About the Dataset

AI-Driven Agricultural Optimization: Sustainable Farming Insights

This dataset is designed to support the development of a multi-agent AI system aimed at optimizing farming practices while promoting sustainability. It integrates data from farmers, weather stations, and market trends to enable AI-driven decision-making for resource-efficient and profitable agriculture.

Dataset Composition

• Farmer Data: Land characteristics, crop preferences, financial constraints, and past yield records.
• Weather & Soil Data: Rainfall, temperature, humidity, soil moisture, and other climate-related variables affecting crop growth.
• Market Trends: Regional crop pricing, demand forecasts, and trade patterns to help farmers maximize profits.
• Sustainability Metrics: Water usage, pesticide application, carbon footprint, and soil health indicators for eco-friendly farming recommendations.

This dataset serves as a foundation for building intelligent AI solutions that help reduce environmental impact, optimize agricultural resources, and enhance farmers' decision-making.

The dataset you've provided appears to capture agricultural data for Karnataka, specifically focusing on crop yields in Mangalore. Key features include the year of production, geographic details, and environmental conditions such as rainfall (measured in mm), temperature (in degrees Celsius), and humidity (as a percentage). Soil type, irrigation method, and crop type are also recorded, along with crop yields, market price, and season of growth (e.g., Kharif).

The dataset includes several columns related to crop production conditions and outcomes. For example, coconut crop data reveals a pattern of yields over different area sizes, showing how factors like rainfall, temperature, and irrigation influence production. Prices also vary, offering insights into the economic aspects of agriculture in the region. This information could be used to study the impact of environmental conditions and farming techniques on crop productivity, assisting in the development of optimized agricultural practices tailored for specific soil types, climates, and crop needs.

These files from Statistics Canada present Census of Agriculture data allocated by standard census geographic polygons: Provinces and Territories (PR), Census Agricultural Regions (CAR), Census Divisions (CD) and Census Consolidated Subdivisions (CCS). Five datasets are provided: 1. Agricultural operation characteristics: includes information on farm type, operating arrangements, paid agricultural work and financial characteristics of the agricultural operation. 2. Land tenure and management practices: includes information on land use, land tenure, agricultural practices, land inputs, technologies used on the operation and the renewable energy production on the operation. 3. Crops: includes information on hay and field crops, vegetables (excluding greenhouse vegetables), fruits, berries, nuts, greenhouse productions and other crops. 4. Livestock, poultry and bees: includes information on livestock, poultry and bees. 5. Characteristics of farm operators: includes information on age, sex and the hours of works of farm operators. Note: For all the datasets, confidential values have been assigned a value of -1. Correction notice: On January 18, 2023, selected estimates have been corrected for selected variables in the following 2021 Census of Agriculture domains: Direct sales of agricultural products to consumers (Agricultural operations category), Succession plan for the agricultural operation (Agricultural operators category), and Renewable energy production (Use, tenure and practices category).

Quick Stats is the National Agricultural Statistics Service's (NASS) online, self-service tool to access complete results from the 1997, 2002, 2007, and 2012 Censuses of Agriculture as well as the best source of NASS survey published estimates. The census collects data on all commodities produced on U.S. farms and ranches, as well as detailed information on expenses, income, and operator characteristics. The surveys that NASS conducts collect information on virtually every facet of U.S. agricultural production.

Source Data with Authors

In the master's thesis research conducted by student Mohammed Ismail Lifta (2023-2024) at the Department of Computer Science, College of Computer Science and Mathematics- Tikrit University,Iraq.Data were collected from the Agriculture Lab on plants that grow in a IoT greenhouse and Traditional greenhouse .The study was supervised by Professor (Assistant) Wisam Dawood Abdullah, administrator of Cisco Networking Academy / Tikrit University.

Dataset Description

The dataset "Advanced_IoT_Dataset.csv" consists of 30,000 entries and 14 columns. Below are the detailed descriptions of each column:

Random: An identifier for each record, likely indicating a random sample or batch (object type). Average of chlorophyll in the plant (ACHP): The average chlorophyll content in the plant (float type). Plant height rate (PHR): The rate of plant height growth (float type). Average wet weight of the growth vegetative (AWWGV): The average wet weight of vegetative growth (float type). Average leaf area of the plant (ALAP): The average leaf area of the plant (float type). Average number of plant leaves (ANPL): The average number of leaves per plant (float type). Average root diameter (ARD): The average diameter of the plant's roots (float type). Average dry weight of the root (ADWR): The average dry weight of the plant's roots (float type). Percentage of dry matter for vegetative growth (PDMVG): The percentage of dry matter in vegetative growth (float type). Average root length (ARL): The average length of the plant's roots (float type). Average wet weight of the root (AWWR): The average wet weight of the plant's roots (float type). Average dry weight of vegetative plants (ADWV): The average dry weight of vegetative parts of the plant (float type). Percentage of dry matter for root growth (PDMRG): The percentage of dry matter in root growth (float type). Class: The class or category to which the plant record belongs (object type).

