ABSTRACT To enhance speed and agility in interpreting physiological quality tests of seeds, The use of algorithms has emerged. This study aimed to identify suitable machine learning models to assist in the precise management of seed lot quality. Soybean lots from two companies were assessed using the Supplied Test Set, Cross-Validation (with 8, 10, and 12 folds), and Percentage Split (with 66% and 70%) methods. Variables analyzed through Tetrazolium tests included vigor, viability, mechanical damage, moisture damage, bed bug damage, and water content. Method performance was determined by Kappa, Precision, and ROC Area metrics. Classification Via Regression and J48 algorithms were employed. The technique utilizing 66% of data for training achieved 93.55% accuracy, with Precision and ROC Area reaching 94.50% for the J48 algorithm. Applying the cross-validation method with 10 folds resulted in 90.22% of correctly classified instances, with a ROC Area outcome like the previous method. Tetrazolium Vigor was the primary attribute used. However, these results are specific to this study's database, and careful planning is necessary to select the most effective application methods.

UAV-Captured Sorghum Crop Line Detection Dataset

Description

This dataset contains UAV-captured images of sorghum fields, annotated for crop line detection. It has been curated to facilitate machine learning research, particularly for developing and evaluating algorithms for agricultural monitoring and analysis.

The dataset has been divided into six separate folders, each formatted for compatibility with different object detection architectures:

• 416x416_augmented: Prepared for use with Detectron2 architectures, such as RetinaNet and Faster R-CNN, with images augmented and resized to 416x416 pixels.
• sorghumfield.v3-416x416_augmented.mt-yolov6: Contains images augmented and tailored for use with the YOLOv6 Meituan architecture.
• sorghumfield.v3-416x416_augmented.yolov5pytorch: Formatted specifically for the YOLOv5 architecture implemented in PyTorch.
• sorghumfield.v3-416x416_augmented.yolov8: Adapted for the latest YOLOv8 architecture, with the same augmentation and resizing.
• sorghumfield.v3i.darknet: Designed for use with YOLOv3, YOLOv4 and YOLOv7 architectures within the Darknet framework.
• sorghumfield.v9i.yolov8_synthetic: An updated set that incorporates synthetic images generated to augment the YOLOv8 dataset.

Each folder contains images that have been manually annotated with bounding boxes to identify crop lines. Annotations were performed using LabelBox, and the data has been segregated into training, validation, and testing sets.

Data Augmentation and Synthetic Data

Data augmentation techniques such as rotations, translations, scaling, and flipping have been applied to increase the diversity and robustness of the dataset. Additionally, synthetic data has been generated and included to enhance the dataset further, providing additional variability and complexity for more effective training of object detection models.

Intended Use

This dataset is intended for use by researchers and practitioners in the fields of computer vision and agriculture technology. It is particularly useful for those developing object detection models for agricultural applications.

Acknowledgments

When utilizing this dataset, please reference the original source of the sorghum images made available by Purdue University and the manual annotations provided in this work.

Citation

If you use this dataset in your research, please cite the following: - Fernandes, G., & Pedro, J. (2023). "Aplicabilidade de Técnicas de Inteligência Artificial na Análise Automática de Imagens Agrícolas Aéreas". Undergraduate Thesis, UnB. - J. Ribera, F. He, Y. Chen, A. F. Habib, and E. J. Delp, "Estimating Phenotypic Traits From UAV Based RGB Imagery", ACM SIGKDD Conference on Knowledge Discovery and Data Mining Workshop - August 2016, San Francisco, CA - J. Ribera, D. Güera, E. J. Delp, "Locating Objects Without Bounding Boxes", Computer Vision and Pattern Recognition (CVPR), June 2019, Long Beach, CA. arXiv:1806.07564.

License

The dataset is available for non-commercial research and educational purposes. For any other use, please contact the authors for permission.

This is the data repository for the article A stocktake of countries producing the most scientific literature on digital technologies in agriculture. The study reviews peer-reviewed literature to document the use of digital technologies in agriculture across six world regions: Africa, Asia, Europe, North America and the Caribbean, Oceania and surrounding islands, and South America. Drawing on 1,259 relevant articles, the review provides a comprehensive overview and highlights emerging trends.

