Accurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO 2 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 …
%0 Journal Article
%1 montero2024recurrent
%A Montero, David
%A Mahecha, Miguel D
%A Martinuzzi, Francesco
%A Aybar, César
%A Klosterhalfen, Anne
%A Knohl, Alexander
%A Koebsch, Franziska
%A Anaya, Jesús
%A Wieneke, Sebastian
%D 2024
%I IEEE
%K imported topic_earthenvironment
%P 4214-4217
%T Recurrent Neural Networks for Modelling Gross Primary Production
%X Accurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO 2 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 …
@article{montero2024recurrent,
abstract = {Accurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO 2 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 …},
added-at = {2024-11-29T11:53:34.000+0100},
author = {Montero, David and Mahecha, Miguel D and Martinuzzi, Francesco and Aybar, César and Klosterhalfen, Anne and Knohl, Alexander and Koebsch, Franziska and Anaya, Jesús and Wieneke, Sebastian},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/220f8df5a2e6b901ceb347a7a3fde7809/joum576e},
citation = {IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium …, 2024},
conference = {IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium},
interhash = {3b1feb4c23e61bc323f142eb21ea03fc},
intrahash = {20f8df5a2e6b901ceb347a7a3fde7809},
keywords = {imported topic_earthenvironment},
pages = {4214-4217},
publisher = {IEEE},
timestamp = {2024-11-29T11:53:34.000+0100},
title = {Recurrent Neural Networks for Modelling Gross Primary Production},
year = 2024
}