More detailed description of the columns in the dataset:

Random: A categorical identifier for each record. This column appears to have values like R1, R2, and R3, which could represent different random samples.

Average of chlorophyll in the plant (ACHP): This column contains float values representing the average chlorophyll content in the plant. Chlorophyll is vital for photosynthesis, and its measurement can indicate the health and efficiency of the plant in converting light energy into chemical energy.

Plant height rate (PHR): This column contains float values representing the rate of growth in the height of the plant. This metric is essential for understanding the vertical growth dynamics of the plant over time.

Average wet weight of the growth vegetative (AWWGV): This column contains float values representing the average wet weight of the vegetative parts of the plant. Wet weight can be an indicator of the water content and overall biomass of the plant's vegetative growth.

Average leaf area of the plant (ALAP): This column contains float values representing the average leaf area of the plant. Leaf area is a critical factor in photosynthesis, as it determines the surface area available for light absorption.

Average number of plant leaves (ANPL): This column contains float values representing the average number of leaves per plant. The number of leaves can correlate with the plant's ability to perform photosynthesis and its overall health.

Average root diameter (ARD): This column contains float values representing the average diameter of the plant's roots. Root diameter can affect the plant's ability to absorb water and nutrients from the soil.

Average dry weight of the root (ADWR): This column contains float values representing the average dry weight of the plant's roots. Dry weight is a measure of the plant's biomass after removing water content and is an indicator of the root's structural and storage capacity.

Percentage of dry matter for vegetative growth (PDMVG): This column contains float values representing the percentage of dry matter in the vegetative parts of the plant. This metric indicates the proportion of the plant's biomass that is not water, which can be crucial for understanding its structural and nutritional status.

Average root length (ARL): This column contains float values representing the average length of the plant's roots. Root length can influence the plant's ability to explore and absorb nutrients and water from the soil.

Average wet weight of the root (AWWR): This column contains float values representing the average wet weight of the plant's roots. Wet weight includes the water content in the roots, indicating their overall biomass and water retention capacity.

Average dry weight of vegetative plants (ADWV): This column contains float values representing the average dry weight of the vegetative parts of the plant. This me...

NASS USDA estimates the irrigated croplands at county level every five years. But this estimation does not provide the geospatial information of the irrigated croplands. To provide a comprehensive, consistent, and timely geospatially detailed information about irrigated cropland conterminous U.S. (CONUS), the “Moderate Resolution Imaging Spectroradiometer (MODIS) Irrigated Agriculture Dataset for the United States (MIrAD-US)” product was produced by the U.S. Geological Survey (USGS) Earth Resources Observation and Science (EROS) Center with funding from several USGS programs (National Land Imaging and National Water-Quality Assessment). A primary objective was to identify, and map irrigated agricultural areas to factor into water quality studies and drought monitoring investigations. This product uses three primary data inputs, (a) USDA county-level irrigation area statistics for 2002, (b) annual peak eMODIS Normalized Difference Vegetation Index (NDVI), and (c) a land cover mask for agricultural lands derived from NLCD to map the spatial distribution of irrigated lands across the conterminous United States. The MIrAD Version 4 offers the datasets for the years 2002, 2007, 2012, and 2017 at 250-m and 1-km spatial resolutions. The validation of MIrAD-US is a challenge because no other single-source current datasets are available at a national scale for comparison. Thus, this dataset should be considered provisional until a formal accuracy assessment can be completed. The product update is planned for every 5 years, synchronized with the update of the Census of Agriculture by the U.S Department of Agriculture (USDA) but contingent upon availability of Collection 6 (C6) Aqua eMODIS data and funding.

IOT Agriculture

## Overview

IOT Agriculture is a dataset for object detection tasks - it contains Insect Pest annotations for 547 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Data on Agriculture and Agricultural Related Information in Ghana

Precision Agriculture

## Overview

Precision Agriculture is a dataset for semantic segmentation tasks - it contains Precise Maps annotations for 4,121 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

season

Demographic, occupational, and economic information for over 21,000 rural households in the northern United States in 1860 are presented in this dataset. The data were obtained from the manuscript agricultural and population schedules of the 1860 United States Census and are provided for all households in a single township from each of 102 randomly-selected counties in sixteen northern states. Variables in the dataset include farm values, livestock, and crop production figures for the households which owned or operated farms (over half the households sampled), as well as value of real and personal estate, color, sex, age, literacy, school attendance, occupation, place of birth, and parents' nationality of all individuals residing in the sampled townships.

