Recurrent Neural Networks for Modelling Gross Primary Production
This work addresses the need for better GPP estimation in areas lacking local measurements, using deep learning to improve predictions, though it is incremental as it compares existing architectures.
This study tackled the problem of accurately estimating Gross Primary Production (GPP) for terrestrial carbon dynamics by comparing recurrent neural network architectures, finding that LSTMs outperformed others in predicting climate-induced GPP extremes while all models showed comparable performance for full-year and growing season predictions.
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.