What question did this study set out to answer?

This research aims to refine the simulation of maximum carboxylation rate (Vcmax) and its variability using machine learning techniques.

August 11, 2026AgronomyOpen Access

Exploring the Response of Maximum Carboxylation Rate to Drivers Through an Interpretable Machine Learning Framework

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial explores the response of maximum carboxylation rate in maize, indicating improved carbon cycle modeling.

This research aims to refine the simulation of maximum carboxylation rate (Vcmax) and its variability using machine learning techniques.
Employed four machine learning models (KNN, SVM, Random Forest, XGBoost) to simulate Vcmax normalized to 25 °C (Vm25) using eddy covariance data from five maize sites.
Coupled the Breathing Earth System Simulator (BESS) model with light response curves for Vcmax inversion.
Utilized the SHAP method for feature importance assessment of environmental factors influencing Vm25.
Random Forest model achieved the best performance for Vm25 simulation with R2 = 0.83 and RMSE = 7.57 μmol m−2s−1 during testing.
Incorporating RF-simulated Vm25 into the BESS model enhanced GPP estimates with R2 increasing from 0.53–0.81 to 0.77–0.84.
Leaf age emerged as the most influential factor on Vm25, with a SHAP value of 8.37 μmol m−2s−1, surpassing other factors like temperature and solar radiation.

Zhang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark