Effective landslide hazard prevention requires accurate landslide prediction models, and the data-driven approaches based on deep learning models are gradually becoming a hot research topic. When training deep learning models, it is always preferable to have a large dataset, while most available landslide monitoring data are limited. For data missing or data sparseness problems, conventional interpolation methods based on mathematical knowledge lack mechanism interpretability. This paper proposes that numerical simulations can be used to expand the deep learning dataset we need. Taking the Jiuxianping landslide in the Three Gorges Reservoir Area (TGRA) as the geological background, a finite element numerical model was established, and the landslide displacement time series data were solved considering the boundary conditions of reservoir water level change and precipitation. Next, based on three metrics: Euclidean distance, cosine similarity, and dynamic time warping (DTW) distance, the time series similarity between the displacement data obtained from simulation and data obtained from actual monitoring were verified. Finally, the combined deep learning model was built to predict the displacement of the Jiuxianping landslide. The model was trained on both the simulated and monitored datasets and tested by the last 12 monitored data points. Prediction results with the testing set showed that the models trained using the expanded training set from numerical simulations exhibited lower prediction errors, and the errors had a more concentrated distribution. The results suggest that this landslide displacement prediction method combining numerical simulation and deep learning can solve the problem of inadequate datasets due to low monitoring frequency, as well as provide an interpretation of the physical mechanism for data vacancy filling.

In the southwest of China, there are widely distributed expansive soils. However, to save costs and manage the speed of construction, these shallow expansive soils are often filled with subgrade materials. Therefore, it is necessary to clearly understand the mechanical behaviors of unmodified shallow expansive soils. Current research on the mechanical behaviors of shallow expansive soils is mainly focused on shear and compressive strengths but rarely on the tensile strength since general tests are costly, time consuming, and difficult to conduct. Therefore, uniaxial tensile, unconfined compression and direct shear tests were carried out to study the mechanical behavior of shallow unsaturated expansive soils under different saturation degrees, and the tests analyzed the change mechanism of its mechanical behavior. The following were found: (1) with an increase in saturation degree, the uniaxial tensile strength, unconfined compressive strength, shear strength, cohesive force, and internal friction angle first increased and then decreased; (2) when the saturation degree increased from 18.7% to the saturation degree corresponding to the peak, the uniaxial tensile strength, unconfined compressive strength, cohesive force, and internal friction angle increased by about 11 times, 3.24 times, 2.34 times, and 0.52 times, respectively; (3) when the saturation degree increased from the saturation degree corresponding to the peak to 80.3%, they decreases by about 42%, 51.4%, 36%, and 50%, respectively; (4) with the increase in dry density, the saturation degree corresponding to the peak of uniaxial tensile strength gradually increased, while the saturation degree corresponding to the peak of unconfined compressive and shear strength did not significantly change.