Pasar al contenido principal

Dinámica de la cubierta vegetal de zonas áridas y semiáridas bajo un contexto de cambio climático

JDC2022-048710-I

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Desarrollar, Atraer y Retener Talento
Subprograma Subprograma Estatal de Formación
Convocatoria Juan de la Cierva
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Near-real-time vegetation monitoring and historical database (1981–present) for the Iberian Peninsula and the Balearic Islands

  • Franquesa, Magí
  • Reig-Gracia, Fergus
  • Arretxea Iriarte, Manuel
  • Adell-Michavila, Maria
  • Halifa-Marín, Amar
  • Vilas, Daniel
  • Beguería, Santiago
  • Vicente Serrano, Sergio M.
This preprint is currently under review for the journal ESSD., Systematic monitoring and assessment of vegetation dynamics and changes are essential for informing environmental management and conservation strategies. Addressing this need, our study introduces a pioneering procedure to generate a database of vegetation indices that provides semi-monthly updates from 1981 to the present at a 1.1 km spatial resolution, focusing on the Iberian Peninsula and the Balearic Islands. This database enables near-real-time monitoring and analysis of vegetation anomalies. The methodology developed combines harmonized historical satellite imagery from AVHRR, MODIS, and VIIRS sensors. The database's performance was assessed, demonstrating highly accurate and consistent harmonization of NDVI data over time. Notably, the database is adept at identifying temporal variability and trends in vegetation activity and detecting disturbances caused by fire and other phenomena. This work not only advances our understanding of vegetation dynamics in the region but also serves as a crucial tool for policymakers, environmental managers, and agricultural stakeholders. By providing near-real-time updates and using indices to monitor vegetation anomalies, the data allows for comparisons across seasons and vegetation types. The database, which includes the NDVI and kNDVI vegetation indices as well as their standardized versions, SNDVI and SkNDVI, is accessible via https://doi.org/10.20350/digitalCSIC/16201 (Franquesa et al., 2024)., This research has been supported by the Grant JDC2022-048710-I funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Inferring Wildfire Ignition Causes in Spain Using Machine Learning and Explainable AI

  • Ochoa, Clara
  • Franquesa, Magí
  • Rodrigues, Marcos
  • Chuvieco, Emilio
This article belongs to the Topic AI for Natural Disasters Detection, Prediction and Modeling, A 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., This paper is funded by the H2020 Project FirEUrisk (Grant Agreement Number: 101003890). The FirEUrisk project contributions reported in this paper were carried out by Rodrigues, M., Ochoa, C. and Chuvieco, E. Franquesa, M. was supported by the Grant JDC2022-048710-I, funded by MCIN/AEI/10.13039/501100011033, and by the European Union NextGenerationEU/PRTR., Peer reviewed
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Inferring Wildfire Ignition Causes in Spain Using Machine Learning and Explainable AI

  • Ochoa, Clara
  • Franquesa, Magí
  • Rodrigues, Marcos
  • Chuvieco, Emilio
A 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.