The primary greenhouse gas (GHG) sources for agriculture are nitrous oxide (N2O) emissions from cropped and grazed soils, methane (CH4) emissions from ruminant livestock production and rice cultivation, and CH4 and N2O emissions from managed livestock waste. The management of cropped, grazed, and forestland has helped offset GHG emissions by promoting the biological uptake of carbon dioxide (CO2) through the incorporation of carbon into biomass, wood products, and soils, yielding a U.S. net emissions of 5,903 MMT CO2 eq (million metric tonnes of carbon dioxide equivalents). Net emissions equate to total greenhouse gas emissions minus CO2 sequestration in growing forests, wood products, and soils. The report 'U.S. Agriculture and Forestry Greenhouse Gas Inventory: 1990-2018' serves to estimate U.S. GHG emissions for the agricultural sector, to quantify uncertainty in emission estimates, and to estimate the potential of agriculture to mitigate U.S. GHG emissions. This dataset contains tabulated data from the figures and tables presented in Chapter 5, Energy Use in Agriculture, of the report. Data are presented for carbon dioxide emissions from on-farm energy use. Please refer to the report for full descriptions of and notes on the data. Resources in this dataset:Resource Title: Table 5-1. File Name: Table5_1.csvResource Description: Energy Use and Carbon Dioxide Emissions by Fuel Source on U.S. Farms, 2018. Energy consumed is shown in the table as QBTU (quadrillion British thermal units). Carbon content is displayed as MMT C/QBTU (million metric tons carbon per quadrillion British thermal units). Emissions are shown as Tg CO2 eq. (teragrams carbon dioxide equivalent). Resource Title: Data for Figure 5-1. File Name: Figure5_1.csvResource Description: CO2 Emissions From Energy Use in Agriculture, by State, 2018 in MMT CO2 eq. (million metric tons carbon dioxide equivalent).Resource Title: Data for Figure 5-2. File Name: Figure5_2.csvResource Description: Energy use in agriculture, by source, 1965–2018 in QBTU (quadrillion British thermal units).Resource Title: Data for Figure 5-3. File Name: Figure5_3.csvResource Description: CO2 Emissions from Energy Use in Agriculture, by Fuel Source, 2001, 2005, 2008, 2013, and 2018 in MMT CO2 eq. (million metric tons carbon dioxide equivalent).Resource Title: Chapter 5 tables and figures. File Name: Chapter 5 data.zip

1, Chinese Academy of Agricultural Sciences, Document No. 1 of the Central Committee of China and Ministry of Agriculture and Rural Affairs of the People's Republic of China contain the original collection of relevant datasets. 2, The file Agricultural policy intensity dataset contains four contents, all of which are datasets obtained from the study of the paper "China's Agricultural Policy Intensity from 1982 to 2023". Chinese Academy of Agricultural Sciences file score collection. Chinese Academy of Agricultural Sciences file score collection.xlsx folder contains the scores of agricultural policy documents related to the Chinese Academy of Agricultural Sciences. collection of Central No.1 File Scores.xlsx folder contains the scores of policy documents related to the Central No.1 Document. Collection of Ministry of Agriculture and Rural Documentation scores.xlsx folder, contains scores corresponding to agricultural policy documents of the Ministry of Agriculture and Rural Affairs of China. Chinese Agricultural Policy Corpus and its scores.xlsx file contains the corpus of agricultural policies generated in the study "China's Agricultural Policy Intensity from 1982 to 2023" and the quantitative values of the corresponding words. 3, In the code folder, two files are included: corpus_building_code.docx and stop_words.txt. where corpus_building_code.docx contains the corpus building code for this paper, and stop_words.txt contains the stop words in the data preprocessing phase of the file. The whole code is in python language and runs on jupyter.

A collection of over 75 charts and maps presenting key statistics on the farm sector, food spending and prices, food security, rural communities, the interaction of agriculture and natural resources, and more.

How much do you know about food and agriculture? What about rural America or conservation? ERS has assembled more than 75 charts and maps covering key information about the farm and food sectors, including agricultural markets and trade, farm income, food prices and consumption, food security, rural economies, and the interaction of agriculture and natural resources.

