1. Recurrent Neural Networks for Modelling Gross Primary Production
- Author
-
Montero, David, Mahecha, Miguel D., Martinuzzi, Francesco, Aybar, César, Klosterhalfen, Anne, Knohl, Alexander, Koebsch, Franziska, Anaya, Jesús, and Wieneke, Sebastian
- Subjects
Computer Science - Machine Learning - 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., Comment: Accepted at IGARSS24
- Published
- 2024
- Full Text
- View/download PDF