AUTHOR=Han Nana , Miao Wending , Li Mingzhi , Mohamad Ismail Mohd Ashraf , Hu Qiang , Duan Liyuan , Tang Jintao 

TITLE=Integrating multi-source monitoring data and deep convolutional autoencoder technology for slope failure pattern recognition

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 13 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2025.1531857

DOI=10.3389/feart.2025.1531857

ISSN=2296-6463

ABSTRACT=IntroductionOver the past few decades, China has vigorously advanced its strategy to build a powerful transportation network, constructing and maintaining numerous slope engineering projects. However, frequent major safety incidents caused by slope failures highlight the urgent need for automated identification of failure events during the operational phase of slopes.MethodsThis study integrates rainfall, surface displacement, and vertical displacement monitoring data, and proposes an automatic failure mode identification method based on deep convolutional autoencoder technology. The model is trained on monitoring data collected during the normal operational phase of slopes, extracting features from normal data to reconstruct the original data. The trained model is then utilized for structural anomaly detection by leveraging the characteristic that reconstruction errors for failure mode samples are significantly higher than for normal samples.ResultsA case study was conducted on a specific slope where, on 24 May 2024, the displacement development rate in some areas increased significantly, ultimately leading to collapse. The proposed model accurately identified the time and evolution of the landslide, demonstrating its capability to detect failure events effectively.DiscussionValidation results confirm that the model can effectively distinguish previously unseen abnormal modes, offering significant practical value for identifying similar structural anomalies. This approach provides a reliable tool for slope monitoring and anomaly detection, enhancing safety in slope engineering projects.