysis unit

• Agricultural households
• Individuals, members of agricultural households

Universe

A sample of small and medium scale agriculture households and all large scale farmers

Kind of data

Sample survey data [ssd]

Sampling procedure

The sampling frame of Standard Enumeration Areas (SEAs) was constructed using the results from the 2000 Census of Population and Housing. Within each district, the SEAs were stratified by predominant crop in order to ensure a representative sample for each crop. The SEAs were then sorted by geographic codes to ensure that geographical distribution of the sample SEAs is also representative. The sampling frame included all 12,358 rural SEAs. In addition, 431 urban SEAs which had 70 percent or more agricultural households according to the 2000 Census were included in the frame. A sample of 680 SEAs was selected from the total of 12,789 SEAs.

A two-stage sampling scheme was adopted. At the first stage, an allocated proportional number of SEAs in each province and district was selected using the Probability Proportional to Size (PPS) selection procedure. The measure of size was the number of agricultural households (as listed in the Census) in each SEA.

The household was the second stage-sampling unit. Firstly, all households in each sample SEA were listed and agricultural households were identified. To improve the precision of the survey estimates, the agricultural households were stratified into three (3) categories -- A, B and C, based on total area under crops, presence of some specified crops and on numbers of cattle, goats, pigs and chickens raised. A number of households were selected from each category using the systematic random sampling method, coming up with a total of twenty (20) sample households in each sample SEA.

Mode of data collection

Face-to-face [f2f]

Research instrument

The questionnaire for the Crop Forecast Survey contained and collected information on the following: - Name of the village/locality; - Household serial number (assigned by the Enumerator during listing); - Name of the head of household; - Sex and age of head of household; - Household size; - Type of agricultural activity the household is involved in; - Fertilizer acquisition and use; - Crop production and sales; - Livestock and poultry production and marketing; - Crop Management - input application and tillage methods; - Crop rotation and irrigation.

Cleaning operations

Supervisors and some enumerators based at provincial headquarters edited the questionnaires. The edited questionnaires were entered on microcomputers using a software package known as CSpro. Data capturing was accomplished at each provincial centre. Initial computer data processing was done at the provincial headquarters using CSpro software. Staff in Agriculture and Environment Division based at CSO headquarters did further data computer processing.

Response rate

Since this is mainly rural based household survey the response rates are generally high i.e. close to hundred percent

