Logo do repositório
 
Publicação

Integration of a Deep-Learning-Based Fire Model Into a Global Land Surface Model

2024-01Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorSon, Rackhun
dc.contributor.authorStacke, Tobias
dc.contributor.authorGayler, Veronika
dc.contributor.authorNabel, Julia E. M. S.
dc.contributor.authorSchnur, Reiner
dc.contributor.authorAlonso, Lazaro
dc.contributor.authorRequena-Mesa, Christian
dc.contributor.authorWinkler, Alexander J.
dc.contributor.authorHantson, Stijn
dc.contributor.authorZaehle, Sönke
dc.contributor.authorWeber, Ulrich
dc.contributor.authorCarvalhais, Nuno
dc.contributor.institutionDCEA - Departamento de Ciências e Engenharia do Ambiente
dc.contributor.pblJohn Wiley and Sons Inc.
dc.date.accessioned2024-09-26T22:23:48Z
dc.date.available2024-09-26T22:23:48Z
dc.date.issued2024-01
dc.descriptionFunding Information: This project has received funding from the European Union's H2020 research and innovation programme under grant agreement N.101003536 (ESM2025 ‐ Earth System Models for the Future). We should secondly acknowledge SeasFire (Lazaro), DeepCube (Christian) and USMILE (Alex). Stijn acknowledges support from the Max Planck Tandem group program. Also, we appreciate valuable comments for elevating the quality of the manuscript from two anonymous reviewers. This work used resources of the Deutsches Klimarechenzentrum (DKRZ) and the Max Planck Gesellschaft (MPG) under project ID mj0143. Further, data sets provided by the Max Planck Institute for Meteorology (MPI‐M) via the DKRZ data pool were used. Open Access funding enabled and organized by Projekt DEAL. Funding Information: This project has received funding from the European Union's H2020 research and innovation programme under grant agreement N.101003536 (ESM2025 - Earth System Models for the Future). We should secondly acknowledge SeasFire (Lazaro), DeepCube (Christian) and USMILE (Alex). Stijn acknowledges support from the Max Planck Tandem group program. Also, we appreciate valuable comments for elevating the quality of the manuscript from two anonymous reviewers. This work used resources of the Deutsches Klimarechenzentrum (DKRZ) and the Max Planck Gesellschaft (MPG) under project ID mj0143. Further, data sets provided by the Max Planck Institute for Meteorology (MPI-M) via the DKRZ data pool were used. Open Access funding enabled and organized by Projekt DEAL. Publisher Copyright: © 2024 The Authors. Journal of Advances in Modeling Earth Systems published by Wiley Periodicals LLC on behalf of American Geophysical Union.
dc.description.abstractFire is a crucial factor in terrestrial ecosystems playing a role in disturbance for vegetation dynamics. Process-based fire models quantify fire disturbance effects in stand-alone dynamic global vegetation models (DGVMs) and their advances have incorporated both descriptions of natural processes and anthropogenic drivers. Nevertheless, these models show limited skill in modeling fire events at the global scale, due to stochastic characteristics of fire occurrence and behavior as well as the limits in empirical parameterizations in process-based models. As an alternative, machine learning has shown the capability of providing robust diagnostics of fire regimes. Here, we develop a deep-learning-based fire model (DL-fire) to estimate daily burnt area fraction at the global scale and couple it within JSBACH4, the land surface model used in the ICON-ESM. The stand-alone DL-fire model forced with meteorological, terrestrial and socio-economic variables is able to simulate global total burnt area, showing 0.8 of monthly correlation (rm) with GFED4 during the evaluation period (2011–2015). The performance remains similar with the hybrid modeling approach JSB4-DL-fire (rm = 0.79) outperforming the currently used uncalibrated standard fire model in JSBACH4 (rm = −0.07). We further quantify the importance of each predictor by applying layer-wise relevance propagation (LRP). Overall, land properties, such as fuel amount and water content in soil layers, stand out as the major factors determining burnt fraction in DL-fire, paralleled by meteorological conditions over tropical and high latitude regions. Our study demonstrates the potential of hybrid modeling in advancing fire prediction in ESMs by integrating deep learning approaches in physics-based dynamical models.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent17
dc.format.extent2439002
dc.identifier.doi10.1029/2023MS003710
dc.identifier.issn1942-2466
dc.identifier.otherPURE: 99694888
dc.identifier.otherPURE UUID: e587eb3d-6664-4951-a380-d02c64fa9e03
dc.identifier.otherScopus: 85170372294
dc.identifier.otherWOS: 001138419300001
dc.identifier.urihttp://hdl.handle.net/10362/172477
dc.identifier.urlhttps://www.scopus.com/pages/publications/85170372294
dc.language.isoeng
dc.peerreviewedyes
dc.subjectdeep learning
dc.subjectDGVM
dc.subjectfire
dc.subjecthybrid modeling
dc.subjectGlobal and Planetary Change
dc.subjectEnvironmental Chemistry
dc.subjectGeneral Earth and Planetary Sciences
dc.subjectSDG 15 - Life on Land
dc.titleIntegration of a Deep-Learning-Based Fire Model Into a Global Land Surface Modelen
dc.typejournal article
degois.publication.issue1
degois.publication.titleJournal of Advances in Modeling Earth Systems
degois.publication.volume16
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Integration_of_a_Deep-Learning-Based_Fire_Model_Into_a.pdf
Tamanho:
2.33 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)