What question did this study set out to answer?

This research aims to enhance the estimation of CO2 fluxes by integrating spatial and temporal data using deep learning techniques.

May 9, 2026Ecological Processes2 citationsOpen Access

Estimating CO2 fluxes through integrating spatial and temporal input layers via deep learning algorithms

HZHuimin ZouNational Center of Ocean Standards and Metrology JCJiquan ChenMichigan State University XLXiaojian LiuTianjin Research Institute of Water Transport Engineering

Puntos clave

This research aims to enhance the estimation of CO2 fluxes by integrating spatial and temporal data using deep learning techniques.
Developed a spatiotemporal model combining graph convolutional and gated recurrent unit networks.
Utilized multi-year flux tower observations and remote sensing vegetation indices.
Evaluated model performance across three distinct land cover types.
The model achieved an R2 of 0.9569, indicating high accuracy in CO2 flux estimation.
Lowest RMSE recorded at 1.8128 μmol m−2 s−1 and MAE at 1.1939 μmol m−2 s−1.
Performance improvements noted particularly in ecosystems with high vegetation heterogeneity.

Resumen

Accurate estimation of net ecosystem exchange of CO2 fluxes (Fc) is essential for understanding carbon cycle processes and assessing ecosystem carbon budgets. However, conventional modeling approaches often emphasize temporal dynamics while overlooking the pronounced spatial heterogeneity within the footprint of eddy covariance (EC) towers, potentially limiting predictive accuracy and interpretability of Fc estimates. To address this challenge, we developed a spatiotemporal model that integrates high-resolution footprint-weighted spatial information with sequential environmental drivers. The integrated model combines a deeper graph convolutional network to characterize fine-scale spatial variability within EC footprints and a gated recurrent unit network to capture temporal dependencies in biophysical conditions. Using multi-year flux tower observations, remote sensing vegetation indices and footprint modeling, we evaluate the proposed method across three land cover types. This spatiotemporal model consistently outperforms temporal-only and spatial-only baselines, achieving the highest overall accuracy (R2 = 0.9569) and the lowest RMSE (1.8128 μmol m−2 s−1) and MAE (1.1939 μmol m−2 s−1). Performance gains are particularly evident in ecosystems with strong vegetation heterogeneity, where spatial structure substantially modulates Fc variability. This study demonstrates the importance of joint modeling spatial heterogeneity and temporal dynamics for improving Fc estimation and provides a robust method for advancing footprint-based Fc estimates across diverse ecosystems, supporting refined assessments of terrestrial carbon fluxes, and enhancing scientific foundations for carbon studies.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo