loading page

Exploring the Potential of Long Short-Term Memory Networks for Predicting Net CO2 Exchange Across Various Ecosystems With Multi-Source Data
  • +5
  • Chengcheng Huang,
  • Wei He,
  • Jinxiu Liu,
  • Ngoc Tu Nguyen,
  • Hua Yang,
  • Yiming Lv,
  • Hui Chen,
  • Mengyao Zhao
Chengcheng Huang
School of Information Engineering, China University of Geosciences
Author Profile
Wei He
International Institute for Earth System Science, Nanjing University

Corresponding Author:[email protected]

Author Profile
Jinxiu Liu
China University of Geosciences
Author Profile
Ngoc Tu Nguyen
Hohai University
Author Profile
Hua Yang
Beijing Normal University
Author Profile
Yiming Lv
China University of Geosciences, Beijing
Author Profile
Hui Chen
School of Information Engineering, China University of Geosciences
Author Profile
Mengyao Zhao
School of Geography and Tourism, Anhui Normal University
Author Profile


Upscaling flux tower measurements based on machine learning (ML) algorithms is an essential approach for large-scale net ecosystem CO2 exchange (NEE) estimation, but existing ML upscaling methods face some challenges, particularly in capturing NEE interannual variations (IAVs) that may relate to lagged effects. With the capacity of characterizing temporal memory effects, the Long Short-Term Memory (LSTM) networks are expected to help solve this problem. Here we explored the potential of LSTM for predicting NEE across various ecosystems using flux tower data over 82 sites in North America. The LSTM model with differentiated plant function types (PFTs) demonstrates the capability to explain 79.19% (R2 = 0.79) of the monthly variations in NEE within the testing set, with RMSE and MAE values of 0.89 and 0.57 g C m-2 d-1 respectively (r = 0.89, p < 0.001). Moreover, the LSTM model performed robustly in predicting cross-site variability, with 67.19% of the sites that can be predicted by both LSTM models with and without distinguished PFTs showing improved predictive ability. Most importantly, the IAV of predicted NEE highly correlated with that in flux observations (r = 0.81, p < 0.001), clearly outperforming that by the random forest model (r = -0.21, p = 0.011). Among all nine PFTs, solar-induced chlorophyll fluorescence, downward shortwave radiation, and leaf area index are the most important variables for explaining NEE variations, collectively accounting for approximately 54.01% in total. This study highlights the great potential of LSTM for improving carbon flux upscaling with multi-source remote sensing data.
14 Nov 2023Submitted to ESS Open Archive
14 Nov 2023Published in ESS Open Archive