Data · dataset · 2026
training_samples_zarr_v34.zip
Listed in ScienceDB
This dataset is a multi-scale spatiotemporal foundation benchmark designed for field-level and county-level crop yield prediction across the contiguous United States (CONUS).
Description
The dataset integrates multi-source Earth observation records, combining 16-day MODIS MOD13C1 vegetation indices (NDVI), ERA5-Land surface meteorological reanalysis (temperature, precipitation, downward solar radiation, GDD, EDD, VPD, extreme climate indices, and dual-layer volumetric soil moisture SWVL1/SWVL2), USDA Cropland Data Layer (CDL) crop-specific geographic masks, and official USDA county-level statistical crop yield densities.
All continuous physical variables were harmonized, cropped across the CONUS bounding box (25.9°N–49.0°N, 123.1°W–69.1°W), and extracted around target field centroids across three spatial receptive fields ($8\times8$, $24\times24$, and $56\times56$ grids at 0.1° base resolution). Features were resampled to a standardized $8\times8$ patch tensor using bilinear interpolation, while discrete crop masks were preserved using nearest-neighbor interpolation.The dataset spans 18 consecutive production years from 2008 to 2025 with an 8-month monthly temporal sequence covering the key crop growing season (March to October).
Read the rest (2 more)
Stored in a standardized Zarr array format compressed with Blosc (LZ4 level 5), the archive contains 420,102 samples covering two major crops (214,355 corn samples under crop ID 0 and 205,747 soybean samples under crop ID 1). Each sample comprises an 8-month, 36-channel dynamic tensor of shape (8, 36, 8, 8), a 9-channel static geographic/topographic prior tensor of shape (9, 8, 8), a corresponding $8\times8$ binary crop mask, geographic centroid coordinates (lat, lon), production year, crop classification ID, and a scalar target yield label in metric tons per hectare (t/ha).
Physical variables have been filtered for quality with no invalid NaN or infinite values, while unharvested or inference-only grid instances without survey ground truth are encoded with a standard sentinel label of -1.0. The data can be directly loaded and processed in Python using the official zarr library (version 2.12 or higher, zarr.readthedocs.io) or PyTorch spatial dataloaders without complex decompression overhead.
Links
Where it is published
- DOI doi.org/10.57760/sciencedb.0133e ↗
DOI / persistent id · from scidb cn
Catalogue records · 1
- OAI-PMH record scidb.cn/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.57760%2… ↗
metadata API · from scidb cn
Topics
- From keywords
- Earth & Environmental Science · Engineering · Humanities · Life Sciences · Social Science
- Inferred from text
- Crop and pasture production 69% · Satellite remote sensing 65%
Provenance · 1 source records, 12 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| ScienceDB | 10.57760/sciencedb.0133e | 12 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].anzsrc:group:3004 | enrichment · scidb cn | taxonomy-embedding@1.0.0 | title+keywords+description (69%) |
| concepts[field].local:field:earth-environmental | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:engineering | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:humanities | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:social-science | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[modality].local:modality:remote-sensing | enrichment · scidb cn | keyword-concept-rules@1.0.0 | title+description (65%) |
| description | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/description |
| license | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/rights |
| publication_date | source · scidb cn | connector:scidb_cn@1.0.0 | |
| title | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/title |