Publication Details |
| Category | Text Publication |
| Reference Category | Book chapters |
| DOI | 10.1109/IGARSS53475.2024.10640715 |
| Title (Primary) | Recurrent neural networks for modelling gross primary production |
| Title (Secondary) | 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 07-12 July 2024 |
| Author | Montero, D.; Mahecha, M.D.; Martinuzzi, F.; Aybar, C.; Klosterhalfen, A.; Knohl, A.; Koebsch, F.; Anaya, J.; Wieneke, S. |
| Source Titel | International Geoscience and Remote Sensing Symposium |
| Year | 2024 |
| Department | RS |
| Volume | IGARSS 2024 |
| Page From | 4214 |
| Page To | 4217 |
| Language | englisch |
| Topic | T5 Future Landscapes |
| 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 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. |
| Persistent UFZ Identifier | https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=30294 |
| Montero, D., Mahecha, M.D., Martinuzzi, F., Aybar, C., Klosterhalfen, A., Knohl, A., Koebsch, F., Anaya, J., Wieneke, S. (2024): Recurrent neural networks for modelling gross primary production 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 07-12 July 2024 International Geoscience and Remote Sensing Symposium IGARSS 2024 Institute of Electrical and Electronics Engineers (IEEE), New York, NY, p. 4214 - 4217 10.1109/IGARSS53475.2024.10640715 |
|