Loading...
Loading...
Crop yield, soil data, pest surveillance, livestock, food composition, precision farming
18,155 datasets
25 soil samples were collected on a 100-meter grid within a native forest creation site and adjacent grassland in Aberdeenshire, Scotland. The dataset provides baseline measurements of soil carbon and nitrogen content from September and November 2022, supported by the Natural Environment Research Council and Leverhulme Trust. This data establishes a reference for tracking changes as planted and naturally regenerating trees establish.
Mosquito apparent densities, species, and sex were collected in Bura, Kenya, between September 2013 and November 2014. Sampling was repeated four times to cover wet, dry, irrigation, and fallow seasons using CDC light traps. The data were analyzed by researchers from icipe, ILRI, and KEMRI to assess the impact of land use change on mosquito habitats and Rift Valley fever vectors.
A study investigated toxic pollutants at 26 locations in Oregon's Willamette River and selected tributaries. The Oregon Department of Environmental Quality, U.S. EPA, and Oregon State University conducted sampling from 1988 to 1991 to screen for bioaccumulative pollutants in sediment and fish tissue. Target analytes included dioxins, furans, pesticides, PCBs, PAHs, and metals, analyzed using standardized EPA methods.
Lahore fast food restaurants, Area, Ratings, number of Reviews. The dataset appears to list establishments in the Pakistani city of Lahore. Its origin and specific size are unknown.
Cropland areas expanded from 3-4 million km² in 1700 to 15-18 million km² in 1990, while pasture grew from 4-5 million km² to 31-33 million km². This reconstructed dataset was developed by RIVM in the Netherlands and SAGE at the University of Wisconsin-Madison using historical inventories and spatial analysis. It provides annual or decadal land use data from 1700 to 1992.
10-minute resolution data from multiple sensors and irrigation systems. The dataset is synthetic and designed for time-series machine learning and IoT applications. Its source, author, and exact size are unknown.
Handwritten-Decision Tree and Forest is a dataset hosted on Kaggle. The title suggests it likely contains images of handwritten diagrams or text related to decision tree and random forest algorithms. Metadata such as author, size, and specific content details are unavailable.
Decision Tree and Forest is a dataset hosted on Kaggle. The title suggests it contains data related to decision tree and random forest algorithms, likely for educational or benchmarking purposes. No further metadata is available to confirm its specific contents or origin.
Task3 Deci Tree and forest is a dataset published on Kaggle. The title suggests it likely contains data for training or evaluating decision tree and random forest models. No further details on size, source, or features are available in the provided metadata.
A University of Nebraska–Lincoln research site near Mead, Nebraska, provides carbon flux measurements from an irrigated, continuous maize field. The data, part of the AmeriFlux network, was contributed by author Andy Suyker. The site has a documented history of crop rotation and specific tillage practices, including a conservation-plow operation initiated after the 2005 harvest.
Ghanaian smallholder cocoa farmers' perceptions and constraints regarding cash, non-cash, and blended agricultural credit. The data explores the impact of these credit types on farmer welfare. It was authored by Joseph Acheampong and last updated on April 14, 2026.
E-commerce sales data for the North American Industry Classification System (NAICS) food services and drinking places sector in Canada. The dataset covers one year of sales figures for all members under the sales category, provided by Statistics Canada.
Featuring tree features from the City of Hobart, managed by the City of Hobart Open Data. It includes records of trees with and without associated asset IDs. The dataset is available in multiple formats including CSV, GeoJSON, and KML.
City of Sioux Falls provides an authoritative feature layer of tree points for the city. The dataset is available in multiple formats including CSV and GeoJSON and was last updated on March 22, 2026. It is published under a CC-BY-4.0 license.
tmax_cropped_full is a dataset hosted on Kaggle. The title suggests it contains temperature data, likely maximum temperatures, related to agricultural contexts. No further metadata on its size, origin, or specific content is available.
Field sampling from August 27-30, 2013, collected coral tissues (Pocillopora damicornis) in Tinian, Commonwealth of the Northern Mariana Islands, for laboratory analysis of pollutants. The dataset includes concentrations of trace elements, PAHs, PCBs, pesticides, and organotins. It was produced by NOAA's National Centers for Coastal Ocean Science (NCCOS) as part of the National Status and Trends Special Study.
Large updates to the foundational GIS data for Joshua Tree National Park, including park boundary, trails, and visitor center locations. The data is maintained by the park's GIS staff and is used for official maps, applications, and visitor information. Trail updates incorporate GNSS data collection with sub-meter accuracy.
Multi-granularity time series of vegetation and water indices derived from Sentinel-2 satellite imagery, specifically for wheat parcels. The data covers a five-year period from 2019 to 2024 and is intended for wheat harvest prediction modeling. It was sourced from the Kaggle platform, but the specific author and collection methodology are not provided.
Comprising acoustic monitoring data from 15 locations in the Mandla district of Madhya Pradesh, India, collected from August 2024 to November 2025. The data was processed using machine learning tools to identify bird species from audio recordings, with identifications assigned a confidence rating. The study aims to understand the long-term impacts of landscape variables and farming practices on bird diversity.
Time-series data on highland crops in Sri Lanka, with coverage extending up to the year 2025. The dataset appears to track agricultural variables over time, likely for modeling and analysis. The specific source, collection method, and granularity of the data are not detailed in the provided metadata.