Global deep learning market worth at USD 2.74 Billion in 2024, is expected to surpass USD 85.99 Billion by 2034, with a CAGR of 41.3% from 2025 to 2034

Nations Between Mining Building Agriculture And Farming Trade Industry Limited Company Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

Graph and download economic data for Electric Power Use: Manufacturing and Mining: Manufacturing: Durable Goods: Logging (NAICS = 1133) (DISCONTINUED) (KWN1133A) from 1972 to 2004 about hunting, forestry, fishing, logging, used, mining, electricity, agriculture, NAICS, manufacturing, and USA.

Global tractor shovel loader market size was $3.59 billion in 2024 and is projected to reach $5.31 billion by 2034, a CAGR of 5.04% between 2025 and 2034.

Estimated industrial manufacturing agriculture construction and mining energy estimated by North American Industrial Classification System NAICS code county and fuel type for 2014. Additional disaggregation by end use e.g. machine drive process heating facility lighting is provided for manufacturing agriculture and mining industries. Estimation approach is described in detail in the data_foundation folder here: https//github.com/NREL/Industry-Energy-Tool

China Input-Output: Intermediate Use: Intermediate Input: Farming, Forestry, Animal Husbandry, Fishery: Mining data was reported at 0.397 RMB bn in 2015. This records a decrease from the previous number of 0.595 RMB bn for 2012. China Input-Output: Intermediate Use: Intermediate Input: Farming, Forestry, Animal Husbandry, Fishery: Mining data is updated yearly, averaging 4.735 RMB bn from Dec 1995 (Median) to 2015, with 9 observations. The data reached an all-time high of 16.993 RMB bn in 2005 and a record low of 0.397 RMB bn in 2015. China Input-Output: Intermediate Use: Intermediate Input: Farming, Forestry, Animal Husbandry, Fishery: Mining data remains active status in CEIC and is reported by National Bureau of Statistics. The data is categorized under China Premium Database’s National Accounts – Table CN.AG: Input-Output Table: Intermediate Use: Input/Output: Farming, Forestry, Animal Husbandry, Fishery.

The International Production Assessment Division (IPAD) is part of the Office of Global Analysis (OGA) within the Foreign Agricultural Service (FAS), an agency within the US Department of Agriculture (USDA). FAS-IPAD uses satellite imagery and remote sensing data to assist in its agricultural estimates of global crop conditions. The division provides monthly estimates of area, yield and production for 17 distinct commodities in over 160 countries around the world, including post-disaster assessments. GADAS is a powerful visualization tool based on an ArcGIS platform that enables FAS-IPAD analysts, and other users, to rapidly assess real-time crop conditions using a wide variety of data layers from a multitude of sources.

GADAS integrates a vast array of highly detailed data streams to include daily precipitation data, vegetation index, crop masks, land cover data, irrigation and water data, elevation and infrastructure, political data, and much more. In addition, FAS-IPAD has partnered with the Pacific Disaster Center (PDC) in Hawaii to incorporate real-time data streams into GADAS for worldwide monitoring, tracking, and pre- and post-disaster agricultural assessments resulting from hurricanes, typhoons, tsunamis, floods, droughts, earthquakes and volcanic eruptions.

You may want to begin exploring GADAS for the many things it can be used for, such as:

• Global agricultural monitoring and commodity forecasting
• Comparative climatic and satellite-derived vegetation analysis
• Environmental change detection studies and analysis
• Drought monitoring
• Natural disaster assessment and analysis
• Tracking current and historical disaster events
• Highlighting regional risk posed by natural disasters
• Spatial modeling of potential disaster impacts
• Delineation of major land-use categories worldwide
• Regional planning and climate-resilience studies
• Program or project-specific data archive and data mining

We welcome your feedback on how GADAS has worked or is working for you, and are enthusiastic about expanding the data layers, utilization, and future development of this very powerful GIS tool. Please contact us at OGA.IPAD@fas.usda.gov to provide your valued comments…we look forward to hearing from you!

Here’s a screenshot centered over the northern Atlantic Ocean:

CN: Input-Output: Intermediate Use: Intermediate Input: Mining: Farming, Forestry, Animal Husbandry, Fishery data was reported at 3.060 RMB bn in 2015. This records an increase from the previous number of 2.500 RMB bn for 2012. CN: Input-Output: Intermediate Use: Intermediate Input: Mining: Farming, Forestry, Animal Husbandry, Fishery data is updated yearly, averaging 6.753 RMB bn from Dec 1995 (Median) to 2015, with 9 observations. The data reached an all-time high of 16.245 RMB bn in 2010 and a record low of 2.500 RMB bn in 2012. CN: Input-Output: Intermediate Use: Intermediate Input: Mining: Farming, Forestry, Animal Husbandry, Fishery data remains active status in CEIC and is reported by National Bureau of Statistics. The data is categorized under China Premium Database’s National Accounts – Table CN.AG: Input-Output Table: Intermediate Use: Input/Output: Mining.

