The evaluation of landslide susceptibility is of great significance in the prevention and management of geological hazards. The accuracy of the landslide susceptibility prediction model based on machine learning is significantly higher than that of traditional expert knowledge and the conventional mathematical statistics model. The correct and reasonable selection of non-landslide samples in the machine learning model greatly improves the prediction accuracy and reliability of the regional landslide susceptibility model. Focusing on the problem of selecting non-landslide samples in the machine learning model for landslide susceptibility evaluation, this paper proposes a landslide susceptibility evaluation method based on the combination of an information model and machine learning in traditional mathematical statistics. First, the influence factors for landslide susceptibility evaluation are screened by the correlation analysis method. Second, the information value model is used to delimit areas with low and relatively low landslide susceptibility, and non-landslide points are randomly selected. Third, a landslide susceptibility evaluation method combined with IV-ML, such as logistic regression (IV-LR), random forest (IV-RF), support vector machine (IV-SVM), and artificial neural network (IV-ANN), is established. Finally, the landslide susceptibility factors in the Dabie Mountain area of Anhui Province are analyzed, and the accuracy of the landslide susceptibility evaluation results using the IV-LR, IV-RF, IV-SVM, and IV-ANN and LR, RF, SVM, and ANN methods are compared. The accuracy is evaluated by examining the ACC, AUC, and kappa values of the model. The results indicate that the evaluation effect of the IV-ML models (IV-LR, IV-RF, IV-SVM, IV-ANN) on landslide susceptibility is significantly higher than that of the ML models (LR, RF, SVM, ANN).

Taking the mausoleums in the main urban area of Nanjing city as the study object, with the support of GIS technology, this paper extracts eight influencing factors (surface roughness, elevation, surface cutting depth, surface peaks, outfall, river system, slope, and aspect) corresponding to geomantic elements (“Long”, “Sha”, “Shui”, and “Xue”) in the geographical environments of mausoleums. The AHP is applied in the correlation weight method to calculate the weights of the eight influencing factors, while the information content method is applied in the grading method to calculate the numerical index of each factor. The feng shui (geomantic) suitability of the mausoleums in the main urban area of Nanjing is evaluated using the AHP-weighted information content method and by combining expert knowledge and experience with mathematical statistical techniques. According to the feng shui (geomantic) suitability evaluation results obtained for the mausoleums in the study area, the relatively low-suitability area accounts for 14.55% of the entire study area, the low-suitability area accounts for 25.40%, the suitable area accounts for 29.13%, the relatively high-suitability area accounts for 22.00%, and the high-suitability area accounts for 8.92%. Finally, through a sensitivity analysis of the model, a verification analysis applied using random mausoleums and a feng shui (geomantic) analysis of the Ming Xiaoling Mausoleum, the feng shui (geomantic) suitability evaluation results obtained for the mausoleums analyzed herein are found to be consistent with the actual distribution of the mausoleum sites. The research shows that the AHP-weighted information method based on GIS is suitable for evaluating the feng shui (geomantic) suitability of mausoleums.

A structural landform is defined by its surface morphology, controlled by tectonics, lithology (arrangement and resistance), and folded structures, and demonstrated by the characteristics and relationships between geological and geomorphic elements. It is very important to use geographic information system (GIS) technology to accurately describe and express elements of structural landforms and their relationships. In this study, a GIS approach for expressing structural landforms, based on “forms–elements–relationships”, was developed. The contributions of this paper are as follows: (1) Combined with the surface morphological characteristics, the structural landforms were abstracted into geological and geomorphic elements, and the characteristics and relationships of these elements were analyzed. (2) The elements of structural landforms and their relationships were abstracted into spatial objects and topological relationships. The spatial objects of the structural landform were designed based on the types and characteristics of structural landform elements. The topological relationships were developed based on the definition of the structural landform morphotype. (3) The structural landform markup language (SLML) method of “forms–elements–relationships” was created. (4) Two typical structural landforms, namely, Qixia Mountain and Gaoli Mountain, were used as examples to verify the feasibility and effectiveness of the GIS approach for expressing structural landforms. This paper describes and expresses the “forms–elements–relationships” of structural landforms from the perspective of GIS, which is expected to promote the joint development of structural geomorphology and GIS.

Knowing the GIS expression of geological phenomena is an important basis for the combination of geology and GIS. Regional geological structures include folds, faults, strata, rocks, and other typical geological phenomena and are the focus of geological GIS research. However, existing research on the GIS expression of regional geological structure focuses on the expression of the spatial and attribute characteristics of geological structures, and our knowledge of the expression of the semantic, relationship, and evolution processes of geological structures is not comprehensive. In this paper, a regional geological structure scene expression model with the semantic terms positional accuracy, geometric shape, relationship type, attribute type, and time-type attributes and operations is proposed. A regional geological structure scenario markup language (RGSSML) and a method for mapping it with graphics are designed to store and graphically express regional geological structure information. According to the geological time scale, a temporal reference coordinate system is defined to dynamically express the evolution of regional geological structures. Based on the dynamic division of the time dimension of regional geological structures, the expression method of “time dimension + space structure” for the regional geological structure evolution process is designed based on the temporal model. Finally, the feasibility and effectiveness of the regional geological structure scene expression method proposed in this paper is verified using the Ningzhen Mountain (Nanjing section) as an example. The research results show that the regional geological structure scene expression method designed in this paper has the following characteristics: (1) It can comprehensively express the spatial characteristics, attribute characteristics, semantics, relationships, and evolution processes of regional geological structures; (2) it can be used to realize formalized expression and unified storage of regional geological information; and (3) it can be used to realize dynamic expression of the regional geological structure evolution process. Moreover, it has significant advantages for the expression of regional geological structure semantics, relationships, and evolution processes. This study improves our knowledge of the GIS expression of regional geological structures and is expected to further promote the combination and development of geology and GIS.