000171165 001__ 171165
000171165 005__ 20260515163945.0
000171165 0247_ $$2doi$$a10.3390/fire9040138
000171165 0248_ $$2sideral$$a149252
000171165 037__ $$aART-2026-149252
000171165 041__ $$aeng
000171165 100__ $$aOchoa, Clara
000171165 245__ $$aInferring Wildfire Ignition Causes in Spain Using Machine Learning and Explainable AI
000171165 260__ $$c2026
000171165 5060_ $$aAccess copy available to the general public$$fUnrestricted
000171165 5203_ $$aA substantial proportion of wildfires in Mediterranean regions continue to be recorded without information about the cause or source of ignition, limiting our ability to understand ignition drivers and design effective prevention strategies. In this study, we develop a spatially harmonised wildfire database for mainland Spain by integrating ignition records from the Spanish General Fire Statistics (EGIF) with fire perimeters generated from satellite images. We then apply a Random Forest classifier to infer ignition causes for events lacking cause attribution. To interpret model behaviour, we use Shapley Additive Explanation (SHAP) values at both global and local scales. Results indicate that human-caused ignitions are dominant, with intentional and negligence-related fires accounting for 52.13% of all known events, although they are associated with contrasting climatic and land-use settings. Negligence-related fires tend to occur under hot, dry and windy conditions, often in agricultural interfaces, whereas intentional fires are more frequent under cooler and wetter conditions and in areas with higher population density and land-use change. Lightning-caused fires represent a small fraction of total ignitions (3%) but exhibit a distinct climatic signature, occurring primarily in sparsely populated areas, under intermediate moisture conditions, and often leading to larger burned areas. Despite strong overall model performance (F1-score = 0.82), minority classes (e.g., lightning and fire rekindling, 0.17%) remain challenging to classify, reflecting both data imbalance and uncertainty in causal attribution. Overall, the combined use of machine learning and explainable AI provides a coherent spatial characterisation of wildfire ignition drivers across mainland Spain, highlights systematic differences among ignition causes, and identifies key limitations in existing fire cause records. This framework represents a practical step towards improving fire cause information by integrating remote sensing products with field-based fire reports, thereby supporting more targeted and evidence-based fire risk management.
000171165 536__ $$9info:eu-repo/grantAgreement/EC/H2020/101003890/EU/FIREURISK - DEVELOPING A HOLISTIC, RISK-WISE STRATEGY FOR EUROPEAN WILDFIRE MANAGEMENT/FirEUrisk$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 101003890-FirEUrisk$$9info:eu-repo/grantAgreement/ES/MICINN/JDC2022-048710-I
000171165 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000171165 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000171165 700__ $$aFranquesa, Magí
000171165 700__ $$0(orcid)0000-0002-0477-0796$$aRodrigues, Marcos$$uUniversidad de Zaragoza
000171165 700__ $$aChuvieco, Emilio
000171165 7102_ $$13006$$2010$$aUniversidad de Zaragoza$$bDpto. Geograf. Ordenac.Territ.$$cÁrea Análisis Geográfico Regi.
000171165 773__ $$g9, 4 (2026), 138 [20 pp.]$$pFire$$tFire (Basel)$$x2571-6255
000171165 8564_ $$s2698947$$uhttps://zaguan.unizar.es/record/171165/files/texto_completo.pdf$$yVersión publicada
000171165 8564_ $$s2455597$$uhttps://zaguan.unizar.es/record/171165/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000171165 909CO $$ooai:zaguan.unizar.es:171165$$particulos$$pdriver
000171165 951__ $$a2026-05-15-14:54:14
000171165 980__ $$aARTICLE