United States agricultural researchers have many options for making their data available online. This dataset aggregates the primary sources of ag-related data and determines where researchers are likely to deposit their agricultural data. These data serve as both a current landscape analysis and also as a baseline for future studies of ag research data. Purpose As sources of agricultural data become more numerous and disparate, and collaboration and open data become more expected if not required, this research provides a landscape inventory of online sources of open agricultural data. An inventory of current agricultural data sharing options will help assess how the Ag Data Commons, a platform for USDA-funded data cataloging and publication, can best support data-intensive and multi-disciplinary research. It will also help agricultural librarians assist their researchers in data management and publication. The goals of this study were to establish where agricultural researchers in the United States-- land grant and USDA researchers, primarily ARS, NRCS, USFS and other agencies -- currently publish their data, including general research data repositories, domain-specific databases, and the top journals compare how much data is in institutional vs. domain-specific vs. federal platforms determine which repositories are recommended by top journals that require or recommend the publication of supporting data ascertain where researchers not affiliated with funding or initiatives possessing a designated open data repository can publish data Approach The National Agricultural Library team focused on Agricultural Research Service (ARS), Natural Resources Conservation Service (NRCS), and United States Forest Service (USFS) style research data, rather than ag economics, statistics, and social sciences data. To find domain-specific, general, institutional, and federal agency repositories and databases that are open to US research submissions and have some amount of ag data, resources including re3data, libguides, and ARS lists were analysed. Primarily environmental or public health databases were not included, but places where ag grantees would publish data were considered. Search methods We first compiled a list of known domain specific USDA / ARS datasets / databases that are represented in the Ag Data Commons, including ARS Image Gallery, ARS Nutrition Databases (sub-components), SoyBase, PeanutBase, National Fungus Collection, i5K Workspace @ NAL, and GRIN. We then searched using search engines such as Bing and Google for non-USDA / federal ag databases, using Boolean variations of “agricultural data” /“ag data” / “scientific data” + NOT + USDA (to filter out the federal / USDA results). Most of these results were domain specific, though some contained a mix of data subjects. We then used search engines such as Bing and Google to find top agricultural university repositories using variations of “agriculture”, “ag data” and “university” to find schools with agriculture programs. Using that list of universities, we searched each university web site to see if their institution had a repository for their unique, independent research data if not apparent in the initial web browser search. We found both ag specific university repositories and general university repositories that housed a portion of agricultural data. Ag specific university repositories are included in the list of domain-specific repositories. Results included Columbia University – International Research Institute for Climate and Society, UC Davis – Cover Crops Database, etc. If a general university repository existed, we determined whether that repository could filter to include only data results after our chosen ag search terms were applied. General university databases that contain ag data included Colorado State University Digital Collections, University of Michigan ICPSR (Inter-university Consortium for Political and Social Research), and University of Minnesota DRUM (Digital Repository of the University of Minnesota). We then split out NCBI (National Center for Biotechnology Information) repositories. Next we searched the internet for open general data repositories using a variety of search engines, and repositories containing a mix of data, journals, books, and other types of records were tested to determine whether that repository could filter for data results after search terms were applied. General subject data repositories include Figshare, Open Science Framework, PANGEA, Protein Data Bank, and Zenodo. Finally, we compared scholarly journal suggestions for data repositories against our list to fill in any missing repositories that might contain agricultural data. Extensive lists of journals were compiled, in which USDA published in 2012 and 2016, combining search results in ARIS, Scopus, and the Forest Service's TreeSearch, plus the USDA web sites Economic Research Service (ERS), National Agricultural Statistics Service (NASS), Natural Resources and Conservation Service (NRCS), Food and Nutrition Service (FNS), Rural Development (RD), and Agricultural Marketing Service (AMS). The top 50 journals' author instructions were consulted to see if they (a) ask or require submitters to provide supplemental data, or (b) require submitters to submit data to open repositories. Data are provided for Journals based on a 2012 and 2016 study of where USDA employees publish their research studies, ranked by number of articles, including 2015/2016 Impact Factor, Author guidelines, Supplemental Data?, Supplemental Data reviewed?, Open Data (Supplemental or in Repository) Required? and Recommended data repositories, as provided in the online author guidelines for each the top 50 journals. Evaluation We ran a series of searches on all resulting general subject databases with the designated search terms. From the results, we noted the total number of datasets in the repository, type of resource searched (datasets, data, images, components, etc.), percentage of the total database that each term comprised, any dataset with a search term that comprised at least 1% and 5% of the total collection, and any search term that returned greater than 100 and greater than 500 results. We compared domain-specific databases and repositories based on parent organization, type of institution, and whether data submissions were dependent on conditions such as funding or affiliation of some kind. Results A summary of the major findings from our data review: Over half of the top 50 ag-related journals from our profile require or encourage open data for their published authors. There are few general repositories that are both large AND contain a significant portion of ag data in their collection. GBIF (Global Biodiversity Information Facility), ICPSR, and ORNL DAAC were among those that had over 500 datasets returned with at least one ag search term and had that result comprise at least 5% of the total collection. Not even one quarter of the domain-specific repositories and datasets reviewed allow open submission by any researcher regardless of funding or affiliation. See included README file for descriptions of each individual data file in this dataset. Resources in this dataset:Resource Title: Journals. File Name: Journals.csvResource Title: Journals - Recommended repositories. File Name: Repos_from_journals.csvResource Title: TDWG presentation. File Name: TDWG_Presentation.pptxResource Title: Domain Specific ag data sources. File Name: domain_specific_ag_databases.csvResource Title: Data Dictionary for Ag Data Repository Inventory. File Name: Ag_Data_Repo_DD.csvResource Title: General repositories containing ag data. File Name: general_repos_1.csvResource Title: README and file inventory. File Name: README_InventoryPublicDBandREepAgData.txt

Climate change has a profound impact on global agriculture, affecting crop yields, soil health, and farming sustainability. This synthetic dataset is designed to simulate real-world agricultural data, enabling researchers, data scientists, and policymakers to explore how climate variations influence food production across different regions.

