Real-time Prediction of Crop Yields from MODIS Relative Vegetation Health: A Continent-wide Analysis of Africa

Developing countries often have poor monitoring and reporting of weather and crop health, leading to slow responses to droughts and food shortages. Here I develop satellite analysis methods and software tools to predict crop yields two to four months before the harvest. This method measures relative vegetation health based on pixel-level monthly anomalies of NDVI, EVI and NDWI. Because no crop mask, tuning, or subnational ground truth data is required, this method can be applied to any location, crop, or climate, making it ideal for African countries with small fields and poor ground observations. Testing began in Illinois where there is reliable county-level crop data. Correlations were computed between corn, soybean, and sorghum yields and monthly vegetation health anomalies for every county and year, and a multivariate regression using every index and month (1600 values) produced a correlation of 0.86 with a p-value less than 10e-6. The high correlations in Illinois show that this model has good forecasting skill for crop yields. Next, the method was applied to every country in Africa for each country’s main crops. Crop production was then predicted for the 2018 harvest and compared to actual production values. Twenty percent of the predictions had less than 2% error, and 40% had less than 5% error. The beauty of this method is its simplicity. The model was developed solely by the author over the course of several months, and the full analysis was run on a laptop computer. And yet this straightforward method produces high quality crop predictions across vastly different crops and landscapes.