How much, for example, do agriculture and related industries contribute to U.S. gross domestic product? Which commodities are the leading agricultural exports? How much of the food dollar goes to farmers? How do job earnings in rural areas compare with metro areas? How much of the Nation’s water is used by agriculture? These are among the statistics covered in this collection of charts and maps—with accompanying text—divided into the nine section titles.This record was taken from the USDA Enterprise Data Inventory that feeds into the https://data.gov catalog. Data for this record includes the following resources: Ag and Food Sectors and the Economy Land and Natural Resources Farming and Farm Income Rural Economy Agricultural Production and Prices Agricultural Trade Food Availability and Consumption Food Prices and Spending Food Security and Nutrition Assistance For complete information, please visit https://data.gov.

The total collected data consists of 3,156 images categorized into 10 different types of pests and diseases on rice. Additionally, this data has been analyzed and evaluated by from Cuu Long Delta Rice Research Institute

The STRIVE project, funded by USAID's Displaced Children and Orphans Fund (DCOF) and managed by FHI 360, used market-led economic strengthening initiatives to improve the well-being of vulnerable children. Through STRIVE, ACDI/VOCA implemented the Agriculture for Children’s Empowerment (ACE) Project in Liberia, which is founded on the premise that increased household economic security will stimulate more consistent investments in children’s well being via longer term social investments in education and nutrition. ACE’s primary focus was on the horticulture value chain (VC) — the production and marketing of vegetables by smallholder farmers in Montserrado, Bong, and Nimba counties of Liberia. ACE also strengthened smallholder rice farming to increase household food security using a market-sensitive approach to rice seed lending and cultivation. This dataset contains endline information about each plot the household owns.

Agricultural Production: Vegetable: Industrial Crops: Industrial Tomatoes data was reported at 23,241,754.000 Quintal in 2020. This records an increase from the previous number of 19,312,672.000 Quintal for 2019. Agricultural Production: Vegetable: Industrial Crops: Industrial Tomatoes data is updated yearly, averaging 4,218,705.000 Quintal from Dec 1975 (Median) to 2020, with 46 observations. The data reached an all-time high of 23,241,754.000 Quintal in 2020 and a record low of 87,999.000 Quintal in 2014. Agricultural Production: Vegetable: Industrial Crops: Industrial Tomatoes data remains active status in CEIC and is reported by Ministry of Agriculture and Rural Development. The data is categorized under Global Database’s Algeria – Table DZ.B006: Agricultural Production .

Ghana Compact - Agriculture - Post-Harvest

The Census of Agriculture provides a detailed picture every five years of U.S. farms and ranches and the people who operate them. Conducted by USDA's National Agricultural Statistics Service, the 2012 Census of Agriculture collected more than six million data items directly from farmers. The Ag Census Web Maps application makes this information available at the county level through a few clicks. The maps and accompanying data help users visualize, download, and analyze Census of Agriculture data in a geospatial context. Resources in this dataset:Resource Title: Ag Census Web Maps. File Name: Web Page, url: https://www.nass.usda.gov/Publications/AgCensus/2012/Online_Resources/Ag_Census_Web_Maps/Overview/index.php/ The interactive map application assembles maps and statistics from the 2012 Census of Agriculture in five broad categories:

Crops and Plants – Data on harvested acreage for major field crops, hay, and other forage crops, as well as acreage data for vegetables, fruits, tree nuts, and berries. Economics – Data on agriculture sales, farm income, government payments from conservation and farm programs, amounts received from loans, a broad range of production expenses, and value of buildings and equipment. Farms – Information on farm size, ownership, and Internet access, as well as data on total land in farms, land use, irrigation, fertilized cropland, and enrollment in crop insurance programs. Livestock and Animals – Statistics on cattle and calves, cows and heifers, milk cows, and other cattle, as well as hogs, sheep, goats, horses, and broilers. Operators – Statistics on hired farm labor, tenure, land rented or leased, primary occupation of farm operator, and demographic characteristics such as age, sex, race/ethnicity, and residence location.

The Ag Census Web Maps application allows you to:

Select a map to display from a the above five general categories and associated subcategories. Zoom and pan to a specific area; use the inset buttons to center the map on the continental United States; zoom to a specific state; and show the state mask to fade areas surrounding the state. Create and print maps showing the variation in a single data item across the United States (for example, average value of agricultural products sold per farm). Select a county and view and download the county’s data for a general category. Download the U.S. county-level dataset of mapped values for all categories in Microsoft ® Excel format.