🔍 Key Features: ✔️ Climate Variables – Simulated data on temperature changes, precipitation levels, and extreme weather events ✔️ Crop Productivity – Modeled impact of climate shifts on yields of key crops like wheat, rice, and corn ✔️ Regional Insights – Includes various geographic regions to analyze diverse climate-agriculture interactions ✔️ Ideal for Predictive Modeling – Supports climate risk assessment, food security studies, and sustainability research

📊 Dataset Overview: This dataset has been synthetically generated and does not contain real-world agricultural records. It is intended for academic learning, climate impact analysis, and machine learning applications in environmental studies.

📖 Columns Description: Region – Simulated geographic region Year – Modeled year of data collection Average_Temperature – Simulated temperature levels (°C) Precipitation – Modeled annual rainfall (mm) Crop_Yield – Synthetic yield data for selected crops (tons/hectare) Extreme_Weather_Events – Number of modeled extreme weather occurrences per year ⚠️ Disclaimer: This dataset is completely synthetic and should not be used for real-world climate policy decisions or agricultural forecasting. It is meant for educational purposes, research, and data science applications.

🔹 Use this dataset to analyze climate trends, build predictive models, and explore solutions for sustainable agriculture! 🌱📊

ABSTRACT Accurate crop data are essential for reliable irrigation water requirements (IWR) calculations, which can be acquired during the crop growth season for a given region using earth observation (EO) satellite time series. In addition, a relationship between crop coefficients and the NDVI can be established to allow for crop evapotranspiration estimation. The main objective of the present work was to develop a methodology, and its implementation in an application software, to extract crop parameters from EO image time series for a set of parcels of different types of crops, to be used as input data for a soil water balance model to compute IWR. The methodology was tested at two distinct test sites, the Vila Franca de Xira (site I) and Vila Velha de Ródão (site II) municipalities, Portugal. Landsat-7 and −8 images acquired from April to October 2013 were used for site I, while SPOT-5 Take-5 images from April to September 2015 were considered for site II. EO data were used to estimate the basal crop coefficients, planting dates, and crops growth stage lengths. Based on crop, soil and meteorological data, the IWR for the main crops of both test regions were estimated using the IrrigRotation model. The crop coefficient curves obtained from the EO data proved to be reliable for IWR estimation.

Calf Weighing Crates with Data Capture Market Outlook

According to our latest research, the global calf weighing crates with data capture market size reached USD 342.7 million in 2024, exhibiting robust momentum driven by increasing technological adoption in livestock management. The market is poised to grow at a CAGR of 7.2% from 2025 to 2033, with the forecasted market size projected to attain USD 644.5 million by 2033. This growth is primarily fueled by the rising emphasis on precision livestock farming, the need for enhanced productivity, and the integration of digital technologies for real-time data capture and analysis in cattle management.

One of the key growth factors for the calf weighing crates with data capture market is the escalating demand for precision livestock farming. As global food security concerns intensify, dairy and beef producers are under pressure to optimize herd health and productivity. Accurate weight monitoring of calves is essential for effective nutrition planning, disease detection, and growth tracking. Advanced weighing crates equipped with data capture capabilities allow for seamless integration with farm management software, enabling farmers to make informed decisions based on real-time analytics. This not only increases operational efficiency but also supports sustainable agricultural practices, thereby driving market expansion.

The proliferation of digital technologies in agriculture has further accelerated the adoption of automated and smart livestock management solutions. The advent of Internet of Things (IoT), wireless sensors, and cloud-based data analytics has transformed traditional weighing systems into intelligent platforms capable of capturing, storing, and analyzing large volumes of animal health and performance data. These digital advancements enable farmers to track calf growth trends, identify anomalies, and implement timely interventions, reducing mortality rates and improving overall herd profitability. Additionally, government support and incentives for the adoption of smart farming technologies, especially in developed regions, have significantly contributed to the growth trajectory of the calf weighing crates with data capture market.

Another pivotal growth driver is the increasing awareness and implementation of animal welfare standards. Regulatory bodies and industry associations worldwide are advocating for improved livestock handling practices, which include the use of humane and efficient weighing systems. Automated weighing crates with data capture minimize animal stress by reducing manual handling and ensuring accurate monitoring. This not only enhances animal welfare but also aligns with consumer preferences for ethically sourced dairy and beef products. As a result, both large-scale commercial farms and smaller operations are investing in modern weighing solutions, further propelling market growth.