Observations of irrigated agricultural land within the Prescott Active Management Area Groundwater Basin in Arizona. Crops were verified in situ once in 2023 on Sep 13th; based on digitized field boundaries. Field boundaries were digitized from U.S. Department of Agriculture, National Agriculture Imagery Program County Mosaic 2023 imagery for Arizona and supplemented with the Sentinel2 imagery collection accessed via the European Space Agency, Copernicus Browser (https://browser.dataspace.copernicus.eu/). Satellite images were also used to identify the length of the growing season and crop condition. Water withdrawals were calculated using the modified Blaney-Criddle model of calculating consumptive use (U.S. Bureau of Reclamation, 1992 appendix A) using crop coefficients from Doorenbos and Pruitt (1975), the number of acres with active crops, crop condition, and irrigation system efficiency. The withdrawal equation was modified from "Water withdrawals for irrigation, municipal, mining, thermoelectric-power, and drainage uses in Arizona outside of active management areas, 1991-2000" (Tadayon, 2005) to account for variations in water application.

The booming drone software market is projected to reach $41.29 billion by 2033, fueled by construction, agriculture, and mining applications. Explore key trends, growth drivers, and leading companies shaping this dynamic sector. Discover market insights and forecasts for open-source vs. closed-source software.

Ãœã‡Sem Agriculture Products Building Food Farming And Mining Industry Trade Limited Company Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

Land Survey Equipment Market Outlook

The global land survey equipment market size was estimated at USD 6.2 billion in 2023 and is expected to reach USD 9.8 billion by 2032, growing at a compound annual growth rate (CAGR) of 5.3% during the forecast period. The significant growth factor driving this market is the increasing demand for sophisticated and accurate land surveying techniques across various industries such as construction, agriculture, mining, and oil & gas.

One of the critical growth factors of the land survey equipment market is the surge in construction activities worldwide. With urbanization at an all-time high, there is an increasing need for advanced land surveying solutions to ensure accuracy, reduce errors, and streamline construction projects. The adoption of total stations, GNSS/GPS, and 3D laser scanners in the construction sector has been pivotal in achieving precision and efficiency. Additionally, the incorporation of these technologies helps in reducing the overall project time and labor costs, thus acting as a significant growth catalyst.

The agriculture sector is also significantly contributing to the growth of the land survey equipment market. Precision farming technologies, such as GNSS/GPS and UAVs/drones, are increasingly adopted to enhance crop yield and optimize resource use. These technologies provide accurate data on field conditions, enabling farmers to make informed decisions. The growing awareness and adoption of precision farming techniques are expected to propel the demand for land survey equipment in the agriculture sector, further driving market growth.

Moreover, the mining and oil & gas sectors are witnessing increasing investments in land survey equipment due to the need for precise data in exploration and extraction activities. The use of advanced surveying equipment, such as theodolites and 3D laser scanners, helps in accurately mapping geological formations and ensuring the safety and efficiency of operations. As these industries continue to expand and adopt more sophisticated technologies, the demand for high-quality land survey equipment is expected to rise.

Geodetic Measuring Equipment plays a crucial role in the land survey equipment market by providing the precision and accuracy required for various surveying applications. These instruments are essential for determining the exact positions of points on the Earth's surface, which is vital for mapping, construction, and infrastructure development. The use of geodetic equipment, such as total stations and GNSS/GPS systems, ensures that surveyors can achieve high levels of accuracy in their measurements, which is critical for the success of any project. As the demand for precise data continues to grow across industries, the importance of geodetic measuring equipment in the market is expected to increase, driving further advancements and innovations in this field.

Regionally, North America and Europe hold a significant share of the land survey equipment market, driven by the advanced infrastructure and high adoption rate of modern technologies in these regions. However, the Asia Pacific region is expected to witness the highest growth during the forecast period, owing to rapid urbanization, increasing construction activities, and the adoption of precision farming techniques. Government initiatives in emerging economies like India and China to improve infrastructure and agricultural productivity are also contributing to regional market growth.

Product Type Analysis

The land survey equipment market is segmented by product types, including total stations, GNSS/GPS, theodolites, levels, 3D laser scanners, UAVs/drones, and others. Among these, total stations are one of the most widely used land survey equipment due to their multifunctional capabilities. Total stations combine the functionalities of theodolites and electronic distance measurement (EDM) instruments, providing precise angle and distance measurements. Their ability to integrate with software for data recording and processing has made them essential in construction, mining, and other sectors.

GNSS/GPS systems have revolutionized the land surveying industry by providing highly accurate positioning data. These systems are extensively used in various applications such as construction, agriculture, and mining. The accuracy, efficiency, and ease of use offered by GNSS/GPS systems make them a popular choice among surveyors. Additionally,

DataSet for use in RapidMiner from the master's thesis. OPEN DATA MINING: AN ANALYSIS OF THE USE OF BOTS IN THEELECTRONIC TRADING FLOORSDissertation presented to the Graduate Program in Management in Learning Organizations in compliance with the requirements for completion of the Professional Master in Management in Learning Organizations-UFPB.Brazil's federal government has sought to match procurement procedures to trends in information and communication technologies. The electronic reverse auction was one of the products of these efforts, being characterized as a modality that presented structural solutions to improve the efficiency of purchases of common goods and services and that represents more than 94% of the bids that occurred in the country. Despite the benefits of electronic format, this environment brings challenges, such as dealing with the use of bots, which works by automatically bidding. While there is no law prohibiting its use, judgments of the Federal Court of Auditors state that its use provides a competitive advantage to suppliers holding this technology in question over other bidders, characterizing an affront to the principle of isonomy. Also in the sense of modernizing public procurement is increasing transparency through open data policies, as part of the context of Open Government and digital transformation. This study aims to analyze the situation of bot use in electronic reverse auctions through open data mining. Electronic reverse auctions held at the Ministry of Agriculture, Livestock and Supply in 2017 were analyzed. Data were obtained by request by the Electronic Information System for Citizen Information (e-SIC), having been adopted as methodology the knowledge discovery in databases. The results indicate that bot use in electronic reverse auctions in 2017 represented a more than 5% advantage in successful bid items observed for only 1.99% of the sample bidders, indicated as suspected use. The most relevant indicator for classifying bidders as suspects was the high number of bids issued in relation to the behavior observed in the sample. Results are expected to foster discussion of the effects of bot use on e-trading and to highlight the need for open data policy development for data mining to be an increasingly effective means to assess anomalies and increase the integrity of the bids made by the Federal Government Procurement Portal.DataSet para uso no RapidMiner provenientes da dissertação de mestrado. MINERAÇÃO DE DADOS ABERTOS: UMA ANÁLISE DO USO DE BOTS EMPREGÕES ELETRÔNICOSDissertação apresentada ao Programa de Pós-Graduação em Gestão nas Organizações Aprendentes em cumprimento às exigências para conclusão do Mestrado Profissional em Gestão nas Organizações Aprendentes-UFPB.https://sig-arq.ufpb.br/arquivos/2019071230f6981803056bc243c9a4b41/Dissertao_-_Hugo_Medeiros_Souto_-_Minerao_de_Dados_Abertos_2.pdf

Drone Data Services Market size was valued at USD 2.96 Billion in 2024 and is projected to reach USD 10.19 Billion by 2032, growing at a CAGR of 55.6% from 2026 to 2032.

Drone Data Services Market Drivers

Growing Adoption of Drones: The increasing adoption of drones across various industries, including agriculture, construction, infrastructure inspection, and mapping, is driving the demand for drone data services.

Advancements in Drone Technology: Improvements in drone technology, such as longer flight times, higher payload capacities, and enhanced image capture capabilities, are making drones more versatile and effective for data collection.

Data-Driven Decision Making: Businesses and organizations are increasingly relying on data-driven decision making to improve efficiency, reduce costs, and gain a competitive advantage. Drone data can provide valuable insights for a wide range of applications.

Drone Data Services Market Restraints

Regulatory Challenges: The use of drones for commercial purposes is subject to various regulations, including restrictions on flight paths, altitudes, and data collection. These regulations can hinder the growth of the drone data services market.

Privacy Concerns: The collection and use of drone data can raise privacy concerns, particularly when it involves capturing images or data of individuals or sensitive areas. Addressing these concerns requires careful consideration of data privacy and security.

Le marché mondial de l'apprentissage profond, d'une valeur de 2.74 milliards USD en 2024, devrait dépasser 85.99 milliards USD d'ici 2034, avec un TCAC de 41.3 % de 2025 à 2034.