On the Generalization of Agricultural Drought Classification from Climate Data. Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) Workshop 2021 "Tackling Climate Change with Machine Learning"

Abstract

Climate change is expected to increase the likelihood of drought events, with severe implications for food security. Unlike other natural disasters, droughts have a slow onset and depend on various external factors, making drought detection in climate data difficult. In contrast to existing works that rely on simple relative drought indices as ground-truth data, we build upon SMI from a hydrological model, which is directly related to insufficiently available water to vegetation. Given ERA5-Land climate input data of six months with landuse information from MODIS satellite observation, we compare different models with and without sequential inductive bias in their ability to classify droughts based on SMI. We use PR-AUC and Macro F1 Score as evaluation measures to account for the class imbalance and obtain promising results despite a challenging time-based split. We show in an ablation study that the models retain their predictive capabilities given input data of coarser resolutions, as frequently encountered in climate models.