Recurrent Neural Networks for Modelling Gross Primary Production

• Main Authors: Montero, David, Mahecha, Miguel D, Martinuzzi, Francesco, Aybar, César, Klosterhalfen, Anne, Knohl, Alexander, Koebsch, Franziska, Anaya, Jesús, Wieneke, Sebastian
• Format: Journal Article
• Language: English
• Published: 19-04-2024
• Subjects: Computer Science - Learning
• DOI: 10.48550/arxiv.2404.12745

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.