Introduction

Gro’s China Corn Yield Models, like our other yield models, provide in-season forecasts of corn yields in China. Gro offers three Yield Models for Corn in China. These three models use similar inputs and methodologies, but each of the three uses ground truth from a different well-known industry source.

The models predict province-level yields for the 7 main corn-producing provinces in China, which together account for over 70% of China’s corn production.

These machine learning models are driven by inputs reflecting long term trends as well as in-season changes. The models run daily throughout the growing season, and rely on province-by-province signals derived using our domain expertise. They rely on proprietary crop masks, built using high resolution satellite imagery to match estimates of area planted from each source.

Major Model inputs and features include:

  • Crop-masked NDVI
  • Temperature from GHCN
  • Evapotranspiration
  • Soil texture

 

We have made these daily forecasts and commentary publicly available on our web app. For more technical information, you can download our yield model research paper here that lays the technical foundation for our yield modeling approach (using the example of corn in the US) or contact us at intel@gro-intelligence.

You can see the results of the China Corn Yield Models in the Gro Platform here. Please note that we are implementing these gradually, but all three will be available by the time planting is completed, i.e. in early June.