Recurrent Neural Networks for Modelling Gross Primary Production

Vista sencilla de ítem
dc.contributor.affiliationMontero D., Remote Sensing Centre for Earth System Research (RSC4Earth), Leipzig University, Germany, Institute of Earth System Science & Remote Sensing, Leipzig University, Germany, German Centre for Integrative Biodiversity Research (IDiv) Halle-Jena-Leipzig, Germany
dc.contributor.affiliationMahecha M.D., Remote Sensing Centre for Earth System Research (RSC4Earth), Leipzig University, Germany, Institute of Earth System Science & Remote Sensing, Leipzig University, Germany, German Centre for Integrative Biodiversity Research (IDiv) Halle-Jena-Leipzig, Germany, Department of Remote Sensing, Helmholtz Centre for Environmental Research (UFZ), Germany, Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig University, Germany
dc.contributor.affiliationMartinuzzi F., Remote Sensing Centre for Earth System Research (RSC4Earth), Leipzig University, Germany, Institute of Earth System Science & Remote Sensing, Leipzig University, Germany, Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig University, Germany
dc.contributor.affiliationAybar C., Image Processing Laboratory, Universitat de València, Spain
dc.contributor.affiliationKlosterhalfen A., Bioclimatology, University of Göttingen, Germany
dc.contributor.affiliationKnohl A., Bioclimatology, University of Göttingen, Germany
dc.contributor.affiliationKoebsch F., Bioclimatology, University of Göttingen, Germany
dc.contributor.affiliationAnaya J., Grupo de Investigaciones y Mediciones Ambientales (GEMA), Universidad de Medellín, Colombia
dc.contributor.affiliationWieneke S., Remote Sensing Centre for Earth System Research (RSC4Earth), Leipzig University, Germany, Institute of Earth System Science & Remote Sensing, Leipzig University, Germany
dc.contributor.authorMontero D.
dc.contributor.authorMahecha M.D.
dc.contributor.authorMartinuzzi F.
dc.contributor.authorAybar C.
dc.contributor.authorKlosterhalfen A.
dc.contributor.authorKnohl A.
dc.contributor.authorKoebsch F.
dc.contributor.authorAnaya J.
dc.contributor.authorWieneke S.
dc.contributor.conferencename2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024spa
dc.date.accessioned2024-12-27T20:52:15Z
dc.date.available2024-12-27T20:52:15Z
dc.date.issued2024
dc.descriptionAccurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO2 flux, especially significant for forests. Eddy Covariance (EC) measurements are widely used for ecosystem-scale GPP quantification but are globally sparse. In areas lacking local EC measurements, remote sensing (RS) data are typically utilised to estimate GPP after statistically relating them to in-situ data. Deep learning offers novel perspectives, and the potential of recurrent neural network architectures for estimating daily GPP remains underexplored. This study presents a comparative analysis of three architectures: Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs), and Long-Short Term Memory (LSTMs). Our findings reveal comparable performance across all models for full-year and growing season predictions. Notably, LSTMs outperform in predicting climate-induced GPP extremes. Furthermore, our analysis highlights the importance of incorporating radiation and RS inputs (optical, temperature, and radar) for accurate GPP predictions, particularly during climate extremes. © 2024 IEEE.
dc.identifier.doi10.1109/IGARSS53475.2024.10640715
dc.identifier.instnameinstname:Universidad de Medellínspa
dc.identifier.isbn979-835036032-5
dc.identifier.reponamereponame:Repositorio Institucional Universidad de Medellínspa
dc.identifier.repourlrepourl:https://repository.udem.edu.co/
dc.identifier.urihttp://hdl.handle.net/11407/8729
dc.language.isoeng
dc.publisherThe Institute of Electrical and Electronics Engineers, Geoscience and Remote Sensing Society (GRSS)spa
dc.publisher.facultyFacultad de Ingenieríasspa
dc.publisher.programIngeniería Ambientalspa
dc.relation.citationendpage4217
dc.relation.citationstartpage4214
dc.relation.isversionofhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85204883300&doi=10.1109%2fIGARSS53475.2024.10640715&partnerID=40&md5=e2c5ccdd2964fb04f20032d7130e7280
dc.relation.referencesFriedlingstein P., Et al., Global carbon budget 2023, Earth System Science Data, 15, 12, pp. 5301-5369, (2023)
dc.relation.referencesBonan G.B., Forests and climate change: Forcings, feedbacks, and the climate benefits of forests, Science, 320, 5882, pp. 1444-1449, (2008)
dc.relation.referencesBaldocchi D.D., How eddy covariance flux measurements have contributed to our understanding of global change biology, Global Change Biology, 26, 1, pp. 242-260, (2019)
dc.relation.referencesSchimel D., Et al., Observing terrestrial ecosystems and the carbon cycle from space, Global Change Biology, 21, 5, pp. 1762-1776, (2015)
dc.relation.referencesZeng Y., Et al., Optical vegetation indices for monitoring terrestrial ecosystems globally, Nature Reviews Earth & Environment, 3, 7, pp. 477-493, (2022)
dc.relation.referencesJung M., Et al., The fluxcom ensemble of global land-atmosphere energy fluxes, Scientific Data, 6, 1, (2019)
dc.relation.referencesMartinuzzi F., Et al., Learning extreme vegetation response to climate forcing: A comparison of recurrent neural network architectures, EGUsphere, pp. 1-32, (2023)
dc.relation.referencesBesnard S., Et al., Memory effects of climate and vegetation affecting net ecosystem co2 fluxes in global forests, PLOS ONE, 14, 2, (2019)
dc.relation.referencesWarm winter 2020 ecosystem eddy covariance flux product for 73 stations in fluxnet-archive format-release 2022-1, (2022)
dc.relation.referencesReichstein M., Et al., On the separation of net ecosystem exchange into assimilation and ecosystem respiration: Review and improved algorithm, Global Change Biology, 11, 9, pp. 1424-1439, (2005)
dc.relation.referencesAybar C., Et al., CloudSEN12, a global dataset for semantic understanding of cloud and cloud shadow in sentinel-2, Scientific Data, 9, 1, (2022)
dc.relation.referencesRoy D.P., Et al., Examination of Sentinel-2A multispectral instrument (MSI) reflectance anisotropy and the suitability of a general method to normalize MSI reflectance to nadir BRDF adjusted reflectance, Remote Sensing of Environment, 199, pp. 25-38, (2017)
dc.relation.referencesMontero D., Et al., A standardized catalogue of spectral indices to advance the use of remote sensing in earth system research, Scientific Data, 10, 1, (2023)
dc.relation.referencesReda I., Et al., Solar Position Algorithm for Solar Radiation Applications (Revised), (2008)
dc.relation.referencesVan Dijke A.J.H., Et al., Comparing forest and grassland drought responses inferred from eddy covariance and earth observation, Agricultural and Forest Meteorology, 341, (2023)
dc.rights.accessrightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceInternational Geoscience and Remote Sensing Symposium (IGARSS)
dc.sourceDig Int Geosci Remote Sens Symp (IGARSS)
dc.sourceScopus
dc.subjectClimate Extremeseng
dc.subjectGross Primary Productioneng
dc.subjectRecurrent Neural Networkseng
dc.subjectRemote Sensingeng
dc.subjectXAIeng
dc.titleRecurrent Neural Networks for Modelling Gross Primary Productioneng
dc.typeConference paper
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Archivos

Colecciones

Indexados Scopus