Table 1.
Data sources and preprocessing procedures.
Fig 1.
The architecture of the environmental adaptability of the Cubist-BiGRU-SA model.
Fig 2.
The data feature extraction module based on the Cubist regression tree.
Fig 3.
Schematic diagram of BiGRU applied to the temporal learning layer.
Fig 4.
The process pseudocode for the environmental adaptability model based on Cubist-BiGRU-SA.
Table 2.
Data sources and preprocessing procedures.
Table 3.
Key hyperparameter settings of the model.
Fig 5.
The prediction accuracy results of the vegetation restoration rate under different algorithms.
Fig 6.
The predicted RMSE results for the vegetation restoration rate under various algorithms.
Fig 7.
The forecasted MAPE results for the vegetation restoration rate with each algorithm.
Fig 8.
The predicted R² results for the vegetation restoration rate under diverse algorithms.
Table 4.
Performance comparison and statistical significance test of diverse models on the test set.
Fig 9.
The global importance ranking of each input feature based on the mean absolute SHAP value.
Fig 10.
Relationship between irrigation volume and vegetation survival rate.
Table 5.
Prediction accuracy of the model in different altitude regions.