Predicting Crop Yield With Machine Learning: An Extensive Analysis Of Input Modalities And Models On a Field and sub-field Level
This work addresses crop yield prediction for agricultural stakeholders, but it is incremental as it builds on existing methods with a focus on modality combinations.
The paper tackles crop yield prediction by introducing an early fusion method that integrates multiple input modalities like satellite imagery, weather, soil, and DEM data, achieving globally scalable results at the sub-field level, though no concrete numbers are provided.
We introduce a simple yet effective early fusion method for crop yield prediction that handles multiple input modalities with different temporal and spatial resolutions. We use high-resolution crop yield maps as ground truth data to train crop and machine learning model agnostic methods at the sub-field level. We use Sentinel-2 satellite imagery as the primary modality for input data with other complementary modalities, including weather, soil, and DEM data. The proposed method uses input modalities available with global coverage, making the framework globally scalable. We explicitly highlight the importance of input modalities for crop yield prediction and emphasize that the best-performing combination of input modalities depends on region, crop, and chosen model.