Loading...
Loading...
Crop yield, soil data, pest surveillance, livestock, food composition, precision farming
18,217 datasets
Egypt is the geographic focus of this dataset, which appears to contain information about crops. The data has been cleaned, suggesting it may be ready for analysis. It was published on Kaggle, but the original author and specific collection details are unknown.
Train_decision_tree is a dataset hosted on Kaggle, likely intended for building and evaluating decision tree models. The dataset's specific content, size, and features are not described in the available metadata. Its origin, creation date, and author are unknown.
Wave height, period, and directional measurements from a wave radar installed at the offshore substation of the Lincs Wind Farm. The dataset covers December 2021 to April 2025, with a period from December 2021 to May 19, 2022 containing only wave height data due to a sensor malfunction. The data is provided by the Government Digital Service via the eu_open_data platform.
A study of factor interactions in the Chinese A-Share market based on the AP-Tree methodology. The dataset likely contains financial factors and their relationships for analysis. The author, organization, and specific temporal coverage are not provided in the input metadata.
A dataset of 30,000 cropped face images, as indicated by its title. It is hosted on Kaggle, a platform for data science competitions and projects. The dataset's specific source, creation method, and temporal coverage are not detailed in the provided metadata.
A 2016 randomized experiment in New York City public housing developments provides evidence on the effect of street lighting on crime. The dataset likely contains crime outcomes for communities assigned temporary streetlights from March through August 2016. The research, authored by Aaron Chalfin, found a minimum 36 percent reduction in nighttime outdoor index crimes associated with the lighting intervention.
Manoj Thomas of Cornell University analyzed the shopping behavior of 1,000 households over six months. The research investigates how credit card payments, compared to cash, increase purchases of unhealthy food items rated as impulsive. Results from four studies support the hypothesis that the relative painlessness of card payments weakens impulse control.
A lexicon document detailing the terminology and concepts used in lipid nutrition, produced by a joint working group of the International Union of Nutritional Sciences and the International Union of Pure and Applied Chemistry. It includes tables listing shorthand formulas and systematic and trivial names for saturated, monoenoic, and polyenoic fatty acids. The document was authored by J. Beare-Rogers of Okanagan College.
The Longitudinal Nutrient Deficiency dataset is associated with a 2021 AAAI paper on detection and prediction of nutrient deficiency stress. It contains three image sequences of aerial imagery from 386 farm parcels, which have been annotated for nutrient deficiency stress. The data is hosted on AWS Open Data and was contributed by Intelinair, Inc.
Replication data examines the relationship between bans on hazardous pesticides and infant mortality rates in Turkey. The dataset supports a study funded by the European Union's Horizon Europe programme under a Marie Skłodowska-Curie Actions Postdoctoral Fellowship. It was last updated in April 2026.
Kaggle hosts this dataset of images processed using the MediaPipe framework. The title suggests the data likely contains face images that have been automatically cropped. The specific volume, creator, and update details are not provided in the available metadata.
Face forensic++ cropped face is a dataset hosted on Kaggle. The title suggests it contains cropped facial images, likely intended for forensic analysis tasks. The dataset's specific size, creator, and update history are not provided in the available metadata.
FaceForensics++ is a dataset for deepfake detection research, likely containing cropped facial images. The data appears to be sourced from manipulated videos, focusing on facial regions. It is hosted on Kaggle, but specific details about its size, creation date, and authors are not provided in the available metadata.
Kaggle hosts a dataset titled 'digital agriculture'. The dataset's specific content, size, and origin are not detailed in the available metadata. Its columns, row count, and creation details are unknown.
FaceForensicX+ is a dataset of cropped facial images, likely intended for research in media forensics and deepfake detection. The dataset is hosted on Kaggle, but its specific origin, size, and creation details are not provided in the available metadata. The content and structure must be verified after download.
PadangFood - Kompetisi is a dataset from Kaggle related to a food competition. The dataset likely contains information about dishes, participants, or scores from a culinary event. Its specific contents, size, and creation details are not provided in the available metadata.
Soil, rock, and stone samples collected from pits and outcrops in the Beacon Valley area of Antarctica. Samples were excavated from moraines on Aztec Ridge and from three sites in New Valley, west of Aztec Ridge, for analysis of quartz grains. The dataset was collected by SCIOPS and last updated in January 1998.
Measurements of organochlorine pesticides and polybrominated diphenyl ethers in species from the Adelie penguin food web near McMurdo Station. Data includes concentration levels for cod, krill, and penguin eggs, with specific readings such as ΣPBDE6 at 311 ng/g in cod. The dataset was produced by the organization SCIOPS and last updated in January 1996.
One year of data profiles the distribution of nitrogen and chloride in soil following fertilizer application. The study, conducted by SCIOPS, was published in May 1984. It tracked the movement of NH4-N and NO3-N, comparing it to chloride as a tracer.
1995 irrigation water withdrawals are modeled as a gridded field at a 30-minute latitude by longitude resolution. The dataset estimates annual withdrawals in cubic kilometers by distributing country-level data over irrigated lands, prorated by computed irrigation need. It was produced by Vorosmarty et al. (2005) using methods from the World Water Development II project.