Predicting crop yields with little ground truth: A simple statistical model for in-season forecasting

TL;DR

This paper introduces a simple, automated satellite-data-based model for in-season crop yield prediction that performs well across diverse regions with minimal ground truth data, providing timely forecasts.

Contribution

It presents a novel, easy-to-implement regression approach leveraging satellite data for accurate in-season crop yield forecasting worldwide.

Findings

Achieves 5%-10% RMSE for predictions 9 months into the season.

Achieves 7%-14% RMSE for predictions 3 months into the season.

Works effectively across multiple crops and countries with minimal ground truth data.

Abstract

We present a fully automated model for in-season crop yield prediction, designed to work where there is a dearth of sub-national "ground truth" information. Our approach relies primarily on satellite data and is characterized by careful feature engineering combined with a simple regression model. As such, it can work almost anywhere in the world. Applying it to 10 different crop-country pairs (5 cereals -- corn, wheat, sorghum, barley and millet, in 2 countries -- Ethiopia and Kenya), we achieve RMSEs of 5%-10% for predictions 9 months into the year, and 7%-14% for predictions 3 months into the year. The model outputs daily forecasts for the final yield of the current year. It is trained using approximately 4 million data points for each crop-country pair. These consist of: historical country-level annual yields, crop calendars, crop cover, NDVI, temperature, rainfall, and evapotransporation.