From a regional perspective, North America and Europe continue to dominate the calf weighing crates with data capture market due to their advanced agricultural infrastructure and early adoption of precision farming technologies. However, the Asia Pacific region is emerging as a lucrative market, driven by rapid urbanization, increasing dairy and beef consumption, and governmental initiatives to modernize the livestock sector. Countries such as China, India, and Australia are witnessing robust investments in smart agriculture, which is anticipated to further boost market growth across the region. Meanwhile, Latin America and the Middle East & Africa are gradually embracing these technologies, presenting significant untapped opportunities for market players.

Product Type Analysis

The product type segment of the calf weighing crates with data capture market is broadly categorized into manual weighing crates and automated weighing crates. Manual weighing crates, while traditional, remain prevalent in regions with limited access to advanced technology or where small-scale farms dominate. These crates are valued for their cost-effectiveness and simplicity of operation, making them suitable for emerging markets and rural areas. However, manual crates often require more labor and time, and the risk of human error during data recording can compromise the accuracy of weight measurements and subsequent data analysis.

Automated weighing crates, on the other hand, are rapidly gaining traction,

Abstract

Syngenta is committed to increasing crop productivity and to using limited resources such as land, water and inputs more efficiently. Since 2014, Syngenta has been measuring trends in agricultural input efficiency on a global network of real farms. The Good Growth Plan dataset shows aggregated productivity and resource efficiency indicators by harvest year. The data has been collected from more than 4,000 farms and covers more than 20 different crops in 46 countries. The data (except USA data and for Barley in UK, Germany, Poland, Czech Republic, France and Spain) was collected, consolidated and reported by Kynetec (previously Market Probe), an independent market research agency. It can be used as benchmarks for crop yield and input efficiency.

Geographic coverage

National coverage

Analysis unit

Agricultural holdings

Kind of data

Sample survey data [ssd]

Sampling procedure

A. Sample design Farms are grouped in clusters, which represent a crop grown in an area with homogenous agro- ecological conditions and include comparable types of farms. The sample includes reference and benchmark farms. The reference farms were selected by Syngenta and the benchmark farms were randomly selected by Kynetec within the same cluster.

B. Sample size Sample sizes for each cluster are determined with the aim to measure statistically significant increases in crop efficiency over time. This is done by Kynetec based on target productivity increases and assumptions regarding the variability of farm metrics in each cluster. The smaller the expected increase, the larger the sample size needed to measure significant differences over time. Variability within clusters is assumed based on public research and expert opinion. In addition, growers are also grouped in clusters as a means of keeping variances under control, as well as distinguishing between growers in terms of crop size, region and technological level. A minimum sample size of 20 interviews per cluster is needed. The minimum number of reference farms is 5 of 20. The optimal number of reference farms is 10 of 20 (balanced sample).

C. Selection procedure The respondents were picked randomly using a “quota based random sampling” procedure. Growers were first randomly selected and then checked if they complied with the quotas for crops, region, farm size etc. To avoid clustering high number of interviews at one sampling point, interviewers were instructed to do a maximum of 5 interviews in one village.

BF Screened from Philippines were selected based on the following criterion: (a) smallholder rice growers Location: Luzon - Mindoro (Southern Luzon) mid-tier (sub-optimal CP/SE use): mid-tier growers use generic CP, cheaper CP, non hybrid (conventional) seeds
Smallholder farms with average to high levels of mechanization
Should be Integrated Pest Management advocates
less accessible to technology: poor farmers, don't have the money to buy quality seeds, fertilizers,... Don't use machinery yet
simple knowledge on agronomy and pests
influenced by fellow farmers and retailers
not strong financial status: don't have extra money on bank account and so need longer credit to pay (as a consequence: interest increases) may need longer credit

Mode of data collection

Face-to-face [f2f]

Research instrument

Data collection tool for 2019 covered the following information:

