Scalable Crop Yield Prediction with Sentinel-2 Time Series and Temporal Convolutional Network

One of the precepts of food security is the proper functioning of the global food markets. This calls for open and timely intelligence on crop production on an agroclimatically meaningful territorial scale. We propose an operationally suitable method for large-scale in-season crop yield estimations from a satellite image time series (SITS) for statistical production. As an object-based method, it is spatially scalable from parcel to regional scale, making it useful for prediction tasks in which the reference data are available only at a coarser level, such as counties. We show that deep learning-based temporal convolutional network (TCN) outperforms the classical machine learning method random forests and produces more accurate results overall than published national crop forecasts. Our novel contribution is to show that mean-aggregated regional predictions with histogram-based features calculated from farm-level observations perform better than other tested approaches. In addition, TCN is robust to the presence of cloudy pixels, suggesting TCN can learn cloud masking from the data. The temporal compositing of information do not improve prediction performance. This indicates that with end-to-end learning less preprocessing in SITS tasks seems viable.

Automated summary

One of the key principles of food security is to ensure the proper functioning of global food markets. This study proposes a method for large-scale crop yield estimations using satellite image time series, and demonstrates that a deep learning-based temporal convolutional network outperforms traditional machine learning methods and national crop forecasts in accuracy. The study also shows that mean-aggregated regional predictions with histogram-based features calculated from farm-level observations perform better than other tested approaches.