An ecologically-constrained deep learning model for tropical leaf phenology monitoring using PlanetScope satellites

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorShenzhen Campus of Sun Yat-sen University-
Autor(es): dc.contributorThe University of Hong Kong-
Autor(es): dc.contributorJames Cook University-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorBrookhaven National Laboratory-
Autor(es): dc.contributorInstituto Tecnológico Vale-
Autor(es): dc.contributorPrinceton University-
Autor(es): dc.contributorLanzhou University-
Autor(es): dc.contributorInternational Research Center of Big Data for Sustainable Development Goals-
Autor(es): dc.contributorEast China Normal University-
Autor(es): dc.contributorNational Institute for Amazon Research (INPA)-
Autor(es): dc.contributorUniversity of Technology Sydney-
Autor(es): dc.creatorWang, Jing-
Autor(es): dc.creatorSong, Guangqin-
Autor(es): dc.creatorLiddell, Michael-
Autor(es): dc.creatorMorellato, Patricia-
Autor(es): dc.creatorLee, Calvin K.F.-
Autor(es): dc.creatorYang, Dedi-
Autor(es): dc.creatorAlberton, Bruna-
Autor(es): dc.creatorDetto, Matteo-
Autor(es): dc.creatorMa, Xuanlong-
Autor(es): dc.creatorZhao, Yingyi-
Autor(es): dc.creatorYeung, Henry C.H.-
Autor(es): dc.creatorZhang, Hongsheng-
Autor(es): dc.creatorNg, Michael-
Autor(es): dc.creatorNelson, Bruce W.-
Autor(es): dc.creatorHuete, Alfredo-
Autor(es): dc.creatorWu, Jin-
Data de aceite: dc.date.accessioned2025-08-21T20:43:34Z-
Data de disponibilização: dc.date.available2025-08-21T20:43:34Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-03-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.rse.2022.113429-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/246610-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/246610-
Descrição: dc.descriptionIn tropical forests, leaf phenology signals leaf-on/off status and exhibits considerable variability across scales from a single tree-crown to the entire forest ecosystem. Such phenology signals importantly regulate large-scale biogeochemical cycles and regional climate. PlanetScope CubeSats data with a 3-m resolution and near-daily global coverage provide an unprecedented opportunity to monitor both fine- and ecosystem-scale phenology variability along large environmental gradients. However, a scalable method that accurately characterizes leaf phenology from PlanetScope with biophysically meaningful metrics remains lacking. We developed an index-guided, ecologically constrained autoencoder (IG-ECAE) method to automatically derive a deciduousness metric (percentage of upper tree canopies with leaf-off status within an image pixel) from PlanetScope. The IG-ECAE first estimated the reflectance spectra of leafy/leafless canopies based on their spectral indices characteristics, then used the derived reflectance spectra to guide an autoencoder deep learning method with additional ecological constraints to refine the reflectance spectra, and finally used linear spectral unmixing to estimate the relative abundance of leafless canopies (or deciduousness) per PlanetScope image pixel. We tested the IG-ECAE method at 16 tropical forest sites spanning multiple continents and a large precipitation gradient (1470–2819 mm year−1). Among these sites, we evaluated the PlanetScope-derived deciduousness against corresponding measures derived from WorldView-2 (n = 9 sites) and local phenocams (n = 9 sites). Our results show that PlanetScope-derived deciduousness agrees: 1) with that derived from WorldView-2 at the patch level (90 m × 90 m) with r2 = 0.89 across all sites; and 2) with that derived from phenocams to quantify ecosystem-scale seasonality with r2 ranging from 0.62 to 0.96. These results demonstrate the effectiveness and scalability of IG-ECAE in characterizing the wide variability in deciduousness across scales from pixels to forest ecosystems, and from a single date to the full annual cycle, indicating the potential for using high-resolution satellites to track the large-scale phenological patterns and response of tropical forests to climate change.-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionUniversity of Hong Kong-
Descrição: dc.descriptionNational Natural Science Foundation of China-
Descrição: dc.descriptionU.S. Department of Energy-
Descrição: dc.descriptionSchool of Ecology Shenzhen Campus of Sun Yat-sen University, Guangdong-
Descrição: dc.descriptionResearch Area of Ecology and Biodiversity School for Biological Sciences The University of Hong Kong-
Descrição: dc.descriptionCentre for Tropical Environmental and Sustainability Science College of Science and Engineering James Cook University-
Descrição: dc.descriptionDepartment of Biodiversity Bioscience Institute São Paulo State University UNESP, São Paulo-
Descrição: dc.descriptionDepartment of Environmental and Climate Sciences Brookhaven National Laboratory-
Descrição: dc.descriptionInstituto Tecnológico Vale, Pará-
Descrição: dc.descriptionDepartment of Ecology and Evolutionary Biology Princeton University-
Descrição: dc.descriptionCollege of Earth and Environmental Sciences Lanzhou University-
Descrição: dc.descriptionInternational Research Center of Big Data for Sustainable Development Goals-
Descrição: dc.descriptionKey Laboratory of Geographic Information Science (Ministry of Education) East China Normal University-
Descrição: dc.descriptionDepartment of Geography The University of Hong Kong-
Descrição: dc.descriptionInstitute for Climate and Carbon Neutrality The University of Hong Kong-
Descrição: dc.descriptionInstitute of Data Science and Department of Mathematics The University of Hong Kong-
Descrição: dc.descriptionNational Institute for Amazon Research (INPA)-
Descrição: dc.descriptionSchool of Life Sciences University of Technology Sydney-
Descrição: dc.descriptionDepartment of Biodiversity Bioscience Institute São Paulo State University UNESP, São Paulo-
Idioma: dc.languageen-
Relação: dc.relationRemote Sensing of Environment-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectCarbon cycles-
Palavras-chave: dc.subjectDeciduousness-
Palavras-chave: dc.subjectEnvironmental gradient-
Palavras-chave: dc.subjectMachine learning-
Palavras-chave: dc.subjectMulti-scale remote sensing-
Palavras-chave: dc.subjectTropical forests-
Título: dc.titleAn ecologically-constrained deep learning model for tropical leaf phenology monitoring using PlanetScope satellites-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.