Grouping Shapley Value Feature Importances of Random Forests for explainable Yield Prediction
This work addresses the need for explainable AI in agricultural yield prediction, offering a method to simplify model interpretation for researchers and practitioners, though it is incremental as it builds on existing Shapley value techniques.
The paper tackled the problem of interpreting complex yield prediction models by proposing a method to compute Shapley values directly for predefined feature groups, enabling more accurate explanations. It demonstrated the approach's effectiveness through evaluation on two yield prediction problems, showing improved model understanding.
Explainability in yield prediction helps us fully explore the potential of machine learning models that are already able to achieve high accuracy for a variety of yield prediction scenarios. The data included for the prediction of yields are intricate and the models are often difficult to understand. However, understanding the models can be simplified by using natural groupings of the input features. Grouping can be achieved, for example, by the time the features are captured or by the sensor used to do so. The state-of-the-art for interpreting machine learning models is currently defined by the game-theoretic approach of Shapley values. To handle groups of features, the calculated Shapley values are typically added together, ignoring the theoretical limitations of this approach. We explain the concept of Shapley values directly computed for predefined groups of features and introduce an algorithm to compute them efficiently on tree structures. We provide a blueprint for designing swarm plots that combine many local explanations for global understanding. Extensive evaluation of two different yield prediction problems shows the worth of our approach and demonstrates how we can enable a better understanding of yield prediction models in the future, ultimately leading to mutual enrichment of research and application.