Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Improving net ecosystem CO2 flux prediction using memory-based interpretable machine learning

Conference ·

Terrestrial ecosystems play a central role in the global carbon cycle and affect climate change. However, our predictive understanding of these systems is still limited due to their complexity and uncertainty about how key drivers and their legacy effects influence carbon fluxes. Here, we propose an interpretable Long Short-Term Memory (iLSTM) network for predicting net ecosystem CO 2 exchange (NEE) and interpreting the influence on the NEE prediction from environmental drivers and their memory effects. We consider five drivers and apply the method to three forest sites in the United States. Besides performing the prediction in each site, we also conduct transfer learning by using the iLSTM model trained in one site to predict at other sites. Results show that the iLSTM model produces good NEE predictions for all three sites and, more importantly, it provides reasonable interpretations on the input driver's importance as well as their temporal importance on the NEE prediction. Additionally, the iLSTM model demonstrates good across-site transferability in terms of both prediction accuracy and interpretability. The transferability can improve the NEE prediction in unobserved forest sites, and the interpretability advances our predictive understanding and guides process-based model development.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-00OR22725
OSTI ID:
1928933
Country of Publication:
United States
Language:
English

References (18)

Interpretability of Recurrent Neural Networks in Remote Sensing conference September 2020
Long Short-Term Memory journal November 1997
The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data journal July 2020
Memory effects of climate and vegetation affecting net ecosystem CO2 fluxes in global forests journal February 2019
Stock Price Prediction via Discovering Multi-Frequency Trading Patterns conference August 2017
Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US journal September 2020
From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling journal October 2021
Finding Structure in Time journal March 1990
Modeling and interpreting hydrological responses of sustainable urban drainage systems with explainable machine learning methods journal January 2021
Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest journal March 2020
Artificial neural network application for multi-ecosystem carbon flux simulation journal December 2005
An Efficient Bayesian Method for Advancing the Application of Deep Learning in Earth Science conference November 2019
Sustained carbon uptake and storage following moderate disturbance in a Great Lakes forest journal July 2013
Drought during canopy development has lasting effect on annual carbon balance in a deciduous temperate forest journal August 2008
Physics‐Constrained Machine Learning of Evapotranspiration journal December 2019
Identifying Dynamic Memory Effects on Vegetation State Using Recurrent Neural Networks journal October 2019
Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt journal January 2021
The role of isohydric and anisohydric species in determining ecosystem-scale response to severe drought journal July 2015

Similar Records

An interpretable machine learning model for advancing terrestrial ecosystem predictions
Conference · 2022 · OSTI ID:1871086

Direct and indirect effects of climatic variations on the interannual variability in net ecosystem exchange across terrestrial ecosystems
Journal Article · 2016 · Tellus. Series B, Chemical and Physical Meteorology (Online) · OSTI ID:1474905

Forests dominate the interannual variability of the North American carbon sink
Journal Article · 2018 · Environmental Research Letters · OSTI ID:1463982

Related Subjects