Not a fragment, but the whole: Map-based evaluation of data-driven Fire Danger Index models

TL;DR

This paper introduces a new map-based evaluation method for fire danger prediction models, emphasizing operational relevance and false positive management, and demonstrates ensemble models' effectiveness in improving fire detection and reducing false alarms.

Contribution

It proposes a novel evaluation approach aligned with real-world decision-making and systematically assesses model performance, highlighting the benefits of ensemble methods.

Findings

Ensemble models improve fire detection accuracy.

The new evaluation method better reflects operational needs.

Ensemble models reduce false positive rates.

Abstract

A growing body of literature has focused on predicting wildfire occurrence using machine learning methods, capitalizing on high-resolution data and fire predictors that canonical process-based frameworks largely ignore. Standard evaluation metrics for an ML classifier, while important, provide a potentially limited measure of the model's operational performance for the Fire Danger Index (FDI) forecast. Furthermore, model evaluation is frequently conducted without adequately accounting for false positive rates, despite their critical relevance in operational contexts. In this paper, we revisit the daily FDI model evaluation paradigm and propose a novel method for evaluating a forest fire forecasting model that is aligned with real-world decision-making. Furthermore, we systematically assess performance in accurately predicting fire activity and the false positives (false alarms). We further demonstrate that an ensemble of ML models improves both fire identification and reduces false positives.