(A) PRE- HARVEST INFORMATION

PART I: Screening PART II: Contact Information PART III: Farm Characteristics a. Biodiversity conservation b. Soil conservation c. Soil erosion d. Description of growing area e. Training on crop cultivation and safety measures PART IV: Farming Practices - Before Harvest a. Planting and fruit development - Field crops b. Planting and fruit development - Tree crops c. Planting and fruit development - Sugarcane d. Planting and fruit development - Cauliflower e. Seed treatment

(B) HARVEST INFORMATION

PART V: Farming Practices - After Harvest a. Fertilizer usage b. Crop protection products c. Harvest timing & quality per crop - Field crops d. Harvest timing & quality per crop - Tree crops e. Harvest timing & quality per crop - Sugarcane f. Harvest timing & quality per crop - Banana g. After harvest PART VI - Other inputs - After Harvest a. Input costs b. Abiotic stress c. Irrigation

See all questionnaires in external materials tab.

Cleaning operations

Data processing:

Kynetec uses SPSS (Statistical Package for the Social Sciences) for data entry, cleaning, analysis, and reporting. After collection, the farm data is entered into a local database, reviewed, and quality-checked by the local Kynetec agency. In the case of missing values or inconsistencies, farmers are re-contacted. In some cases, grower data is verified with local experts (e.g. retailers) to ensure data accuracy and validity. After country-level cleaning, the farm-level data is submitted to the global Kynetec headquarters for processing. In the case of missing values or inconsistences, the local Kynetec office was re-contacted to clarify and solve issues.

Quality assurance Various consistency checks and internal controls are implemented throughout the entire data collection and reporting process in order to ensure unbiased, high quality data.

• Screening: Each grower is screened and selected by Kynetec based on cluster-specific criteria to ensure a comparable group of growers within each cluster. This helps keeping variability low.

• Evaluation of the questionnaire: The questionnaire aligns with the global objective of the project and is adapted to the local context (e.g. interviewers and growers should understand what is asked). Each year the questionnaire is evaluated based on several criteria, and updated where needed.

• Briefing of interviewers: Each year, local interviewers - familiar with the local context of farming -are thoroughly briefed to fully comprehend the questionnaire to obtain unbiased, accurate answers from respondents.

• Cross-validation of the answers: o Kynetec captures all growers' responses through a digital data-entry tool. Various logical and consistency checks are automated in this tool (e.g. total crop size in hectares cannot be larger than farm size) o Kynetec cross validates the answers of the growers in three different ways: 1. Within the grower (check if growers respond consistently during the interview) 2. Across years (check if growers respond consistently throughout the years) 3. Within cluster (compare a grower's responses with those of others in the group) o All the above mentioned inconsistencies are followed up by contacting the growers and asking them to verify their answers. The data is updated after verification. All updates are tracked.

• Check and discuss evolutions and patterns: Global evolutions are calculated, discussed and reviewed on a monthly basis jointly by Kynetec and Syngenta.

• Sensitivity analysis: sensitivity analysis is conducted to evaluate the global results in terms of outliers, retention rates and overall statistical robustness. The results of the sensitivity analysis are discussed jointly by Kynetec and Syngenta.

• It is recommended that users interested in using the administrative level 1 variable in the location dataset use this variable with care and crosscheck it with the postal code variable.

Data appraisal

Due to the above mentioned checks, irregularities in fertilizer usage data were discovered which had to be corrected:

For data collection wave 2014, respondents were asked to give a total estimate of the fertilizer NPK-rates that were applied in the fields. From 2015 onwards, the questionnaire was redesigned to be more precise and obtain data by individual fertilizer products. The new method of measuring fertilizer inputs leads to more accurate results, but also makes a year-on-year comparison difficult. After evaluating several solutions to this problems, 2014 fertilizer usage (NPK input) was re-estimated by calculating a weighted average of fertilizer usage in the following years.

Crop Health and Environmental Stress Dataset Dataset Overview: The Crop Health and Environmental Stress Dataset is a real-world dataset collected from multiple agricultural regions in Netherlands to facilitate research in precision agriculture, crop health monitoring, and environmental stress analysis. It integrates multispectral imaging, environmental conditions, soil health parameters, and pest activity indicators to provide a holistic view of crop conditions.

The dataset contains 212,019 records, collected through satellite imagery, UAV-based remote sensing, weather stations, and on-field sensors across diverse agricultural landscapes. It aims to support the development of machine learning (ML) and deep learning (DL) models for crop health classification, yield prediction, and early detection of plant stress.

