Forecasting the cost of drought events in France by Super Learning

TL;DR

This paper introduces a novel Super Learning-based methodology to accurately forecast the costs of drought events in France, accounting for spatial and temporal dependencies, to improve disaster cost predictions.

Contribution

It develops a new Super Learning approach tailored for drought cost forecasting, incorporating spatial-temporal data dependencies, which is a novel application in this context.

Findings

Super Learner outperforms individual algorithms in forecasting accuracy.

The methodology effectively captures complex spatial-temporal dependencies.

Forecasting model provides reliable cost estimates for drought events.

Abstract

Drought events are the second most expensive type of natural disaster within the French legal framework known as the natural disasters compensation scheme. In recent years, drought events have been remarkable in their geographical scale and intensity. We develop and apply a new methodology to forecast the cost of a drought event in France. The methodology hinges on Super Learning (van der Laan et al., 2007; Benkeser et al., 2018), a general aggregation strategy to learn a feature of the law of the data identified through an ad hoc risk function by relying on a library of algorithms. The algorithms either compete (discrete Super Learning) or collaborate (continuous Super Learning), with a cross-validation scheme determining the best performing algorithm or combination of algorithms, respectively. Our Super Learner takes into account the complex dependence structure induced in the data by the spatial and temporal nature of drought events.