Assessment of landslide susceptibility along mountain highways based on different machine learning algorithms and mapping units by hybrid factors screening and sample optimization

Sun, Dongmei; Gu, Qingyu; Wen, Haijia; Xu, Jiahui; Zhang, Yalan; Shi, Shuxian; Xue, Mengmeng; Zhou, Xinzhi

doi:10.1016/j.gr.2022.07.013

Cited by 65 publications

(12 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Landslides are typically framed as a binary classification problem (0,1), often evaluated using a confusion matrix in conjunction with the AUC curve to visualise and assess the predictive accuracy of the model (Sun, Gu, Wen, Xu, et al, 2022). Using a threshold of 0.5, a predicted value greater than 0.5 signifies a predicted landslide occurrence, whereas a predicted value less than 0.5 suggests no landslide occurrence.…”

Section: Methodsmentioning

confidence: 99%

Insights into landslide susceptibility in different karst erosion landforms based on interpretable machine learning

Sun,

Wang,

Wen

et al. 2023

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

The aim of the present study was to assess differences in the conditioning factors and the performance of landslide susceptibility mapping (LSM), employing the SHapley Additive exPlanations (SHAP) model to gain profound insights into the intrinsic decision‐making mechanism of LSM in diverse landforms. Two typical karst erosion landforms were selected as the research areas. Based on 15 conditioning factors, LSMs for the two areas were developed using the Bayesian optimization random forest (RF) and eXtreme Gradient Boosting (XGBoost). The SHAP model was used to explore the landslide formation mechanisms from both global and local perspectives. The results show that the area under the curve (AUC) values of the XGBoost models were 0.791 and 0.761, and the AUC values of the RF models were 0.844 and 0.817, in the two different landform areas, respectively. The RF model's accuracy was higher than that of the XGBoost model in both regions. In the low‐elevation hills area, the primary three conditioning factors were identified as slope, topographic relief and distance from the river. Conversely, in the microrelief and mesorelief low mountain area, the predominant conditioning factors were elevation, distance from the river and distance from the road. Both karst landform areas exhibited a high sensitivity to the distance from the river, indicating its significant interaction with other factors contributing to landslide occurrences. Notably, the RF model demonstrated superior performance compared to the XGBoost model, rendering it a more suitable choice for conducting landslide susceptibility mapping research in karst erosion landform areas. In the present study, a comprehensive explanatory framework based on the RF‐SHAP model was proposed, which enables both global and local interpretation of landslides in various karst landscapes. Such an approach explores the intrinsic decision‐making mechanism of the model, enhancing the transparency and realism of landslide susceptibility prediction results.

show abstract

Section: Methodsmentioning

confidence: 99%

Insights into landslide susceptibility in different karst erosion landforms based on interpretable machine learning

Sun,

Wang,

Wen

et al. 2023

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

show abstract

“…In terms of type, small/shallow/soil landslides account for 82% of the total number of landslides, and large/deep/clay landslides account for only 18%. From the perspective of main triggering factors, rainfall-induced landslides accounted for the majority (75.88%), whereas groundwater (pore water) and human activity-induced landslides accounted for 10.05% and 2.01%, respectively (Sun, Gu, Wen, Shi, et al, 2022). Data sources of each conditioning factor are shown in Table 1.…”

Section: Data Sourcementioning

confidence: 99%

“…Landslides are a prevalent natural disaster in China, occurring frequently and having a wide distribution, resulting in significant devastation (Bruz on et al, 2021;Reichenbach et al, 2018). According to statistics (Sun, Gu, Wen, Shi, et al, 2022), 320 000 landslide disasters have occurred in China from 2000 to 2019, causing a total economic loss of $9.894 billion. The scientific prediction and prevention of landslides have become a growing concern in recent times (Fleuchaus et al, 2021;Ji et al, 2020;Nguyen et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Recently, a combination of interpretable algorithms and machine learning is favoured to study LSM (Sun, Gu, Wen, Xu, et al, 2022;Zhang et al, 2023). Interpretable algorithms can explain the predictive results of the model and effectively infer its decision-making principles, consequently enhancing the model's credibility (Ghorbani et al, 2022;Guo et al, 2022;Zhang et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel QLattice‐based whitening machine learning model of landslide susceptibility mapping

