What does this research mean for the field?

A prediction framework combining Dung Beetle Optimizer (DBO), Variational Mode Decomposition (VMD), and Long Short-Term Memory (LSTM) with SHAP analysis provides highly accurate and interpretable predictions of slope deformation, significantly outperforming existing models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To resolve non-stationary signal complexity and black-box interpretability limitations in predicting slope deformation.

September 5, 2026Scientific ReportsOpen Access

A novel prediction method for slope deformation based on adaptive mode decomposition and interpretable deep learning

View Full Paper

Ask AI

Bookmark

Authors

HZHong ZhangTsinghua University ZWZhibo Wang BZBang Zhang

Discussion

Member takes

Overview

Computational study demonstrates high-precision slope deformation forecasting in red clay high slopes, highlighting the value of interpretable deep learning for landslide risk assessment.

Key Points

To resolve non-stationary signal complexity and black-box interpretability limitations in predicting slope deformation.
Integrated the Dung Beetle Optimizer (DBO) to simultaneously optimize Variational Mode Decomposition (VMD) decomposition parameters and Long Short-Term Memory (LSTM) network hyperparameters.
Applied SHapley Additive exPlanations (SHAP) interaction analysis to examine the physical mechanisms linking multi-scale rainfall and displacement components on a red clay high slope in Jiangxi Province.
The DBO-VMD-LSTM model achieved an RMSE of 0.155 mm and an R² of 0.993, significantly outperforming comparison models including SSA-VMD-LSTM (p < 0.001).
SHAP interaction analysis identified an alternating coupling pattern between displacement rate and rainfall across time scales, with the maximum interaction for the trend component measuring only 15% of that for the periodic component.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd4126b95aff0620eb759 https://doi.org/10.1038/s41598-026-56000-y

View Full Paper

Ask AI

Bookmark

September 5, 2026Scientific ReportsOpen Access

A novel prediction method for slope deformation based on adaptive mode decomposition and interpretable deep learning

View Full Paper

Ask AI

Bookmark

Authors

HZHong ZhangTsinghua University ZWZhibo Wang BZBang Zhang

Discussion

Member takes

Overview

Computational study demonstrates high-precision slope deformation forecasting in red clay high slopes, highlighting the value of interpretable deep learning for landslide risk assessment.

Key Points

To resolve non-stationary signal complexity and black-box interpretability limitations in predicting slope deformation.
Integrated the Dung Beetle Optimizer (DBO) to simultaneously optimize Variational Mode Decomposition (VMD) decomposition parameters and Long Short-Term Memory (LSTM) network hyperparameters.
Applied SHapley Additive exPlanations (SHAP) interaction analysis to examine the physical mechanisms linking multi-scale rainfall and displacement components on a red clay high slope in Jiangxi Province.
The DBO-VMD-LSTM model achieved an RMSE of 0.155 mm and an R² of 0.993, significantly outperforming comparison models including SSA-VMD-LSTM (p < 0.001).
SHAP interaction analysis identified an alternating coupling pattern between displacement rate and rainfall across time scales, with the maximum interaction for the trend component measuring only 15% of that for the periodic component.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a9bd4126b95aff0620eb759 https://doi.org/10.1038/s41598-026-56000-y

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark