Machine learning-based methods are commonly used for landslide susceptibility mapping. Most of the recent publications focused on quantitative analysis, i.e., improving data processing methods, comparing and perfecting the data-driven model itself, but rarely taking the qualitative aspects of the local landslide occurrences into consideration and the further analysis of the key features was always lacking. This study aims to combine qualitative and quantitative analysis and examine its effect on mapping accuracy; based on the feature importance ranks and the related literature, the key features for identifying landslide/non-landslide points of different sub-zones were further analyzed. Before modeling, the study area Yunyang County, Chongqing City, China, was manually divided into four sub-zones based on the information from geological hazards exploration in Chongqing, including the mechanism of landslide formation and sliding failure and geomorphic unit characteristics. Upon the qualitative analysis basis, five grid searches tuned random forest models (one for the whole region and four for the sub-zones independently) were established by 1654 data points and 20 conditioning features. Compared with the conventional data-driven method, the integrated quantitative evaluation based on the qualitative analysis results showed higher reliability, which not only improved the mapping accuracy but also increased the AUC values of all four sub-models, which were 8.8%, 2.3%, 1.9% and 9.1% higher than that of the parent model. Moreover, the quantitative evaluation based on the qualitative analysis revealed the key factors affecting local landslide formation. Therefore, qualitative analysis is recommended in future landslide susceptibility modeling with the additional combination of data-driven methods.

It is crucial to predict landslide displacement accurately for establishing a reliable early warning system. Such a requirement is more urgent for landslides in the reservoir area. The main reason is that an inaccurate prediction can lead to riverine disasters and secondary surge disasters. Machine learning (ML) methods have been developed and commonly applied in landslide displacement prediction because of their powerful nonlinear processing ability. Recently, deep ML methods have become popular, as they can deal with more complicated problems than conventional ML methods. However, it is usually not easy to obtain a well-trained deep ML model, as many hyperparameters need to be trained. In this paper, a deep ML method—the gated recurrent unit (GRU)—with the advantages of a powerful prediction ability and fewer hyperparameters, was applied to forecast landslide displacement in the dam reservoir. The accumulated displacement was firstly decomposed into a trend term, a periodic term, and a stochastic term by complementary ensemble empirical mode decomposition (CEEMD). A univariate GRU model and a multivariable GRU model were employed to forecast trend and stochastic displacements, respectively. A multivariable GRU model was applied to predict periodic displacement, and another two popular ML methods—long short-term memory neural networks (LSTM) and random forest (RF)—were used for comparison. Precipitation, reservoir level, and previous displacement were considered to be candidate-triggering factors for inputs of the models. The Baijiabao landslide, located in the Three Gorges Reservoir Area (TGRA), was taken as a case study to test the prediction ability of the model. The results demonstrated that the GRU algorithm provided the most encouraging results. Such a satisfactory prediction accuracy of the GRU algorithm depends on its ability to fully use the historical information while having fewer hyperparameters to train. It is concluded that the proposed model can be a valuable tool for predicting the displacements of landslides in the TGRA and other dam reservoirs.

A landslide susceptibility map (LSM) is the basis of hazard and risk assessment, guiding land planning and utilization, early warning of disaster, etc. Researchers are often overly keen on hybridizing state-of-the-art models or exploring new mathematical susceptibility models to improve the accuracy of the susceptibility map in terms of a receiver operator characteristic curve. Correlation analysis of the causal factors is a necessary routine process before susceptibility modeling to ensure that the overall correlation among all factors is low. However, this overall correlation analysis is insufficient to detect a high local correlation among the causal factor classes. The objective of this study is to answer three questions: 1) Is there a high correlation between causal factors in some parts locally? 2) Does it affect the accuracy of landslide susceptibility assessment? and 3) How can this influence be eliminated? To this aim, Wanzhou County was taken as the test site, where landslide susceptibility assessment based on 12 causal factors has been previously performed using the frequency ratio (FR) model and random forest (RF) model. In this work, we conducted a local spatial correlation analysis of the “altitude” and “rivers” factors and found a sizeable spatial overlap between altitude-class-1 and rivers-class-1. The “altitude” and “rivers” factors were reclassified, and then the FR model and RF model were used to reevaluate the susceptibility and analyze the accuracy loss caused by the local spatial correlation of the two factors. The results demonstrated that the accuracy of LSMs was markedly enhanced after reclassification of “altitude” and “rivers,” especially for the RF model–based LSM. This research shed new light on the local correlation of causal factors arising from a particular geomorphology and their impact on susceptibility.