From Forecast Skill to Economic Value: Sub-Hourly Wildfire Potential Forecasting Across Australian Regions

Background. Wildfire risk is rising under climate change, yet most operational forecasts rely on daily indices that miss rapid sub-daily weather shifts preceding ignition. Accurate, timely, and economically justified forecasts are critical for early warning and resource allocation. Aims. This study evaluates a sub-hourly machine-learning (ML) forecasting system for fire potential using weather-station data from three Australian regions—Sunshine Coast, Brisbane, and Hobart—and quantifies its economic value using a cost–loss framework. Methods. ML classifiers were trained on sub-hourly Automatic Weather Station data and benchmarked against the Fire Behaviour Index (FBI). Forecast discrimination was assessed using true positive and false positive rates, as well as a potential economic value (PEV) analysis, over more than 15 years for each region, complemented by learning-curve tests of data sufficiency and cross-regional transferability. Key results. The ML model improved forecast skill over the FBI by 30% in the Sunshine Coast, 20% in Hobart, and 10% in Brisbane. Economic evaluation showed consistent net benefits, with the ML system doubling potential savings relative to the FBI under realistic suppression and loss assumptions. Learning-curve diagnostics indicated that stable performance is achieved after ~30 fire events, enabling application in data-scarce regions. Conclusions. The ML forecasting framework demonstrates not only enhanced predictive skill but also measurable economic value, highlighting its potential for scalable, cost-effective early-warning systems. Implications. By linking forecast skill directly to financial and operational outcomes, this approach provides a quantitative basis for prioritising investment in timely, data-driven fire-warning tools across regions with limited data and constrained budgets.