Loading...
Loading...
Crop yield, soil data, pest surveillance, livestock, food composition, precision farming
19,128 datasets
Global maps at a 10 arc-second resolution model the potential for land conversion into three categories of cropland. Artificial Neural Network models trained on conversion data from 2007-2020 achieved cross-validation AUC scores of 0.88-0.93. The data, from a study by Mirza Čengić at Radboud University Nijmegen, is intended to downscale projections for global environmental assessments.
10 arc-second resolution raster maps project global suitability for converting land to three agricultural categories. The data was created by Mirza Čengić of Radboud University Nijmegen using Artificial Neural Network models trained on conversion data from 2003 to 2013. Cross-validation indicated good model performance with a mean Area Under the Curve value of 0.95.
400 one-minute audio recordings sampled at 48000 Hz, divided into four cross-validation splits. The datasets contain synthesized spatial sound events with temporal and directional annotations, created by Tampere University for the DCASE 2019 challenge. Recordings were synthesized using spatial room impulse responses collected in Finland between December 2017 and June 2018, convolved with isolated sound events and mixed with ambient noise.
A 2019 dataset from Tampere University contains real-life first-order Ambisonic recordings of moving sound events. It consists of three sub-datasets with up to three temporally overlapping events, each with 240 training and 60 testing recordings of about 30 seconds. The dataset was synthesized using impulse responses from a university corridor and sound events from the UrbanSound8K dataset.
Recordings from 2018 consist of real-life first order Ambisonic (FOA) format audio with stationary point sources. The dataset was generated by collecting impulse responses in a university corridor using an Eigenmike spherical microphone array and a moving loudspeaker. It contains three sub-datasets for overlapping sound events, with metadata including temporal onset/offset and spatial coordinates for events sourced from the UrbanSound8K dataset.
Farm Census District Electoral Area 2015 covers all farm businesses in Northern Ireland. Data is collected via survey and supplemented with administrative data from the Animal and Public Health Information System (APHIS). The statistics, collected since 1847, provide information on farm counts, land use, livestock populations, and labor.
27.5 tonnes per hectare of standing biomass characterize the mulga woodland where this flux tower measures ecosystem-atmosphere exchanges. Data from the Ti Tree East station, located 170 km north of Alice Springs, were processed using PyFluxPro (v3.4.23) to produce gap-filled estimates of Net Ecosystem Exchange (NEE), Gross Primary Productivity (GPP), and Ecosystem Respiration (ER). The Terrestrial Ecosystem Research Network's Data Discovery platform released this version in June 2026.
Brazil's national soil spectral library contains harmonized physicochemical and spectral reflectance data from 16,084 sampling sites at 0-20 cm depth. The database includes Visible, Near-Infrared, and Shortwave Infrared (Vis-NIR-SWIR) data for all samples, with a subset also containing Middle Infrared (MIR) spectral measurements. This open-access repository supports modeling of soil attributes to reduce the time and cost of traditional soil surveying.
16,084 soil sample sites provide harmonized physicochemical and spectral reflectance data (Vis-NIR-SWIR and MIR ranges) at 0-20 cm depth. The Brazilian Soil Spectral Library (BSSL) is an open-access repository coordinated by José Alexandre Melo Demattê of the Universidade de São Paulo and published in 2019. The library consolidates data from 42 institutions and 61 researchers, focusing on diverse tropical soil types.
Agricultural Spatial Reference (ASR) areas designated as particularly important for agricultural production under Lower Austria's Regional Spatial Planning Programmes. The dataset aims to secure spatial prerequisites for sustainable agriculture and forestry to ensure food security. It is provided by Cooperation OGD Österreich and Wikimedia Österreich under a CC-BY-4.0 license.
The United Kingdom's Environmental Change Network (ECN) provides a geospatial view of 57 long-term environmental monitoring sites. This includes 12 terrestrial and 45 freshwater locations, ranging from upland moors to lowland chalk grasslands and from small ponds to large rivers. The programme collates integrated physical, chemical, and biological variables to serve as an evidence base for environmental policy and scientific research.
This project evaluates strategies to reduce nitrogen fertilizer runoff from sugarcane farms into the Great Barrier Reef. It tests production zone yield potential and enhanced efficiency fertilizers at identified nitrogen loss 'hot spots' to measure water quality, productivity, and economic impacts. The dataset is associated with the Australian Ocean Data Network and was last updated in July 2026.
HYDROBOD2 provides hydrological soil characteristics for the federal state of Lower Austria. The project compiled parameters like hydraulic conductivity, total pore volume, and usable field capacity, which are used as a basis for flood prediction models. Data includes reports, maps, and grid data from two project phases, with the second phase incorporating new agricultural land mapping.
Experimental data from the Australian Ocean Data Network quantifies the chronic effects and persistence of agricultural herbicides on seagrass and corals in the Great Barrier Reef. The project, active from 2011 to 2014, involved controlled laboratory and outdoor tank experiments simulating flood plume conditions. It measured toxic thresholds and herbicide half-lives under various stressors like temperature and low light.
Median farm equity ratios for Australian broadacre and dairy farms averaged over three years from 1996-1997 to 1998-1999. The data was collected by the Australian Bureau of Agricultural and Resource Economics and Sciences through annual farm survey interviews and farm accounts. It includes attributes such as the average equity ratio, the proportion of properties with equity below 80%, and the relative standard error for each Statistical Division.
An annual survey compiled by the Statistics and Analytical Services Branch of DAERA. Information includes the number of farms, area farmed, crop and grass hectares, livestock counts, and labor statistics. Data for small areas with fewer than 5 farm businesses is suppressed to prevent disclosure.
Agricultural Land Classification (ALC) survey data for a specific site in St Helens, England, collected between 1989 and 1999. The dataset includes scanned original paper maps and survey reports detailing land quality, with Grade 3 land subdivided into subgrades 3a and 3b. It likely contains unedited sample point soils data and soil pit descriptions for detailed site analysis.
Scanned paper maps and survey reports detail the Agricultural Land Classification (ALC) for specific sites in England, such as Hordle, Kings Farm and Middleton, Yapton Road. These detailed surveys were conducted between 1989 and 1999 by the Ministry of Agriculture, Fisheries and Food, using a methodology that subdivides Grade 3 land into subgrades 3a and 3b. The collection includes unedited sample point soils data and soil pit descriptions for some sites, with maps at scales from 1:5,000 to 1:50,000.
Scanned original paper maps and survey reports detail the Agricultural Land Classification for specific sites in England, surveyed between 1989 and 1999. The data includes the subdivision of Grade 3 land into subgrades 3a and 3b, following the official grading methodology. Unedited sample point soils data and soil pit descriptions are available for some of the individual site surveys.
Agricultural Land Classification (ALC) site survey data for Bickton, Salisbury Road, surveyed between 1989 and 1999. The dataset contains scanned original paper maps and survey reports, detailing land grades including the subdivision of Grade 3 into subgrades 3a and 3b. Unedited sample point soils data and soil pit descriptions are also available for some surveys.