Published May 18, 2022 | Version 1.0

Sample data for "A weakly supervised framework for high resolution crop yield forecasts"

  • 1. Wageningen University and Research

Description

This dataset includes sample data for the United States to run the weakly supervised framework as described in the paper titled A weakly supervised framework for high resolution crop yield forecasts, accessible at 

https://doi.org/10.48550/arXiv.2205.09016

 

The updated paper (including results from the US) is published in Environmental Research Letters:

https://doi.org/10.1088/1748-9326/acf50e

 

The software implementation of the machine learning baseline is available at: https://github.com/BigDataWUR/MLforCropYieldForecasting/tree/weaksup.

 

Data

1. County data (county-data.zip) for county-level strongly supervised models:

* CROP_AREA_COUNTY_US.csv: County crop production area statistics (acres). Source: NASS (USDA-NASS, 2022).

* CSSF_COUNTY_US.csv: Crop productivity indicators including total above-ground production (kg ha-1), total weight of storage organs (kg ha-1), development stage (0-2). Source: de Wit et al. (2022).

* METEO_COUNTY_US.csv: Meteo data including maximum, minimum, average daily air temperature (℃); sum of daily precipitation (PREC) (mm); sum of daily evapotranspiration of short vegetation (ET0) (Penman-Monteith, Allen et al., (1998)) (mm); climate water balance = (PREC - ET0) (mm). Source: Boogaard et al. (2022).

* REMOTE_SENSING_COUNTY_US.csv: Fraction of Absorbed Photosynthetically Active Radiation (Smoothed) (FAPAR). Source: Copernicus GLS (2020).

* SOIL_COUNTY_US.csv: Soil water holding capacity. Source: WISE Soil Property Database (Batjes, 2016).

* YIELD_COUNTY_US.csv: County yield statistics (bushels/acre). Source: NASS (USDA-NASS, 2022).

 

2. 10-km grid data (grid-data.zip) for grid-level strongly supervised models:

* COUNTY_GRIDS_US.csv: Mapping between counties and grids.

* CSSF_GRIDS_US.csv: Crop productivity indicators at 10km grid level (similar to county data above).

* METEO_GRIDs_US.csv: Meteo data at 10km grid level (similar to county data above).

* REMOTE_SENSING_GRIDS_US.csv: FAPAR at 10km grid level (similar to county data above).

* SOIL_GRIDS_US.csv: Soil water holding capacity at 10km grid level (similar to county data above).

* YIELD_GRIDS_US.csv: Grid-level modeled yields (t ha-1). Source: Deines et al. (2021), Lobell et al. (2020).

 

3. County labels and 10-km grid inputs (dscale-US.zip) for weak supervision:

* COUNTY_GRIDS_US.csv: Mapping between counties and grids.

* CSSF_GRIDS_US.csv: Crop productivity indicators at 10km grid level.

* METEO_GRIDs_US.csv: Meteo indicators at 10km grid level.

* REMOTE_SENSING_GRIDS_US.csv: FAPAR at 10km grid level.

* SOIL_GRIDS_US.csv: Soil water holding capacity at 10km grid level.

* YIELD_GRIDS_US.csv: Grid-level modeled yields (t ha-1). Source: Deines et al. (2021).

* YIELD_COUNTY_US.csv: County yield statistics (bushels/acre). Source: NASS (USDA-NASS, 2022).

* CROP_AREA_COUNTY_US.csv: County crop production area statistics (acres). Source: NASS (USDA-NASS, 2022).

Files

county-data.zip

Files (1.1 GB)

Name Size
md5:b7cf000262da294caffc2fea39932246
50.1 MB Preview Download
md5:247382fbe1aedf392b36ca214449ce81
532.9 MB Preview Download
md5:f7379fdadc36076a20420aae95826fe0
532.4 MB Preview Download
md5:31605b7623e2b6d9461d38ba45ec72a6
984.8 kB Preview Download

Additional details

Funding

European Commission
CYBELE - FOSTERING PRECISION AGRICULTURE AND LIVESTOCK FARMING THROUGH SECURE ACCESS TO LARGE-SCALE HPC-ENABLED VIRTUAL INDUSTRIAL EXPERIMENTATION ENVIRONMENT EMPOWERING SCALABLE BIG DATA ANALYTICS 825355

References

  • Niels H Batjes. Harmonized soil property values for broad-scale modelling (WISE30sec) with estimates of global soil carbon stocks. Geoderma, 269:61–68, 2016. doi:10.1016/j.geoderma.2016.01.034.
  • H. Boogaard, J. Schubert, A. De Wit, J. Lazebnik, R. Hutjes, and G. Van der Grijn. Agrometeorological indicators from 1979 to present derived from reanalysis. Climate Data Store - Copernicus Climate Change Service, https://doi.org/10.24381/cds.6c68c9bb, 2022.
  • Copernicus CDS. Copernicus Climate Data Store. Copernicus Climate Change Service, https://cds.climate.copernicus.eu/, 2022.
  • Copernicus GLS. Fraction of Absorbed Photosynthetically Active Radiation, 2020. https://land.copernicus.eu/global/products/fapar, Last accessed: Oct 19, 2020.
  • Jillian M Deines. (2020). SCYM Maize Yield Maps (Low Resolution) from Deines et al. 2021, Lobell et al. 2020 [Data set]. In Remote Sensing of Environment (v1.0.0). Zenodo. https://doi.org/10.5281/zenodo.4267589
  • Jillian M Deines, Rinkal Patel, Sang-Zi Liang, Walter Dado, and David B Lobell. A million kernels of truth: insights into scalable satellite maize yield mapping and yield gap analysis from an extensive ground dataset in the US corn belt. Remote Sensing of Environment, 253:112174, 2021 doi:10.1016/j.rse.2020.112174.
  • D.B. Lobell, J.M. Deines, & S. Di Tomasso. 2020. Changes in the drought sensitivity of U.S. maize yields. Nature Food 1:729-735. https://doi.org/10.1038/s43016-020-00165-w
  • Allard de Wit, A. Elhaddad, S. Meyer zum Alten Borgloh, U.D. Turdukulov, and R.W.A. Hutjes. Crop productivity and evapotranspiration indicators from 2000 to present derived from satellite observations. Climate Data Store - Copernicus Climate Change Service, https://doi.org/10.24381/cds.b2f6f9f6, 2022.