Precise and reliable crop yield prediction serves as a valuable tool empowering farmers to make informed and sustainable decisions. However, yield prediction is intricately challenging due to the various factors that play a role in the complex landscape of crop growth. In this paper, we propose an operational yield forecasting approach based on spatiotemporal Machine Learning and a many-to-many network structure. We demonstrate that the simultaneous consideration of spatial and temporal dependencies of crop yield substantially improves the yield prediction performance on field and subfield level across all regions of our large-scale dataset. We further show how our many-to-many network structure leads to outstanding operational results.

Accurate and reliable crop yield prediction is a complex task. The yield of a crop depends on a variety of factors whose accurate measurement and modeling is challenging. At the same time, reliable yield prediction is highly desirable for farmers to optimize crop production. In this paper, we introduce a modeling based on remote sensing data and Machine Learning models evaluated on a large-scale dataset to address the challenge of an operational crop yield estimation and forecasting on field and subfield level. With our approach, we aim towards a global yield modeling based on Machine Learning models which operates across crop types without the need for crop-specific modeling. We demonstrate that our approach learns to map in-field variability for all studied crop types. Overall, the predictions have an error (RRMSE) of around 15% and an R2value of 0.77 at field level.

Numerous remote sensing applications rely on temporal satellite data, and Deep learning models are increasingly being used for such tasks. Nevertheless, these models operate as black boxes, lacking transparency and understandability. We address this gap by using explainable AI on an agricultural task. Specifically, we trained a recurrent neural network on individual pixels from multispectral time-series of Sentinel-2 satellite images to predict crop yield. We then applied nine feature attribution methods on a sample of the dataset and computed the spectral and temporal contributions to the final individual predictions. The aggregated results were evaluated qualitatively and quantitatively. Results suggest that LIME and Shapley sampling value methods performed best on the quantitative scores, followed by GradientShap. Most backpropagation-based techniques had highly inconsistent scores across the explained data points. Finally, to guide remote sensing practitioners in using Explainable AI on similar datasets, we further discuss some selection criteria to be considered.

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.

Modern combine harvesters can collect geo-located real-time yield measurement while harvesting. This data can be used to train Machine Learning models that predict the yield at sub-field level based on remote sensing input data. The performance of these models is, however, highly dependent on the quality of the yield data. It is therefore important to develop automatic cleaning techniques to correct for common errors in combine harvester yield maps. In this work, we compare different combinations of data cleaning techniques by evaluating their impact on the yield-prediction model performance at field and sub-field level. Our findings indicate that basic cleaning techniques such as absolute thresholds are sufficient at the field level, whereas the performance at the sub-field level is enhanced through the utilization of more intricate statistical cleaning methods.