Elsevier BVActa Medica Okayama0266-352X1782025End-to-end time-dependent probabilistic assessment of landslide hazards using hybrid deep learning simulator106920ENMengluHuangDepartment of Civil and Environmental Engineering, Okayama UniversityShin-ichiNishimuraDepartment of Civil and Environmental Engineering, Okayama UniversityToshifumiShibataDepartment of Civil and Environmental Engineering, Okayama UniversityZe ZhouWangMarie Skłodowska-Curie Fellow, Department of Engineering, University of CambridgeEarly warning detection of landslide hazards often requires real-time or near real-time predictions, which can be challenging due to the presence of multiple geo-uncertainties and time-variant external environmental loadings. The propagation of these uncertainties at the system level for understanding the spatiotemporal behavior of slopes often requires time-consuming numerical calculations, significantly hindering the establishment of an early warning system. This paper presents a hybrid deep learning simulator, which fuses parallel convolutional neural networks (CNNs) and long short-term memory (LSTM) networks through attention mechanisms, termed PCLA-Net, to facilitate time-dependent probabilistic assessment of landslide hazards. PCLA-Net features two novelties. First, it is capable of simultaneously handling both temporal and spatial information. CNNs specialize in interpreting spatial data, while LSTM excels in handling time-variant data. Coupled with two attention mechanisms, the two modules are combined to probabilistically predict the spatiotemporal behavior of slopes. Second, PCLA-Net realizes end-to-end predictions. In this paper, the Liangshuijing landslide in the Three Gorges Reservoir area of China is used to illustrate PCLA-Net. It is first validated followed by a comparison with existing techniques to demonstrate its improved predictive capabilities. The proposed PCLA-Net simulator can achieve the same level of accuracy with at least 50% reduction in computation resources.No potential conflict of interest relevant to this article was reported.ElsevierActa Medica Okayama003808066122021Reliability-based design for earth-fill dams against severe natural disaster events271282ENShin-ichiNishimuraGraduate School of Environmental and Life Science, Okayama UniversityToshifumiShibataGraduate School of Environmental and Life Science, Okayama UniversityTakayukiShukuGraduate School of Environmental and Life Science, Okayama UniversityThe maintenance of geotechnical structures, such as earth-fill dams, is required as a countermeasure against severe natural disasters, particularly earthquakes and heavy rains. The reliability-based analysis introduced here is in response to the recent demand for low-cost improvements.First, a statistical model of N values was determined from Swedish weight sounding (SWS) tests to present the spatial variability of the soil strength. Then, a reliability-based analysis of embankments was conducted by considering the variability of the internal friction angle derived from N value, and the seismic hazard for the Nankai Trough. The next step was to evaluate the probability of the overflow of earth-fills during heavy rains. The rainfall intensity was considered as a probabilistic parameter, and the various rainfall patterns were tested by the proposed method. Finally, the total risk due to both earthquakes and heavy rains was evaluated for an earth-fill site. As a result, the possibility for the practical use of the proposed method in making plans for the maintenance of deteriorated earth-fill dams was verified.No potential conflict of interest relevant to this article was reported.岡山大学環境理工学部Acta Medica Okayama1341909925120203次元計測を利用した効率的な3次元有限要素モデル化法の提案14ENMinoruKANESHIGEShin-ichiNISHIMURAToshifumiSHIBATATakayukiSHUKU10.18926/fest/58060 In this decade, 3-dimensional topographic survey has been developed by using the UAV as like drones. With the technique, the complete topographies of the geo-structures can be measured. Although the accurate shapes of the geo-structures can be obtained, the numerical methods as like the finite element method is are not related to the 3-dimensional survey directly. In this research, the finite mesh modelling technique with use of the 3-D topographic survey is developed. The models of the earth-fill embankments formed from measured 3-D data are introduced as the examples.No potential conflict of interest relevant to this article was reported.