000121443 001__ 121443
000121443 005__ 20240720100815.0
000121443 0247_ $$2doi$$a10.1016/j.jag.2022.103175
000121443 0248_ $$2sideral$$a131712
000121443 037__ $$aART-2023-131712
000121443 041__ $$aeng
000121443 100__ $$0(orcid)0000-0002-9123-304X$$aHoffrén, Raúl$$uUniversidad de Zaragoza
000121443 245__ $$aAssessing GEDI-NASA system for forest fuels classification using machine learning techniques
000121443 260__ $$c2023
000121443 5060_ $$aAccess copy available to the general public$$fUnrestricted
000121443 5203_ $$aIdentification of forest fuels is a key step for forest fire prevention since they provide valuable information of fire behavior. This study assesses NASA’s Global Ecosystem Dynamics Investigation (GEDI) system to classify fuel types in Mediterranean environments according to the Prometheus model in a forested area of NE Spain. We used 59,554 GEDI footprints and extracted variables related to height metrics, canopy profile metrics, and aboveground biomass density estimates from products L2A, L2B, and L4A, respectively. Four quality filters were applied to discard high uncertainty data, reducing the initial footprints to 9,703. Spectral indices from Landsat-8 OLI scenes were created to test the effect of their integration with GEDI variables on fuel types estimation. Ground-truth data were comprised of Prometheus fuel types estimated in two previous studies. Only the types that matched in each GEDI footprint in both studies were used, resulting in a final sample of 1,112 footprints. Spearman’s correlation coefficient, Kruskal-Wallis and Dunn’s tests determined the variables to be included in the classification models: the relative height at the 85th percentile, the Plant Area Index, and the Aboveground Biomass Density from GEDI, and the brightness from Landsat-8 OLI. Best performances were achieved with Random Forest (RF) and Support Vector Machine with radial kernel (SVM-R), which were lower including only GEDI variables (accuracies: RF and SVM-R = 61.54 %) than integrating the brightness from Landsat-8 OLI (accuracies: RF = 83.71 %, SVM-R = 81.90 %). These results allow validating GEDI for fuel type classification of Prometheus model, constituting a promising information for forest management over large areas.
000121443 536__ $$9info:eu-repo/grantAgreement/ES/DGA/S51-20R$$9info:eu-repo/grantAgreement/ES/MCIU/FPU18-05027$$9info:eu-repo/grantAgreement/ES/NextGenerationEU/MS-240621$$9info:eu-repo/grantAgreement/ES/UZ/CUD2020-07
000121443 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000121443 590__ $$a7.6$$b2023
000121443 592__ $$a2.108$$b2023
000121443 591__ $$aREMOTE SENSING$$b6 / 62 = 0.097$$c2023$$dQ1$$eT1
000121443 593__ $$aComputers in Earth Sciences$$c2023$$dQ1
000121443 593__ $$aManagement, Monitoring, Policy and Law$$c2023$$dQ1
000121443 593__ $$aGlobal and Planetary Change$$c2023$$dQ1
000121443 593__ $$aEarth-Surface Processes$$c2023$$dQ1
000121443 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000121443 700__ $$0(orcid)0000-0002-8954-7517$$aLamelas, María Teresa$$uUniversidad de Zaragoza
000121443 700__ $$0(orcid)0000-0003-2615-270X$$ade la Riva, Juan$$uUniversidad de Zaragoza
000121443 700__ $$0(orcid)0000-0002-8362-7559$$aDomingo, Darío
000121443 700__ $$0(orcid)0000-0001-6288-2780$$aMontealegre, Antonio Luis$$uUniversidad de Zaragoza
000121443 700__ $$0(orcid)0000-0003-2610-7749$$aGarcía-Martín, Alberto$$uUniversidad de Zaragoza
000121443 700__ $$0(orcid)0000-0001-8481-8712$$aRevilla, Sergio
000121443 7102_ $$13006$$2010$$aUniversidad de Zaragoza$$bDpto. Geograf. Ordenac.Territ.$$cÁrea Análisis Geográfico Regi.
000121443 773__ $$g116 (2023), 103175 [10 pp.]$$pInt J Appl Earth Obs Geoinf$$tInternational Journal of Applied Earth Observation and Geoinformation$$x1569-8432
000121443 8564_ $$s9587144$$uhttps://zaguan.unizar.es/record/121443/files/texto_completo.pdf$$yVersión publicada
000121443 8564_ $$s2597730$$uhttps://zaguan.unizar.es/record/121443/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000121443 909CO $$ooai:zaguan.unizar.es:121443$$particulos$$pdriver
000121443 951__ $$a2024-07-19-18:38:33
000121443 980__ $$aARTICLE