Loading...
Loading...
Crop yield, soil data, pest surveillance, livestock, food composition, precision farming
19,247 datasets
Environmental Information Data Centre provides compositional and growth assay data from wild bacterial communities in tree-holes at Wytham Woods, Oxford. The dataset includes manipulated and control pH conditions, with compositional sampling over 12 weeks and laboratory growth rate measurements on beech tea media.
Humber catchment rivers contain weekly and storm-period measurements of 11 specific pesticides including Atrazine, Simazine, and Permethrin. Data was collected between 1994 and 1996 by the Land Ocean Interaction Study (LOIS) project, with samples processed via solid-phase extraction and Gas Chromatography analysis.
Monitoring records of a wild field cricket (Gryllus campestris) population in Asturias, Spain. Data include male cricket mating-related activities such as age, singing activity, dominance in fights, and lifespan, collected over an 11-year period from 2006 to 2016.
Ecological field data from the UK's East Midlands and South West England assesses biodiversity impacts of converting land to Miscanthus grass and short-rotation coppice willow. The dataset was collected from 2006 to 2009 as part of the NERC Rural Economy and Land Use (RELU) programme by the Environmental Information Data Centre. It provides interdisciplinary indicators for social, economic, hydrological, and biodiversity studies.
A 10-year monitoring dataset tracks a population of Gryllus campestris, a flightless, univoltine field cricket, in a meadow in Asturias, North Spain. The data include basic traits, behavioral observations, genotypes, and pheromone measurements collected from 2006 to 2016.
Southern England farms in Hampshire and West Sussex provided data on flower and bee abundance, diversity, and bee pollen foraging from 2013 to 2015. Surveys quantified wild solitary bee pollen diets using direct observations and pollen load analysis. The work was funded by the Natural Environment Research Council and the Game and Wildlife Conservation Trust.
20 Indian food categories are included in this dataset for image classification tasks. The dataset was sourced from Kaggle, but details about its author, creation date, and size are not provided. Its primary purpose is to support computer vision models in identifying different types of Indian cuisine.
crop_nigerian_dataset is a dataset hosted on Kaggle. The title and platform tags suggest it contains information related to crop yields and farming in Nigeria. The dataset's specific content, size, and provenance are not detailed in the available metadata.
FoodLensVN is a visual question answering dataset containing images of Vietnamese traditional dishes paired with question and answer pairs. The dataset likely contains a collection of dish images and corresponding textual queries and answers. It was sourced from Kaggle, but the author, organization, and last update date are unknown.
Nashik district in Maharashtra contains 434 registered non-governmental organizations active in the food processing sector. Exploratory analysis of these organizations is available on Kaggle. The dataset's author, organization, and last update date are unknown.
Nine distinct US federal geospatial datasets are accessible through this package, including elevation, hydrography, soil, climate, and land cover data. The collection is maintained by author R. Kyle Bocinsky and aggregates sources from agencies like USGS, NOAA, and USDA. Specific datasets include the National Elevation Dataset, National Hydrography Dataset, SSURGO soil database, and the Cropland Data Layer.
CGIAR's research program focuses on developing agricultural solutions for climate change impacts in developing countries. It likely contains data on adaptation strategies, risk management, and mitigation options for smallholder farmers. The program's work is centered on enhancing food security and reducing poverty through climate-resilient practices.
Michael Mayer created a visualization library for SHAP (SHapley Additive exPlanations) values. It provides plots like waterfall, force, importance, dependence, and interaction plots, acting on a 'shapviz' object created from a matrix of SHAP values and a corresponding feature dataset. The package includes wrappers for SHAP value computation from R packages like 'xgboost', 'lightgbm', 'fastshap', 'shapr', 'h2o', 'treeshap', 'DALEX', and 'kernelshap'.
The RST Discourse Treebank was developed by researchers at the Information Sciences Institute (University of Southern California), the US Department of Defense, and the Linguistic Data Consortium. It consists of 385 Wall Street Journal articles from the Penn Treebank, annotated with discourse structure in the Rhetorical Structure Theory framework. The data is divided into a training set of 347 documents and a test set of 38 documents.
Northern Ireland microbiological results published by the Food Standards Agency. The dataset contains regulatory test outcomes for food safety.
Foodinsseg Nutritionp likely contains data related to food security and nutrition. The dataset is hosted on Kaggle, but its specific content, size, and origin are unknown. Its columns and sample data are unavailable for review.
FoodInsSegp is a dataset for computer vision tasks, likely containing images of food items. The dataset is hosted on Kaggle, but its specific contents, scale, and creation details are not provided in the available metadata. Further details such as the number of images, annotation types, and the creator are unknown and require verification after download.
2024 data from the Foodpanda delivery platform across 10 Asian countries, covering 63 features related to orders, finance, and riders. The dataset likely contains full profit and loss statements, delivery performance metrics, and customer analytics. It was sourced from Kaggle, but the specific author, organization, and license details are unknown.
Environmental monitoring data from the University of New Hampshire's Open Ocean Aquaculture demonstration project. The project began in 1997 and is aggregated by the NASA Earthdata platform. The dataset is associated with the organization SCIOPS.
20 classes of soils were acquisited by scanning and raster network encoding of the Soil Map of Poland from the National Atlas of Poland. The dataset likely contains rasterized soil type classifications for Poland. The original atlas was published between 1973 and 1978.