Handling Climate Change Using Counterfactuals: Using Counterfactuals in Data Augmentation to Predict Crop Growth in an Uncertain Climate Future

Climate change poses a major challenge to humanity, especially in its impact on agriculture, that responsible AI should meet. In this paper, we examine CBR system (PBI-CBR) designed aid sustainable dairy farming by supporting grassland management, through accurate crop growth prediction. As climate changes, PBI-CBR’s historical cases become less useful predicting future grass growth. Hence, extend PBI-CBR using data augmentation, specifically handle disruptive events, counterfactual method (from XAI). Study 1 shows historical, extreme climate-events (climate outlier cases) tend be used predict during disrupted periods. 2 synthetic outliers, generated as counterfactuals an outlier-boundary, improve the predictive accuracy of PBI-CBR, drought 2018. This study also case-based does better than benchmark, constraint-guided method.