Sun,

Ding,

Wen

et al. 2023

Earth Surf Processes Landf

Self Cite

View full text Add to dashboard Cite

Landslide susceptibility mapping (LSM) enables the prediction of landslide occurrences, thereby offering a scientific foundation for disaster prevention and control. In recent years, numerous studies have been conducted on LSM using machine learning techniques. However, the majority of machine learning models is considered “black box” models due to their lack of transparent explanations. In contrast, the QLattice model serves as a white box model, as it can elucidate the decision‐making mechanism while representing a novel approach to whitening machine learning models. QLattice possesses the capability to automatically select and scale data features. In this study, Fengjie County in China was selected as the research area, with slope units serving as evaluation units. A geospatial database was constructed using 12 conditioning factors, including elevation, slope, and annual average rainfall. LSM models were conducted using both the QLattice and random forest (RF) algorithms. The findings demonstrate that the QLattice model achieved an area under curve value of 0.868, while the RF model attained an area under curve value of 0.849 for the test datasets. These results highlight the superior predictive ability and stability of the QLattice model compared with RF. Furthermore, QLattice can explicate and clarify the change processes of conditioning factors, thereby revealing the internal decision‐making mechanism and causes behind the LSM model's decisions. The innovative QLattice‐based model provides new ideas and methodologies for LSM research.

show abstract

“…SHAP is easy to operate [36] and can be presented graphically [34]. Another XAI method is LIME (Local Interpretable Model-agnostic Explanations), which reflects the behavior of a classifier in predicting samples, whereby it is possible to observe the prediction behavior of a model [35,37]. Based on the above, it can be said that the aforementioned methods are a reliable option to be considered in the analysis of conditioning factors that influence landslide generation.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Conditioning Factors in Cuenca, Ecuador, for Landslide Susceptibility Maps Generation Employing Machine Learning Methods

Bravo-López

Sellers

Fernández

2023

Land

View full text Add to dashboard Cite

Landslides are events that cause great impact in different parts of the world. Their destructive capacity generates loss of life and considerable economic damage. In this research, several Machine Learning (ML) methods were explored to select the most important conditioning factors, in order to evaluate the susceptibility to rotational landslides in a sector surrounding the city of Cuenca (Ecuador) and with them to elaborate landslide susceptibility maps (LSM) by means of ML. The methods implemented to analyze the importance of the conditioning factors checked for multicollinearity (correlation analysis and VIF), and, with an ML-based approach called feature selection, the most important factors were determined based on Classification and Regression Trees (CART), Feature Selection with Random Forests (FS RF), and Boruta and Recursive Feature Elimination (RFE) algorithms. LSMs were implemented with Random Forests (RF) and eXtreme Gradient Boosting (XGBoost) methods considering a landslide inventory updated to 2019 and 15 available conditioning factors (topographic (10), land cover (3), hydrological (1), and geological (1)), from which, based on the results of the aforementioned analyses, the six most important were chosen. The LSM were elaborated considering all available factors and the six most important ones, with the previously mentioned ML methods, and were compared with the result generated by an Artificial Neural Network with resilient backpropagation (ANN rprop-) with six conditioning factors. The results obtained were validated by means of AUC-ROC value and showed a good predictive capacity for all cases, highlighting those obtained with XGBoost, which, in addition to a high AUC value (>0.84), obtained a good degree of coincidence of landslides at high and very high susceptibility levels (>72%). Despite the findings of this research, it is necessary to study in depth the methods applied for the development of future research that will contribute to developing a preventive approach in the study area.

show abstract

Assessment of landslide susceptibility along mountain highways based on different machine learning algorithms and mapping units by hybrid factors screening and sample optimization

Cited by 65 publications

References 53 publications

Insights into landslide susceptibility in different karst erosion landforms based on interpretable machine learning

Insights into landslide susceptibility in different karst erosion landforms based on interpretable machine learning

A novel QLattice‐based whitening machine learning model of landslide susceptibility mapping

Analysis of Conditioning Factors in Cuenca, Ecuador, for Landslide Susceptibility Maps Generation Employing Machine Learning Methods

Contact Info

Product

Resources

About