Purpose of the Dataset Crop Health Prediction: Identify healthy vs. unhealthy crops based on multispectral and thermal imaging. Pest & Weed Monitoring: Analyze pest infestations and weed presence affecting plant growth. Environmental Stress Analysis: Evaluate the impact of soil, climate, and water availability on plant health. Remote Sensing Applications: Leverage UAV and satellite imagery for agricultural research. Decision Support for Farmers: Develop automated decision-making systems for smart agriculture. Data Collection Methodology This dataset was obtained from multiple agricultural research centers, field surveys, and remote sensing platforms. The data sources include:

Multispectral and Thermal Cameras (UAVs & Satellite Imagery) Field Sensors & Weather Stations (Soil moisture, pH, temperature, humidity) Manual Crop Inspections & Yield Estimates (Human-labeled data) Geospatial Data Processing (NDVI, SAVI, Chlorophyll Content, etc.) All data has been preprocessed and cleaned, ensuring high reliability for ML/DL applications.

Feature Description Each record consists of multiple environmental, remote sensing, and biological factors affecting crop health. Below is a detailed breakdown of all features:

1. Remote Sensing Features Feature Name Description Data Type High_Resolution_RGB Availability of high-resolution RGB images (1 = Yes, 0 = No) Binary Multispectral_Images Presence of multispectral satellite imagery (1 = Yes, 0 = No) Binary Thermal_Images Usage of thermal imaging to analyze crop temperature variations (1 = Yes, 0 = No) Binary Temporal_Images Availability of time-series crop images (1 = Yes, 0 = No) Binary Spatial_Resolution Spatial resolution of the captured image (in meters) Float GPS_Coordinates Unique field location identifiers based on GPS mapping Integer
2. Environmental & Geospatial Features Feature Name Description Data Type Field_Boundaries Categorized field boundary types (1, 2, 3) Categorical Elevation_Data Altitude of the agricultural plot (in meters) Float Canopy_Coverage Percentage of plant canopy coverage over soil Float NDVI Normalized Difference Vegetation Index (0 to 1 scale) Float SAVI Soil-Adjusted Vegetation Index for correcting soil effects Float Chlorophyll_Content Chlorophyll level measurement to assess crop health Float Leaf_Area_Index Ratio of total leaf area per ground area unit Float Crop_Stress_Indicator Stress level assessment (0 = No Stress, 100 = Extreme Stress) Integer
3. Weather & Soil Features Feature Name Description Data Type Temperature Temperature (°C) recorded at the field location Float Humidity Relative humidity (%) in the agricultural environment Float Rainfall Precipitation levels (mm) measured over a period Float Wind_Speed Wind speed (m/s) affecting plant structure Float Soil_Moisture Soil water retention percentage Float Soil_pH pH level of the soil sample collected Float Organic_Matter Organic carbon and nutrients present in soil (g/kg) Float
4. Crop & Pest Features Feature Name Description Data Type Pest_Hotspots Indicator for pest-affected areas (1 = Yes, 0 = No) Binary Weed_Coverage Percentage of weed coverage in the field Float Pest_Damage Severity of pest damage on crops (0-100) Integer Crop_Growth_Stage Growth phase of the crop (1 = Early, 2 = Vegetative, 3 = Flowering, 4 = Maturity) Categorical Expected_Yield Predicted yield of the crop (kg/ha) Float Crop_Type Type of cultivated crop (e.g., Wheat, Maize, Rice) Categorical
5. Ground Truth & Prediction Features Feature Name Description Data Type Ground_Truth_Segmentation Whether ground truth labels are available (1 = Yes, 0 = No) Binary Bounding_Boxes Number of detected objects in a satellite image Integer Water_Flow Water availability for irrigation (L/s) Float Drainage_Features Presence of drainage features (1 = Yes, 0 = No) Binary
6. Target Variable (Label) Feature Name Description Data Type Crop_Health_Label Target variable indicating crop condition (0 = Unhealthy, 1 = Healthy) Binary Data Distribution & Characteristics Total Records: 212,01...

