Estimating Forest Gross Primary Production Using Machine Learning, Light Use Efficiency Model, and Global Eddy Covariance Data
Open Access
Abstract
Forests play a vital role in atmospheric CO2 sequestration among terrestrial ecosystems, mitigating the greenhouse effect induced by human activity in a changing climate. The LUE (light use efficiency) model is a popular algorithm for calculating terrestrial GPP (gross primary production) based on physiological mechanisms and is easy to implement. Different versions have been applied for many years to simulate the GPP of different ecosystem types at regional or global scales. For estimating forest GPP using different approaches, we implemented five LUE models (EC-LUE, VPM, GOL-PEM, CASA, and C-Fix) in forests of type DBF, EBF, ENF, and MF, using the FLUXNET2015 dataset, remote sensing observations, and Köppen–Geiger climate zones. We then fused these models to additionally improve the ability of the GPP estimation using an RF (random forest) and an SVM (support vector machine). Our results indicated that under a unified parameterization scheme, EC-LUE and VPM yielded the best performance in simulating GPP variations, followed by GLO-PEM, CASA, and C-fix, while MODIS also demonstrated reliable GPP estimation ability. The results of the model fusion across different forest types and flux net sites indicated that the RF could capture more GPP variation magnitudes with higher R2 and lower RMSE than the SVM. Both RF and SVM were validated using cross-validation for all forest types and flux net sites, showing that the accuracy of the GPP simulation could be improved by the RF and SVM by 28% and 27%.Keywords
Funding Information
- National Bureau of Statistics of China (2023LY063, 24XYJS020, STKY202311)
- China University of Labor Relations (2023LY063, 24XYJS020, STKY202311)
- Beijing Technology and Business University (2023LY063, 24XYJS020, STKY202311)
This publication has 75 references indexed in Scilit:
- A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studiesScientometrics, 2021
- A global study of GPP focusing on light‐use efficiency in a random forest regression modelEcosphere, 2017
- Seasonal controls of canopy chlorophyll content on forest carbon uptake: Implications for GPP modelingJournal of Geophysical Research: Biogeosciences, 2015
- A data-driven analysis of energy balance closure across FLUXNET research sites: The role of landscape scale heterogeneityAgricultural and Forest Meteorology, 2013
- Deriving a light use efficiency model from eddy covariance flux data for predicting daily gross primary production across biomesAgricultural and Forest Meteorology, 2007
- Multiobjective analysis of chaotic dynamic systems with sparse learning machinesAdvances in Water Resources, 2006
- Remotely Sensed Interannual Variations and Trends in Terrestrial Net Primary Productivity 1981?2000Ecosystems, 2004
- Global Terrestrial Gross and Net Primary Productivity from the Earth Observing System2000
- Estimating net ecosystem exchange of carbon using the normalized difference vegetation index and an ecosystem modelRemote Sensing of Environment, 1996
- Support-vector networksMachine Learning, 1995