Henan Energy & Chemical Industry Group (China)

This study addresses the engineering need to predict multi-position underground responses during multi-hole polymer grouting in shallow voided soil, where coupled effects of grouting volume and void depth may lead to insufficient filling or excessive top-soil heave risk. To improve prediction accuracy—especially for the top soil response—an intelligent hybrid model integrating a Convolutional Neural Network, a Bidirectional Gated Recurrent Unit, and an Attention mechanism (CNN-BiGRU-Attention) is developed. The framework extracts coupled parameter patterns via CNN, learns pseudo-sequential dependencies constructed from the static input features via BiGRU (rather than true temporal evolution), and applies an attention mechanism to dynamically re-weight the learned representations for prediction. Based on indoor test data, grouting volume and void depth are used as inputs, and soil responses at the two-hole end, one-hole end, and top are set as outputs. Model performance is evaluated using the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), and is compared with single CNN, single BiGRU and SVR models. In addition, SHAP (SHapley Additive exPlanations) is employed to analyze feature contributions. Results indicate that the CNN-BiGRU-Attention model significantly outperforms the other models: the average test-set R2 reaches 0.92982, while RMSE and MAE decrease to 0.18124 kPa and 0.14386 kPa, respectively, demonstrating improved accuracy and stability. SHAP analysis shows that grouting volume dominates the holeend responses (contribution > 65%), whereas void depth has a stronger influence on the top response (contribution 63.3%), consistent with soil mechanics theory. Overall, the proposed model provides a practical tool for grouting parameter optimization and risk control.

To construct an ecological security pattern for Henan Province to support regional ecological protection and sustainable development， a comprehensive analysis of the landscape elements in Henan Province was conducted using morphological spatial pattern analysis （MSPA）， circuit theory， and space syntax. By identifying key elements such as ecological sources， corridors， pinch points， and obstacles and evaluating the morphological structure characteristics of the ecological network， critical spaces requiring priority restoration were determined. The results indicated that： ① The total area of landscape types in Henan Province was 32 066 km2， accounting for 19.20% of the study area， with core areas covering 23 095 km2， or 13.83%. When the area threshold was ≥3 km2， 380 ecological sources were identified， occupying 12.96% of the total study area， mainly concentrated in the western， central， and southern regions. ② Based on circuit theory， 1 139 ecological corridors were extracted， with a total length of 18 206.68 km， including 504 important， 403 secondary important， and 232 general corridors. Additionally， 316 ecological pinch points （located at the junctions of corridors and sources） and 290 ecological obstacles （distributed along corridors） were identified. ③ It is recommended to prioritize the restoration of 109 ecological obstacles in the northern and eastern regions， with a total restoration area of 1 387.19 km2. ④ Ultimately， an ecological security pattern of "one belt， two verticals， three screens， four corridors， and multiple nodes" was constructed. This pattern and its key elements fully reflect the actual characteristics of Henan Province's ecosystem， and the proposed restoration strategies provide scientific basis and practical guidance for regional ecological protection and sustainable development.