SHAP-enhanced interpretive MGTWR-CNN-BILSTM-AM framework for predicting surface subsidence: a case study of Shanghai municipality

Abstract Urban expansion and subsurface resource exploitation have intensified ground subsidence, posing significant geological risks. Conventional prediction models often overlook multi-scale spatiotemporal effects that critically influence accuracy. This study proposes an integrated MGTWR-CNN-BiLS...

Full description

Bibliographic Details

Published in:	Scientific Reports
Main Authors:	Long Wen-Jiang, Yu Xue-Xiang, Zhu Ming-Fei, Xue Li, Zhang Guang-Hui, Wang Lin-Lin
Format:	Article
Language:	English
Published:	Nature Portfolio 2025-06-01
Subjects:	Surface settlement MGTWR-CNN-BILSTM-AM method Temporal and spatial variability Geographically weighted regression SHAP
Online Access:	https://doi.org/10.1038/s41598-025-95694-4