A novel hybrid modelling framework for GPP estimation: Integrating a multispectral surface reflectance based Vcmax25 simulator into the process-based model

Xiaolong Hu; Liangsheng Shi; Lin Lin; Shenji Li; Xianzhi Deng; Li Li; Jiang Bian; Xie Lian

doi:10.1016/j.scitotenv.2024.171182

A novel hybrid modelling framework for GPP estimation: Integrating a multispectral surface reflectance based V_cmax²⁵ simulator into the process-based model

Sci Total Environ. 2024 Apr 15:921:171182. doi: 10.1016/j.scitotenv.2024.171182. Epub 2024 Feb 23.

Authors

Xiaolong Hu¹, Liangsheng Shi², Lin Lin¹, Shenji Li³, Xianzhi Deng¹, Li Li⁴, Jiang Bian¹, Xie Lian¹

Affiliations

¹ State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, Hubei 430072, China.
² State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan, Hubei 430072, China. Electronic address: liangshs@whu.edu.cn.
³ Urban Operation Management Center of Hengsha Township, Shanghai 201914, China.
⁴ Shanghai Tramy Green Food (Group) Co., Ltd, Shanghai 201201, China.

PMID: 38402983
DOI: 10.1016/j.scitotenv.2024.171182

Abstract

Terrestrial gross primary productivity (GPP) is the key element in the carbon cycle process. Accurate GPP estimation hinges on the maximum carboxylation rate (V_cmax,0²⁵). The high uncertainty in deriving ecosystem-level V_cmax,0²⁵ has long hampered efforts toward the performance of the GPP model. Recently studies suggest the strong relationship between spectral reflectance and V_cmax,0²⁵. We proposed the multispectral surface reflectance-driven V_cmax,0²⁵ simulator using the fully connected deep neural network and built the hybrid modelling framework for GPP estimation by integrating the data-driven V_cmax,0²⁵ simulator in the process-based model. The performance of hybrid GPP model was evaluated at 95 flux sites. The result shows that the multispectral surface reflectance-driven V_cmax,0²⁵ simulator acquires the satisfactory estimation, with correlation coefficient (R), root mean square error (RMSE) and median absolute percentage error (MdAPE) ranging from 0.34 to 0.80, 14 to 43 μmol m^-2 s^-1 and 21 % to 66 % across different land cover types, respectively. The hybrid framework generates good GPP estimates with R, RMSE and MdAPE varying from 0.76 to 0.89, 1.79 to 6.16 μmol m^-2 s^-1 and 27 % to 90 %, respectively. Compared with EVI-driven method, the multispectral surface reflectance significantly improves the V_cmax,0²⁵ and GPP estimates, with MdAPE declining by 0.6 %-18 % and 1 % to 21 %, respectively. The Shapley value analysis reveals that red (620-670 nm), near-infrared (841-876 nm) and shortwave infrared (1628-1652 nm and 2105-2155 nm) are the key bands for V_cmax,0²⁵ estimation. This study highlights the potential of multispectral surface reflectance for quantifying ecosystem-level V_cmax,0²⁵. The new hybrid framework fully extracts the information of all available spectral bands using deep learning to reduce parameter uncertainty while maintains the description of photosynthetic process to ensure its physical reasonability. It can serve as a powerful tool for accurate global GPP estimation.

Keywords: GPP; Hybrid modelling; Maximum carboxylation rate; Multispectral surface reflectance.