fig3

Figure 3. Data sampling and model construction for the Wen-HV dataset. (A) Exploration of Wen-HV data subsets and algorithm combinations, along with the performance of the original baseline model. The white dots denote the performance of each data subset-algorithm pairing, whereas the red dot highlights the optimal combination achieved in this iteration. The black, blue, and red lines represent the article’s baseline model’s 10-fold accuracy, the data elimination process, and the data addition process, respectively; (B) Error performance of six algorithms on the validation and test sets; (C) Comparison of true and predicted values for the best generalization model, ETR, on the training and test sets; (D) Comparison of true and predicted values for the ETR model on the test set. ETR: Extra trees regression.