Zonation of Landslide Susceptibility in Ruijin, Jiangxi, China

Abstract

Landslides are one of the major geohazards threatening human society. The objective of this study was to conduct a landslide hazard susceptibility assessment for Ruijin, Jiangxi, China, and to provide technical support to the local government for implementing disaster reduction and prevention measures. Machine learning approaches, e.g., random forests (RFs) and support vector machines (SVMs) were employed and multiple geo-environmental factors such as land cover, NDVI, landform, rainfall, lithology, and proximity to faults, roads, and rivers, etc., were utilized to achieve our purposes. For categorical factors, three processing approaches were proposed: simple numerical labeling (SNL), weight assignment (WA)-based and frequency ratio (FR)-based. Then 19 geo-environmental factors were respectively converted into raster to constitute three 19-band datasets, i.e., DS1, DS2, and DS3 from three different processes. Then, 155 observed landslides that occurred in the past decades were vectorized, among which 70% were randomly selected to compose a training set (TS1) and the remaining 30% to form a validation set (VS1). A number of non-landslide (no-risk) samples distributed in the whole study area were identified in low slope (<1–3°) zones such as urban areas and croplands, and also added to the TS1 and VS1 in the same ratio. For comparison, we used the FR approach to identify the no-risk samples in both flat and non-flat areas, and merged them into the field-observed landslides to constitute another pair of training and validation sets (TS2 and VS2) using the same ratio of 7:3. The RF algorithm was applied to model the probability of the landslide occurrence using DS1, DS2, and DS3 as predictive variables and TS1 and TS2 for training to obtain the SNL-based, WA-based, and FR-based RF models, respectively. Verified against VS1 and VS2, the three models have similar overall accuracy (OA) and Kappa coefficient (KC), which are 89.61%, 91.47%, and 94.54%, and 0.7926, 0.8299, and 0.8908, respectively. All of them are much better than the three models obtained by SVM algorithm with OA of 81.79%, 82.86%, and 83%, and KC of 0.6337, 0.655, and 0.660. New case verification with the recent 26 landslide events of 2017–2020 revealed that the landslide susceptibility map from WA-based RF modeling was able to properly identify the high and very high susceptibility zones where 23 new landslides had occurred, and performed better than the SNL-based and FR-based RF modeling, though the latter has a slightly higher OA and KC. Hence, we concluded that all three RF models achieve reasonable risk prediction, but WA-based and FR-based RF modeling deserves a recommendation for application elsewhere. The results of this study may serve as reference for the local authorities in prevention and early warning of landslide hazards.

Factors Affecting Landslide Susceptibility Mapping: Assessing the Influence of Different Machine Learning Approaches, Sampling Strategies and Data Splitting

“…Each DT is a subset of the whole dataset, and is independently sampled by bootstrapping. The randomness of selection at each node is the major advantage of RF model, which often results in highly accurate predictions, making it suitable for LSM [21,[28][29][30].…”

“…The SVM algorithm classifies the objects by using different kernel functions, and the choice of kernel function is critical in the results produced by the algorithm. The algorithm is widely used for LSM applications [29,35] and has been in practice since the 2000s [34].…”

Geoinformation-based landslide susceptibility mapping in subtropical area

“…Since the appearance of artificial intelligence, different ML algorithms including deep learning have been applied in the field of landslide risk mapping 11 , 25 – 28 . Based on the target definition, or rather, collection of samples for training, ML approaches can automatically analyze and extract rules from the input data to make predictions 14 .…”

“…Meanwhile, it is highly efficient in calculating high-dimension data and can fit the nonlinear relationships between target and factors 8 , 29 – 31 . Nevertheless, the prediction accuracy of the most studies, even including those harnessing the hotspotted deep learning techniques 32 – 35 , comes between 75 and 85%, except for those of Huangfu et al 36 , Ou et al 26 , Zhang et al 27 and Zhou et al 28 , who have achieved landslide risk prediction with an accuracy of 86–94.54%. This is not ideal for government to target effectively and accurately the high risk zones for implementing disaster reduction and prevention measures in the subtropical areas.…”

“…It has been decades since hybrid models were proposed for landslide risk assessment. Hybrid models are in fact constructed by integrating two or more models in aspect of sample selection 28 , 37 , feature selection 21 , 38 , information extraction and finally landslide hazard prediction with reasonable accuracy 10 , 22 , 25 , 39 – 41 . Hence, hybrid modeling has gained recently a momentum in improving the accuracy and reliability of landslide risk mapping 26 , 36 , 40 , 42 , 43 .…”