Weather index insurance parameter optimisation using machine learning and remote sensing data

Weather Index Insurance offers protection from extreme corn yield losses. A novel framework is proposed for developing a transparent WII multi-index utilising machine learning. Transparency is achieved for policyholders by applying a surrogate model to machine learning predictions. The surrogate model achieved an MAE of 9.5%, with comparable accuracy to the neural network model (MAE of 7.25%). The proposed index is a linear combination of diverse remote sensing indexes (e.g. EVI, ET, VHI, LST, GPP, NDVI) that captures multi-perils impacting yield. The framework achieved substantial hedging efficiency with a 33% downside risk reduction.