Accurate and spatially explicit information on global crop yield is paramount for guiding policy-making and ensuring food security. However, most public datasets are at coarse resolution in both space and time. Here, we used datadriven models to develop a 4-km dataset of global wheat yield (GlobalWheatYield4km) from 1982 to 2020. First, we proposed 15 a phenology-based approach to map spatial distributions of spring and winter wheat. Then we determined the optimal gridscale yield estimation model by comparing the performance of two data-driven models (i.e., Random Forest (RF) and Long Short-Term Memory (LSTM)), with publicly available data (i.e., satellite and climatic data from the Google Earth Engine (GEE) platform, soil properties, and subnational-level census data covering ~11000 political units). The results showed that GlobalWheatYield4km captured 82% of yield variations with RMSE of 619.8 kg/ha across all subnational regions and years. In addition, our dataset had a higher accuracy (R2~0.71) as compared with Spatial Production Allocation Model (SPAM) (R2 20 ~ 0.49) across all subnational regions and three years. The GlobalWheatYield4km dataset might play important roles in modelling crop system and assessing climate impact over larger areas.
（1）Remote sensing data.We acquired the global daily 0.05° Normalized Difference Vegetation Index (NDVI) data during 1981-2021 derived from the Advanced Very High-Resolution Radiometer (AVHRR) sensor on the Google Earth Engine (GEE) platform(https://developers.google.com/earth-engine/datasets/).
(2) Wheat harvested area and yield.We collected subnational-level census data on harvested area (unit: ha), production (unit: ton), and yield (unit: kg/ha) from ~11000 administrative units for the 54 countries, with the longest time coverage spanning from 1981-2020. Yield is calculated as production divided by harvested area. Overall, 97% of data came from administrative unit level 2 (ADM2) and 3 (ADM3). For European Union, the data was collected at NUTS-2 level. The temporal coverage differs across the study area. We eliminated outliers of census data with values +/− 2 standard deviation from the average.
(3) Environmental Data.Meteorological information was obtained from high-spatial resolution (1/24°, ~4-km) monthly TerraClimate datasets. The climate variables used for this analysis were maximum temperature (Tmin), minimum temperatures (Tmax), precipitation (Pre), vapor pressure (Vap), vapor pressure deficit (Vpd), reference evapotranspiration (Petref), Soil moisture (Soil), palmer drought severity index (Pdsi), and downward surface shortwave radiation (Srad) from 110 1981 to 2021. In addition, soil properties were derived from Harmonized World Soil Database (HWSD) at 0.00833°(~1 km), involving bulk density, organic carbon content, pH, gravel, clay, sand and silt fraction for the topsoil (0-30cm).
We applied the framework, Global Wheat Production Mapping System (GWPMS) with two aspects of improvements. We conducted the study according to the follows: 1) mapping the harvesting area of spring and winter wheat by a phenology-based algorithm; 2) comparing the performances of two ML and DL approaches in predicting gridded yield, 3) generating the GlobalWheatYield4km dataset using the optimal model, and 4) evaluating the accuracy and uncertainty of the dataset.
The data quality is good.
This work is licensed under
CC BY 4.0 (Creative Commons Attribution 4.0 International License).
CSTR:11738.11.NCDC.FIGSHARE.DB4094.2023
10.6084/m9.figshare.10025006.v1
