Seasonal prediction of climate-driven fire risk for decision-making and operational applications in a Mediterranean region
Marco Turco, Raul Marcos-Matamoros, Xavier Castro, Esteve Canyameras,, Maria Carmen Llasat

TL;DR
This study develops a seasonal fire risk prediction system for a Mediterranean region using climate forecasts and stakeholder input, improving proactive fire management and risk assessment.
Contribution
It introduces a data-driven, participatory approach to forecast summer wildfires by linking drought indicators with burned area data and assessing forecast skill.
Findings
The forecasting system shows useful predictive ability for burned areas.
Observed initial conditions significantly influence drought and fire risk.
Stakeholder involvement enhances system relevance and usability.
Abstract
In this paper, we assess and develop a climate service focused on the production of seasonal predictions for summer wildfires in a Mediterranean region through a participatory approach with end-users. We start by building a data-driven model that links a drought indicator (Standardised Precipitation Evapotranspiration Index; SPEI) with a series of burned areas in Catalonia (northeastern Spain). Afterwards, we feed this model with SPEI forecasts obtained through a combination of the antecedent observed conditions and climatology. Finally, we assess the forecasting skill of the system by using cross-validation to evaluate the predictions as if they had been made operationally. Our fire forecasting system reveals an untapped and useful burned area predictive ability. We argue that this source of predictability is mostly attributable to the effect of observed initial conditions on summer…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
