Simple yet effective: a comparative study of statistical models for yearly hurricane forecasting

TL;DR

This study compares machine learning and simple statistical models for predicting annual Atlantic hurricane counts, finding that simpler models, especially quantile regression, outperform more complex methods and can effectively anticipate hurricane trends.

Contribution

The paper introduces the first application of quantile regression for hurricane forecasting and proposes a new index for predicting hurricane direction, demonstrating their effectiveness.

Findings

Quantile regression models outperform other models in accuracy.

Simpler models may be more suitable than complex machine learning approaches.

A new index effectively predicts the direction of future hurricane numbers.

Abstract

In this paper, we study the problem of forecasting the next year's number of Atlantic hurricanes, which is relevant in many fields of applications such as land-use planning, hazard mitigation, reinsurance and long-term weather derivative market. Considering a set of well-known predictors, we compare the forecasting accuracy of both machine learning and simpler models, showing that the latter may be more adequate than the first. Quantile regression models, which are adopted for the first time for forecasting hurricane numbers, provide the best results. Moreover, we construct a new index showing good properties in anticipating the direction of the future number of hurricanes. We consider different evaluation metrics based on both magnitude forecasting errors and directional accuracy.