Mastering the mechanical properties of frozen soil under complex stress states in cold regions and establishing accurate constitutive models to predict the nonlinear stress-strain relationship of the soil under multi-factor coupling are key to ensuring the stability and safety of engineering projects. In this study, true triaxial tests were conducted on roadbed peat soil in seasonally frozen regions under different temperatures, confining pressures, and b-values. Based on analysis of the deviatoric stress-major principal strain curve, the variation patterns of the intermediate principal stress, volumetric strain and minor principal strain deformation characteristics, and anisotropy of deformation, as well as verification of the failure point strength criterion, an intelligent constitutive model that describes the soil's stress-strain behavior was established using the Transformer network, integrated with prior information, and the robustness and generalization ability of the model were evaluated. The results indicate that the deviatoric stress is positively correlated with the confining pressure and the b-value, and it is negatively correlated with the freezing temperature. The variation in the intermediate principal stress exhibits a significant nonlinear growth characteristic. The soil exhibits expansion deformation in the direction of the minor principal stress, and the volumetric strain exhibits shear shrinkage. The anisotropy of the specimen induced by stress is negatively correlated with temperature and positively correlated with the bvalue. Three strength criteria were used to validate the failure point of the sample, and it was found that the spatially mobilized plane strength criterion is the most suitable for describing the failure behavior of frozen peat soil. A path-dependent physics-informed Transformer model that considers the physical constraints and stress paths was established. This model can effectively predict the stress-strain characteristics of soil under different working conditions. The prediction correlation of the model under the Markov chain Monte Carlo strategy was used as an evaluation metric for the original model's robustness, and the analysis results demonstrate that the improved model has good robustness. The validation dataset was input to the trained model, and it was found that the model still exhibits a good prediction accuracy, demonstrating its strong generalization ability. The research results provide a deeper understanding of the mechanical properties of frozen peat soil under true triaxial stress states, and the established intelligent constitutive model provides theoretical support for preventing engineering disasters and for early disaster warning.
Solar panels are essential for converting sunlight into electricity. Still, environmental factors can significantly compromise their efficiency and performance, particularly the accumulation of soiling on their surfaces or damage. This study proposes a hybrid model comprising an ensemble of deep-learning models to distinguish between soiled and damaged solar panels and their corresponding conditions. Our approach utilizes pretrained deep learning models, fine-tuned for detecting soiling or damage on photovoltaic (PV) panels, to extract relevant features and build efficient classifiers. Introducing a post-processing ensemble model improves classification metrics compared to a single deep-learning model. Combining Convolutional Neural Networks and Vision Transformers in an ensemble model achieves the highest accuracy, with 96.3% for damage and soiling detection and 91.8% for damage and soiling type identification. These results significantly outperform one-tier deep learning models, which attain an accuracy of 87.7% when classifying all possible damage and soiling categories.
Predicting slope movement has become a great challenge, especially in the Himalayan region, as such natural hazards cause great damage. Machine Learning (ML) models can help in the prediction of landslide hazards. Despite the capabilities of ML models in predicting landslide hazards, most existing approaches are deficient in capturing changes in weather conditions at day, hour, or minute scales, thus affecting their accuracy in real-time scenarios. These models also generally have difficulties in generalizing predictions due to limited data availability, and they cannot frequently provide multi-step ahead predictions that are crucial for effective disaster preparedness and timely response. We introduced the hierarchical architecture ML model, specifically the hierarchical transformer prediction autoencoder (H-TPA), which is capable of predicting slope movement with high temporal resolution and enhanced generalization capabilities. This study was based on a rich dataset from sixty-four landslide locations over five years. In this work, we utilize 1,066,009 samples for the training set, which were balanced down to 23,328 samples in order to address class imbalance. The validation set contained 100,000 samples, while the test set was made up of 164,082 samples. This work also presents a VSA methodology for determining threshold values of environmental attributes that trigger slope movements. The performance evaluation of the H-TPA model using this dataset demonstrates very good performance with an F1 score of 0.889, 0.760, and 0.746 for the training, validation, and test datasets, respectively, in predicting slope movements 10 min in advance. Moreover, the present study focused on the analyses of weather condition factors and soil moisture affecting the landslide triggers, which indicated the role of temperature, humidity, barometric pressure, rainfall, and sunlight intensity in small or large slope movements according to certain threshold values. This study generally contributes to the present understanding and enhances the knowledge of landslide prediction in the Himalayan region, besides providing recommendations for geo-scientific knowledge improvement and mitigation strategies.
Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities. Despite the potential to improve landslide predictability, deep learning has yet to be sufficiently explored for complex deformation patterns associated with landslides and is inherently opaque. Herein, we developed a holistic landslide deformation forecasting method that considers spatiotemporal correlations of landslide deformation by integrating domain knowledge into interpretable deep learning. By spatially capturing the interconnections between multiple deformations from different observation points, our method contributes to the understanding and forecasting of landslide systematic behavior. By integrating specific domain knowledge relevant to each observation point and merging internal properties with external variables, the local heterogeneity is considered in our method, identifying deformation temporal patterns in different landslide zones. Case studies involving reservoir-induced landslides and creeping landslides demonstrated that our approach (1) enhances the accuracy of landslide deformation forecasting, (2) identifies significant contributing factors and their influence on spatiotemporal deformation characteristics, and (3) demonstrates how identifying these factors and patterns facilitates landslide forecasting. Our research offers a promising and pragmatic pathway toward a deeper understanding and forecasting of complex landslide behaviors. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).
As urban infrastructure becomes denser, subway operations face numerous risks, including adjacent construction and structural damage deterioration. Integrated monitoring is crucial to ensure safety. This study presents a multitask vibration transformer (M-TVT) model, which utilizes an Expert-Gate network to manage task-related information sharing. The model achieves integrated identification for the type and spatial distribution of internal and external tunnel abnormal vibration responses, along with assessing structural damage degree. Meanwhile, a tunnel-train-soil coupling experiment is conducted to validate the efficacy of the M-TVT model. The results demonstrate that the M-TVT model with the Expert-Gate network maintains high accuracy and stability, efficiently shares parameter information among tasks and achieves improvement in accuracy compared to single-task models.
This study is focused on optimizing electromagnetic acoustic transducer (EMAT) sensors for enhanced ultrasonic guided wave signal generation in steel cables using CAD and modern manufacturing to enable contactless ultrasonic signal transmission and reception. A lab test rig with advanced measurement and data processing was set up to test the sensors' ability to detect cable damage, like wire breaks and abrasion, while also examining the effect of potential disruptors such as rope soiling. Machine learning algorithms were applied to improve the damage detection accuracy, leading to significant advancements in magnetostrictive measurement methods and providing a new standard for future development in this area. The use of the Vision Transformer Masked Autoencoder Architecture (ViTMAE) and generative pre-training has shown that reliable damage detection is possible despite the considerable signal fluctuations caused by rope movement.
Time-series interferometric synthetic aperture radar (InSAR) provides a unique tool for measuring large-scale and long-term land surface deformation. Under the assumption of a single linear deformation model in conventional InSAR, it is difficult to quantify and interpret the impacts of multiple environmental factors that presumably induce nonlinear deformations. In this paper, we propose a SAR-Transformer method to decompose InSAR time-series signals into various physics-related components and apply the method to evaluate the deformation of the world's longest cross-sea bridge, the Hong Kong-Zhuhai-Macao Bridge (HZMB). We first developed an improved bridge geometry-based InSAR network to monitor the deformation of the HZMB using Sentinel-1 and COSMO-SkyMed images from 2019 to 2022, which were validated using the leveling and GPS data. The SAR-Transformer model was trained using synthetic InSAR time-series samples and applied to decompose the monitored InSAR measurements. Compared with that of conventional curve-fitting and seasonal-trend decomposition using LOESS, SAR-Transformer reduced the mean absolute error at least by 58.32% and mean absolute percentage error at least by 8.84% for time-series signal reconstruction. We evaluated the decomposed patterns according to the geotechnical, meteorological, and marine processes, and found that: 1) Seasonal thermal expansion owing to temperature changes was significant in all parts of the bridge, and deflection due to concrete shrinkage and creep was observed on cable-stayed bridges. 2) The artificial islands experienced evident ground subsidence with a decelerating trend. In particular, the newly adopted non-dredged reclamation method resulted in a lower decelerated settlement than that of fully-dredged reclamation areas. 3) The seawall showed linear horizontal movement from the outward stretching of the reclaimed soil consolidation and periodic displacement related to sea tidal loading. Furthermore, typhoons and coastal earthquakes had limited effects on the permanent movement of the bridge. These results improve the understanding of the interactions between artificial super-infrastructures and environmental factors, and provide valuable guidelines for the maintenance and management of the HZMB.