Data Mining and Deep Learning for Predicting the Displacement of “Step-Like” Landslides

Landslide displacement prediction is one of the unsolved challenges in the field of geological hazards, especially in reservoir areas. Affected by rainfall and cyclic fluctuations in reservoir water levels, a large number of landslide disasters have developed in the Three Gorges Reservoir Area. In this article, the Baishuihe landslide was taken as the research object. Firstly, based on time series theory, the landslide displacement was decomposed into three parts (trend term, periodic term, and random term) by Variational Mode Decomposition (VMD). Next, the landslide was divided into three deformation states according to the deformation rate. A data mining algorithm was introduced for selecting the triggering factors of periodic displacement, and the Fruit Fly Optimization Algorithm–Back Propagation Neural Network (FOA-BPNN) was applied to the training and prediction of periodic and random displacements. The results show that the displacement monitoring curve of the Baishuihe landslide has a “step-like” trend. Using VMD to decompose the displacement of a landslide can indicate the triggering factors, which has clear physical significance. In the proposed model, the R2 values between the measured and predicted displacements of ZG118 and XD01 were 0.977 and 0.978 respectively. Compared with previous studies, the prediction model proposed in this article not only ensures the calculation efficiency but also further improves the accuracy of the prediction results, which could provide guidance for the prediction and prevention of geological disasters.

Analysis of Reservoir Seismic Law Based on Three-Dimensional Morphological Characteristics of Joint Surface Related to Listric Fault

Since water storage, earthquakes occurred in Badong County, Hubei Province, accounted for as much as one-third of the strong earthquakes in the Three Gorges Reservoir area. For example, the MS5.1 earthquake occurred in December 2013 near the Gaoqiao fault in Badong County. The earthquake time, magnitude, and location analysis showed that reservoir earthquakes in this area exhibited some characteristics, such as periodicity, migration, and deep extension. Based on the regional stratum lithology and structural characteristics, this paper designed a curved joint on a small scale to simulate the structural morphology of the Gaoqiao fault and carried out triaxial compression tests under different immersion times to analyze the morphological parameters of the joint surface. The results showed that topological parameters such as root mean square height (Sq), arithmetic average height (Sa), reverse load area ratio (Smc), and minimum autocorrelation length (Sal) could effectively characterize the degree of damage and deterioration of curved joints. The test privides a reference for analyzing the evolution law of the seismic characteristics of the reservoir.

Assessment of Erosion Characteristics in Purple and Yellow Soils Using Simulated Rainfall Experiments

Soil erosion of sloped lands is one of the important sources of substantive sediments in watersheds. In order to investigate erosion characteristics of sloped lands during rainfall events in the Three Gorges Reservoir Area, erosion processes of purple and yellow soils under different slope gradients and rainfall intensities were studied by using a rainfall simulator. The results showed that the sediment concentration in runoff was closely correlated with rainfall intensity. The sediment concentration in runoff gradually rose to a peak with time, and then gradually declined and approach a steady rate during simulation rainfall events. The particle size distribution of surface soils before the rainfall was different from that after the rainfall. Soil erosion mainly resulted in the loss of fine particles of surface soil through runoff, and the fine particles of soil were enriched in sediments. Soil erosion rates were gradually increased with the slope gradient when the slope gradient was less than 10°, and significantly increased when the slope gradient was more than 10°. The slope factor of yellow soil could be fitted well to that calculated by the formula of Universal Soil Loss Equation (USLE). The trend of the slope factor of purple soil was similar to that of the slope factor that was derived from USLE. Therefore, the effect of slope gradients on soil erosion need to be further researched when USLE was applied to predict erosion in purple soil area.

Characteristics of carbon source greenhouse gas flux in the water–air formation in the middle and upper reaches of the Three Gorges Reservoir

This study selected five points in the middle and upper mainstream of the Three Gorges Reservoir area. Starting from May 2016, the greenhouse gases CO2 and CH4 from the water–air formation at the sampling points have been monitored month by month for 10 months. Using the headspace balance method and the thin boundary layer model estimation method, we obtained the CO2 and CH4 partial pressure ranges and the water–air formation diffusion flux at the mainstream point. It is found that the CH4 partial pressure of water body is significantly positively correlated with water temperature, and significantly negatively correlated with DO; the CH2 partial pressure of water body is positively correlated with water temperature, but negatively correlated with conductivity, DO, pH and wind speed. The diffusion fluxes of CH4 and CO2 at the water–air formation are positively correlated with CH4 partial pressure and water temperature, and negatively correlated with ph, DO and conductivity. It is also found that the reservoir has a certain mitigation effect on the release of CO2 from the river water body, and the CH4 diffusion flux at the water–air formation is roughly equivalent.

Dynamics of Mid-Channel Bar during Different Impoundment Periods of the Three Gorges Reservoir Area in China

The dynamics of the mid-channel bars (MCBs) in the Three Gorges Reservoir (TGR) were substantially impacted by the large water-level changes due to the impoundments of the TGR. However, it is still not clear how the morphology of the MCBs changed under the influence of water level and hydrological regime changes induced by the impoundments and operation of the TGR. In this work, the MCBs in the TGR were retrieved using Landsat remote sensing images from 1989 to 2019, and the spatio-temporal variations in the number, area, morphology and location of the MCBs during different impoundment periods were investigated. The results showed that the number and area of MCBs changed dramatically with water-level changes, and the changes were dominated by MCBs with an area less than 0.03 km2 and larger than 1 km2. The area of MCBs decreased progressively with the rising water level, and the number generally showed a decreasing trend, with the minimum number occurring at the third stage when the water level reached 139 m, resulting in the maximum average area at this period. The ratio of length to width of the MCBs generally decreased with the changes in hydrological and sediment regimes, leading to a shape adjustment from narrow–long to relatively short–round with the rising of the water level. The water impoundments of the TGR led to the migration of the dominant area from the upper section to the middle section of the TGR and resulted in a more even distribution of MCBs in the TGR. The results improve our understanding of the mechanisms of the development of MCBs in the TGR under the influence of water impoundment coupled with the annually cyclic hydrological regime and longer periods of inundation and exposure.