The urban agglomeration in central Guizhou is located in a crustal deformation area caused by tectonic uplift between the Mesozoic orogenic belt of East Asia and the Alpine-Tethys Cenozoic orogenic belt, with high mountains, steep slopes, fractured rock masses and a fragile ecological environment; this area is the most affected by landslides in Guizhou Province, China. In the past decade, there were a total of 613 medium and large landslide disasters, resulting in 137 deaths and a direct economic loss of 1.032 billion yuan. Therefore, this study selected 12 indicators from the topography, geological structure, and external inducing factors, and conducted factor collinearity analysis using the variance expansion coefficient to construct a landslide hazard assessment index system. The statistical analysis model was combined with a variety of machine learning models, and the selection of negative sample points was restricted in various ways to improve training data accuracy and enable machine learning model predictions with sufficiently supervised prerequisites. The accuracy of the model was validated by ROC curve analysis. The AUC values of the SVM, DNN, and bagging models were all greater than 0.85, indicating that the results were credible. However, the overall accuracy was SVM > DNN > Bagging; that is, SVM was more suitable for landslide hazard assessment of the urban agglomeration in central Guizhou. Finally, field surveys were used to validate multiple sites with historical landslides in extremely high-hazard areas and analyse their development characteristics. The evaluation results can provide strong guidance for engineering design, construction and disaster prevention decision-making of urban agglomeration in central Guizhou.

Landslide hazard assessment provides an important basis for regional geological disaster prevention and mitigation. Landslide hazard is commonly characterized in terms of three fundamental dimensions: spatial occurrence, temporal occurrence, and potential magnitude. Based on this conceptual framework, Guiyang, a typical mountainous city in western China, was selected as the study area, and slope units were adopted as the basic assessment units. First, eight topographic, geological, and hydrological conditioning factors were incorporated into an information-value model to evaluate the landslide susceptibility of each slope unit. The resulting min–max-normalized susceptibility index was used as the spatial susceptibility component. Second, the historical landslide inventory was combined with kernel density estimation, and a Poisson-based exceedance probability model was used to estimate the model-based exceedance probability of one or more landslides occurring in each slope unit under a 10-year scenario time window. This probability was used as the temporal component. Third, the potential landslide volume of each slope unit was predicted using machine-learning algorithms. The predicted small-, medium-, and large-volume classes were assigned ordinal magnitude weights of 1, 2, and 3, respectively, and were used as the magnitude component. Finally, the three components were integrated using a multiplicative composite index to obtain the relative landslide hazard of each slope unit. The results were as follows. The overall landslide hazard in Guiyang was dominated by medium and low hazard levels. Furthermore, 422 high-hazard slope units were identified, accounting for 15.58% of all slope units. These units were mainly concentrated in the central and northern regions. In terms of administrative divisions, Xifeng County, Kaiyang County, Xiuwen County, Qingzhen city, and Huaxi district ranked among the top five administrative regions with the most high-hazard slope units. Therefore, these regions should be considered key areas for disaster prevention and mitigation. Based on the hazard zonation, 21 selected high-hazard slopes were examined using UAV imagery and on-site inspection to document their representative geomorphological and deformation characteristics. The observations provided qualitative field support for the geological plausibility of selected high-hazard predictions. The findings of this study provide an important decision-making basis for landslide mitigation efforts by the Guiyang Municipal Government.

The urban agglomeration in central Guizhou is located in a crustal deformation area caused by tectonic uplift between the Mesozoic orogenic belt of East Asia and the Alpine-Tethys Cenozoic orogenic belt, with high mountains, steep slopes, fractured rock masses and a fragile ecological environment; this area is the most affected by landslides in Guizhou Province, China. From 2011 to 2023, there were a total of 648 medium and large landslide disasters, resulting in 143 deaths and a direct economic loss of 1.191 billion yuan. Therefore, this study selected 12 indicators from the topography, geological structure, and external inducing factors, and conducted factor collinearity analysis using the variance expansion coefficient to construct a landslide hazard assessment index system. The statistical analysis model was combined with a variety of machine learning models, and the selection of negative sample points was restricted in various ways to improve training data accuracy and enable machine learning model predictions with sufficiently supervised prerequisites. The accuracy of the model was validated by ROC curve analysis. The AUC values of the SVM, DNN, and bagging models were all greater than 0.85, indicating that the results were credible. However, the overall accuracy was SVM > DNN > Bagging; that is, SVM was more suitable for landslide hazard assessment of the urban agglomeration in central Guizhou. Finally, field surveys were used to validate multiple sites with historical landslides in extremely high-hazard areas and analyse their development characteristics. The evaluation results can provide strong guidance for engineering design, construction and disaster prevention decision-making of urban agglomeration in central Guizhou.