Jeffrey Uyekawa

Jan 9, 2025 | mdpi.com | John Leland |Yujie Liu |Jeffrey Uyekawa |Darby Bergl

5. Results 5.1. Results of 10-Fold Cross-ValidationThe results for fitting each model and testing on each fold of the 10-fold cross-validation experiments are shown in Table 2 (RMSE). The XGBoost model and deep neural network were the only two models with an RMSE less than 2 μmolm−2s−1. The strength of these models suggests that there are non-linearities in the the relationships between the environmental drivers and FCO2.