Abstract

The main objective of the Seasonal Agricultural Survey is to provide timely, accurate, reliable and comprehensive agricultural statistics that describe the structure of agriculture in Rwanda mainly in terms of land use, crop area, yield and crop production to monitor current agricultural and food supply conditions and to facilitate evidence-based decision making for the development of the agricultural sector.

The National Institute of Statistics of Rwanda (NISR) has been conducting an annual agricultural survey since November 2012 for the estimation of the national agricultural crop area and production estimates. In 2019/2020 agricultural year, the NISR conducted the second edition of theUpgraded Seasonal Agricultural Survey (USAS) covering the three agricultural seasons. The USAS incorporated an increased sample size to provide more precise estimates. The USAS allows information for monitoring progress on agriculture programs and policies in Rwanda.

Geographic coverage

National coverage allowing district-level estimation of key indicators

Analysis unit

This seasonal agriculture survey focused on the following units of analysis: Small scale agricultural farms and large scale farms

Universe

The SAS 2020 targeted potential agricultural land and large scale farmers

Kind of data

Sample survey data [ssd]

Frequency of data collection

Seasonal

Sampling procedure

Out of 5 defined agricultural strata, only dominant hill crop land stratum, dominant wetland crops stratum, dominant rangeland stratum and mixed stratum were considered as land potential for agriculture. The remaining stratum is the non-agricultural land. Note that clusters covered by tea plantations were not considered in the area sample frame due to reasons stated above. Thus, SAS is conducted on 4 above mentioned strata to cover other major crops. In 2020 agricultural year, the sample of segments was increased in order to improve agriculture statistics where sample increased from 780 (sample used from 2018 to 2019) to 1200 segments. At first stage,1200 segments were selected and allocated at district level based on the power allocation approach (Bankier3, 1988). Sampled segments inside each district were distributed among strata with a proportional-to-area criterion.

At second stage, 25 sample points were systematically selected, following a special distance of 60 meters between points. Sample points are reporting units within each segment, where enumerators go to every point, locate and delineate plots in which the sample points fall, and collect records of land use and related information. The recorded information represents the characteristics of the whole segment which are extrapolated to the stratum level and hence the combination of strata within each district provides district area related statistics.

Mode of data collection

Face-to-face [f2f]

Research instrument

There were two types of questionnaires used for this survey namely screening questionnaire and plot questionnaire. A Screening questionnaire was used to collect information that enabled identification of a plot and its land use using the plot questionnaire. For point-sampling, the plot questionnaire is concerned with the collection of data on characteristics of crop identification, crop production and use of production, inputs (seeds, fertilizers and pesticides), agricultural practices and land tenure. All the surveys questionnaires used were published in English.

Cleaning operations

The CAPI method of data collection allows the enumerators in the field to collect and enter data with their tablets and then synchronize to the server at headquarters where data are received by NISR staff, checked for consistency at NISR and thereafter transmitted to analysts for tabulation using STATA software, and reporting using office Excel and word as well.

Response rate

Data collection was done in 780 segments and 222 large scale farmers holdings for Season A, whereas in Season C data was collected in 232 segments, response rate was 100% of the sample.

This data set is provided by EOS-EARTHDATA (formerly EOS-Webster). It provides acreage, production and yield statistics for U.S. field crops from the National Agricultural Statistical Service (NASS) for the years 1970 through 2003. Data can be subset by irrigated and non-irrigated areas. Sucrose content, where applicable, is also included. Data are at the county scale and include all counties in the conterminous USA. No spatial subsets are available. For more information, see the Data Guide. Data after 2003 may be obtained from NASS.

Abstract

This agricultural census took place in 2012. The execution of this project is conferred to the Agricultural Statistic Service (DSID) of the Ministry of Agriculture, Livestock and Fishery. The project execution personnel include the department of the Ministry of Agriculture and the National Institute of Statistic. These personnel are divided into two committees: the national committee in charge of financial and monitoring aspects of the project, and the technical committee in charge of technical execution of the project.The 2012 census of agriculture will be completed with a current survey programme based on a sample of 2000 agricultural holdings. Agricultural information will be collected through a set of six questionnaires developed for the circumstance. This set of questionnaires includes:

• Livestock questionnaire
• Agricultural holdings and plots cultivated questionnaire
• Crops harvested questionnaire
• Crops yields questionnaire
• Price received by agricultural producers questionnaire
• Pluviometric information questionnaire

Geographic coverage

National coverage

Analysis unit

Households

Universe

The statistical unit is the agricultural holding, defined as an economic unit of agricultural production comprising all livestock kept and all land wholly or partially used by one or more persons, for agricultural production purposes, without regard to title or size, and is subject to a single management. The CA 2012-2014 covered only the agricultural holdings in the household sector ("agricultural households"). An agricultural household is a household in which one or more members are involved in own-account agricultural production.

Kind of data

Census/enumeration data [cen]

Sampling procedure

i. Survey design Core census module data collection has been carried out through complete enumeration while the 2012 agricultural census is carried out by sample enumeration.

ii. Stratification - agricultural census survey A survey design at two degrees was applied. The stratum at first degree is formed by the administrative divisions of the country including a total of 35 prefectures and one under prefecture. At secondary degree, a stratification has been operated among the agricultural holdings according to agricultural activity practiced (agriculture alone, agriculture and breeding, breeding alone) in the concern to reduce sampling error. The primary units (PU) are the enumeration areas (EA) derived from the 2010 Population Census drawn with probability proportional to their population size (Random replicated selection). The secondary units (SU) are the agricultural holdings drawn with equal probability at the rate of 6 holdings per PU. The complete list of all PU (2 000 PU and 9 000 agricultural holdings) derived from the pre census data. The distribution of the sample of the PU within the prefectures is proportional to the size (population) of the prefecture. In order to avoid small sizes, the minimum weight of primary units is fixed at 25 PU.

Mode of data collection

Face-to-face [f2f]

Research instrument

The CA used seven questionnaires: one for the core module and six for the supplementary module and thematic surveys. The main module included:

1. Agricultural holding questionnaire:

• Gender of the head of the family
• His marital status
• Level of education
• Size of the family (number of men and women)
• Agricultural activities practiced by members of the family
• Non agricultural activities practicedby members of the family
• Number of agricultural actives (men and women) on the holdings
• Number of plots cultivated
• Presence of irrigation
• Temporary crops planted (cereals, tubers and leguminous plants)
• Tree crops (coffee, cocoa, cotton, Palme oil tree etc)
• Fruit trees
• Livestock (cattle, goat, sheep, pigs and poultry)
• Silviculture (number of plots)
• Practice of fishery
• Number of agricultural materials
• Number of persons in the holding having a bank account (men and women)
• Area cultivated ( declaration)

1. Community data questionnaire:

• Infrastructures
• Natural resources of the village
• Forestry site of the village
• Cost of land
• Social and economic organization of the village
• Localization and identification of herds
• Market garden
• Localization and identification of piscicultural ponds
• Main difficulties connected to agricultural production
• Livestock and market selling

In addition, the rural community survey questionnaire was used for community-level data collection. The CA questionnaires covered 15 of the 16 core items recommended for the WCA 2010 round. The core item "Legal status of agricultural holder" was not covered by the CA.

Cleaning operations

1. DATA ENTRY ORGANIZATION Data capture operations was at first organized on 15 Micro computers and then on 40 at the headquarters of DSID. The capture was done through CSPro package and data processing through SPSS. A total of 60 data keying operators have been deployed for the pre census data, including the basic module and the community data. This number of data capture operators has been brought to 170 for the complementary module. In the concern to lighten files balancing, control programmes have been incorporated at different levels of data capture programme, including:

• exhaustiveness control consisting of units checking (enumeration zones, holdings, plots yields, etc) are incorporated • likelihood control ensuring data captured within the likely intervals • consistency control

1. TABULATION Main objectives of data tabulation are to provide complete characteristics of the Togolese agriculture through the census. Most important cross tabulations are developed on:

• Agricultural household • Housing • Total and active population • Crops Land occupation • Livestock • Agricultural materials and equipment • Motorized materials using • Labor force • Dependence and agricultural credits • Yields and destination of the agricultural production

1. DATA QUALITY The layout of the 2012 agricultural census from the stage of the technical preparation, with a sample drawing procedure minimizing sampling error, to the implementation stage, characterized by reinforced monitoring and counter surveys have permitted to improve results quality.