# Recurrent Neural Networks for Modelling Gross Primary Production

arXiv: https://arxiv.org/abs/2404.12745 · HTML: https://mlsanity.com/paper/2404.12745/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 17 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Builds on (most cited first, 1 of 1)

- [The FLUXCOM ensemble of global land-atmosphere energy fluxes](https://mlsanity.com/paper/1812.04951/) (2018)

## Built on by (most cited first, 4 of 4)

- [DeepExtremeCubes: Integrating Earth system spatio-temporal data for impact assessment of climate extremes](https://mlsanity.com/paper/2406.18179/) (2024)
- [Nonlinear spectral analysis extracts harmonics from land-atmosphere fluxes](https://mlsanity.com/paper/2407.19237/) (2024)
- [Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental Modelling](https://mlsanity.com/paper/2511.11706/) (2025)
- [Transformers vs. Recurrent Models for Estimating Forest Gross Primary Production](https://mlsanity.com/paper/2511.11880/) (2025)

## Abstract (arXiv)

Accurate quantification of Gross Primary Production (GPP) is crucial for understanding terrestrial carbon dynamics. It represents the largest atmosphere-to-land CO2 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.