%0 Journal Article %1 martinuzzi2024learning %A Martinuzzi, Francesco %A Mahecha, Miguel D %A Camps-Valls, Gustau %A Montero, David %A Williams, Tristan %A Mora, Karin %D 2024 %I Copernicus Publications %J Nonlinear Processes in Geophysics %K imported topic_earthenvironment %N 4 %P 535-557 %T Learning extreme vegetation response to climate drivers with recurrent neural networks %V 31 %X The spectral signatures of vegetation are indicative of ecosystem states and health. Spectral indices used to monitor vegetation are characterized by long-term trends, seasonal fluctuations, and responses to weather anomalies. This study investigates the potential of neural networks in learning and predicting vegetation response, including extreme behavior from meteorological data. While machine learning methods, particularly neural networks, have significantly advanced in modeling nonlinear dynamics, it has become standard practice to approach the problem using recurrent architectures capable of capturing nonlinear effects and accommodating both long- and short-term memory. We compare four recurrent-based learning models, which differ in their training and architecture for predicting spectral indices at different forest sites in Europe: (1) recurrent neural networks (RNNs), (2) long short-term memory networks (LSTMs), (3) gated recurrent unit networks (GRUs), and (4) echo state networks (ESNs). While our results show minimal quantitative differences in their performances, ESNs exhibit slightly superior results across various metrics. Overall, we show that recurrent network architectures prove generally suitable for vegetation state prediction yet exhibit limitations under extreme conditions. This study highlights the potential of recurrent network architectures for vegetation state prediction, emphasizing the need for further research to address limitations in modeling extreme conditions within ecosystem dynamics.

@article{martinuzzi2024learning, abstract = {The spectral signatures of vegetation are indicative of ecosystem states and health. Spectral indices used to monitor vegetation are characterized by long-term trends, seasonal fluctuations, and responses to weather anomalies. This study investigates the potential of neural networks in learning and predicting vegetation response, including extreme behavior from meteorological data. While machine learning methods, particularly neural networks, have significantly advanced in modeling nonlinear dynamics, it has become standard practice to approach the problem using recurrent architectures capable of capturing nonlinear effects and accommodating both long- and short-term memory. We compare four recurrent-based learning models, which differ in their training and architecture for predicting spectral indices at different forest sites in Europe: (1) recurrent neural networks (RNNs), (2) long short-term memory networks (LSTMs), (3) gated recurrent unit networks (GRUs), and (4) echo state networks (ESNs). While our results show minimal quantitative differences in their performances, ESNs exhibit slightly superior results across various metrics. Overall, we show that recurrent network architectures prove generally suitable for vegetation state prediction yet exhibit limitations under extreme conditions. This study highlights the potential of recurrent network architectures for vegetation state prediction, emphasizing the need for further research to address limitations in modeling extreme conditions within ecosystem dynamics.}, added-at = {2024-11-29T11:53:34.000+0100}, author = {Martinuzzi, Francesco and Mahecha, Miguel D and Camps-Valls, Gustau and Montero, David and Williams, Tristan and Mora, Karin}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/24a1052f468b2afce0c67b5b4bd405a84/joum576e}, citation = {Nonlinear Processes in Geophysics 31 (4), 535-557, 2024}, interhash = {97809ca73e365e2f467bb866d051a5ba}, intrahash = {4a1052f468b2afce0c67b5b4bd405a84}, journal = {Nonlinear Processes in Geophysics}, keywords = {imported topic_earthenvironment}, number = 4, pages = {535-557}, publisher = {Copernicus Publications}, timestamp = {2024-11-29T11:53:34.000+0100}, title = {Learning extreme vegetation response to climate drivers with recurrent neural networks}, volume = 31, year = 2024 }