Reducing false alarms in crackmeter-based early warning of small-scale slope deformation via deep learning-driven asynchronous displacement–rainfall data fusion
- 1Fuzhou University (Fuzhou, China)
Abstract
Real-time crackmeter-based deformation monitoring systems for small-scale rainfall-affected slopes suffer from high false alarm rates. Across multi-slope monitoring settings, threshold-based alerts are vulnerable to noise, while conventional denoising and prediction-based validation methods remain limited in automated warning discrimination and cross-site generalization. To address this bottleneck, a labeled dataset and a data-driven binary classification framework were developed to distinguish true early warnings from false alarms among threshold-triggered sensor alerts. A multi-source dataset of crack-displacement and rainfall observations was constructed from monitored slopes in Fujian Province, China, with genuine and false alerts labelled based on field investigations and geological expert assessment. A patch-based dual-branch temporally-aware Transformer model was developed to fuse asynchronous multi-rate data, preserve the temporal direction from antecedent rainfall to subsequent displacement, and satisfy stringent real-time decision constraints. By simultaneously capturing long-term rainfall-displacement interactions and high-resolution displacement dynamics, the model outperforms competitive baselines, achieving a precision of 90.32 %, a recall of 89.38 %, and an F ₂ -score of 89.54 % in identifying true early warnings. Interpretability analysis reveals that the model's decisions are primarily driven by localized displacement trends and the relationship between rainfall and displacement, aligning with expert judgment. Analyses of misclassified cases informed additional safeguards to further reduce missed warnings. The proposed framework helps reduce false alarms and supports reliable automated slope hazard monitoring. However, the present validation is limited to the Fujian rainfall-triggered monitoring context, and application to other geological or climatic settings requires further external validation and local adaptation.
Versions
Related
- Asynchronous convergence of annual satellite-derived forest productivity and within-year production allocation after fire: Counterfactual evidence from 7197 forest fires in China
- Eastward displacement of the Pacific–Japan pattern weakens its influence on summertime tropical cyclones affecting China
- Principal Surface Fault Rupture Hazard: Moving Beyond Aggregate Displacement Metrics
- Long displacement of thrusts and tectonic patterns in the central Tibetan Plateau
- Time-Resolved Surface-Fault Displacement During the 2026 Kumamoto Earthquake From Near-Fault Video
BibTeX
@article{ouyang2026reducing,
title = {{Reducing false alarms in crackmeter-based early warning of small-scale slope deformation via deep learning-driven asynchronous displacement–rainfall data fusion}},
author = {Shubing Ouyang and Daichao Li and Minjiang Liu and Fengjian Ge and Xia Zheng and Yuan Li and Sheng Wu},
journal = {Natural Hazards and Earth System Sciences},
year = {2026},
month = nov,
doi = {10.5194/nhess-26-5441-2026},
url = {https://nhess.copernicus.org/articles/26/5441/2026/},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Reducing false alarms in crackmeter-based early warning of small-scale slope deformation via deep learning-driven asynchronous displacement–rainfall data fusion
AU - Shubing Ouyang
AU - Daichao Li
AU - Minjiang Liu
AU - Fengjian Ge
AU - Xia Zheng
AU - Yuan Li
AU - Sheng Wu
PY - 2026
DA - 2026/11/02
JO - Natural Hazards and Earth System Sciences
DO - 10.5194/nhess-26-5441-2026
UR - https://nhess.copernicus.org/articles/26/5441/2026/
AB - Real-time crackmeter-based deformation monitoring systems for small-scale rainfall-affected slopes suffer from high false alarm rates. Across multi-slope monitoring settings, threshold-based alerts are vulnerable to noise, while conventional denoising and prediction-based validation methods remain limited in automated warning discrimination and cross-site generalization. To address this bottleneck, a labeled dataset and a data-driven binary classification framework were developed to distinguish true early warnings from false alarms among threshold-triggered sensor alerts. A multi-source dataset of crack-displacement and rainfall observations was constructed from monitored slopes in Fujian Province, China, with genuine and false alerts labelled based on field investigations and geological expert assessment. A patch-based dual-branch temporally-aware Transformer model was developed to fuse asynchronous multi-rate data, preserve the temporal direction from antecedent rainfall to subsequent displacement, and satisfy stringent real-time decision constraints. By simultaneously capturing long-term rainfall-displacement interactions and high-resolution displacement dynamics, the model outperforms competitive baselines, achieving a precision of 90.32 %, a recall of 89.38 %, and an F ₂ -score of 89.54 % in identifying true early warnings. Interpretability analysis reveals that the model's decisions are primarily driven by localized displacement trends and the relationship between rainfall and displacement, aligning with expert judgment. Analyses of misclassified cases informed additional safeguards to further reduce missed warnings. The proposed framework helps reduce false alarms and supports reliable automated slope hazard monitoring. However, the present validation is limited to the Fujian rainfall-triggered monitoring context, and application to other geological or climatic settings requires further external validation and local adaptation.
SN - 1684-9981
SN - 1561-8633
ER -