Landslide Susceptibility Mapping Based on Interpretable Machine Learning from the Perspective of Geomorphological Differentiation

Sun, Dongmei; Chen, D C; Zhang, Jialan; Mi, Changlin; Gu, Qingyu; Wen, Haijia

doi:10.3390/land12051018

Cited by 30 publications

(6 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LightGBM gradient-boosting context stands out due to its exceptional tactics when framing decision trees [74]. LightGBM uses a leaf-wise strategy for tree growth as opposed to traditional level-wise methods, which results in improved arithmetic performance [74,75]. The technique involves training trees in a manner where the growth of each leaf is emphasized.…”

Section: Lightgbmmentioning

confidence: 99%

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Ali,

Chen,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Natural disasters, notably landslides, pose significant threats to communities and infrastructure. Landslide susceptibility mapping (LSM) has been globally deemed as an effective tool to mitigate such threats. In this regard, this study considers the northern region of Pakistan, which is primarily susceptible to landslides amid rugged topography, frequent seismic events, and seasonal rainfall, to carry out LSM. To achieve this goal, this study pioneered the fusion of baseline models (logistic regression (LR), K-nearest neighbors (KNN), and support vector machine (SVM)) with ensembled algorithms (Cascade Generalization (CG), random forest (RF), Light Gradient-Boosting Machine (LightGBM), AdaBoost, Dagging, and XGBoost). With a dataset comprising 228 landslide inventory maps, this study employed a random forest classifier and a correlation-based feature selection (CFS) approach to identify the twelve most significant parameters instigating landslides. The evaluated parameters included slope angle, elevation, aspect, geological features, and proximity to faults, roads, and streams, and slope was revealed as the primary factor influencing landslide distribution, followed by aspect and rainfall with a minute margin. The models, validated with an AUC of 0.784, ACC of 0.912, and K of 0.394 for logistic regression (LR), as well as an AUC of 0.907, ACC of 0.927, and K of 0.620 for XGBoost, highlight the practical effectiveness and potency of LSM. The results revealed the superior performance of LR among the baseline models and XGBoost among the ensembles, which contributed to the development of precise LSM for the study area. LSM may serve as a valuable tool for guiding precise risk-mitigation strategies and policies in geohazard-prone regions at national and global scales.

show abstract

Section: Lightgbmmentioning

confidence: 99%

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Ali,

Chen,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…There are many different types of research conducted and a variety of methods used in the development of LSMs [35][36][37][38][39], but the novelty of the present results is that they do not focus on the LSM but on the development of a reliable LI based on high-resolution RS data in combination with the available digital key infrastructure data in order to provide a simple and usable map for the local community: the TSM. In this sense, the TSM presented herein is a "practical" novelty, and the presented methodology can be used/upscaled for larger areas and regions or at a national level.…”

Section: Reflections and Comments On The Presented Perennial Research...mentioning

confidence: 99%

Remote Sensing and GIS in Landslide Management: An Example from the Kravarsko Area, Croatia

Podolszki,

Karlović

2023

Remote Sensing

View full text Add to dashboard Cite

The Kravarsko area is located in a hilly region of northern Croatia, where numerous landslides endanger and damage houses, roads, water systems, and power lines. Nevertheless, natural hazard management plans are practically non-existent. Therefore, during the initial research, a landslide inventory was developed for the Kravarsko pilot area based on remote sensing data (high-resolution digital elevation models), and some of the landslides were investigated in detail. However, due to the complexity and vulnerability of the area, additional zoning of landslide-susceptible areas was needed. As a result, a slope gradient map, a map of engineering geological units, and a land-cover map were developed as inputs for the landslide susceptibility map. Additionally, based on the available data and a landslide inventory, a terrain stability map was developed for landslide management. Analysis and map development were performed within a geographical information system environment, and the terrain stability map with key infrastructure data was determined to be the “most user-friendly and practically usable” resource for non-expert users in natural hazard management, for example, the local administration. At the same time, the terrain stability map can easily provide practical information for the local community and population about the expected landslide “risk” depending on the location of infrastructure, estates, or objects of interest or for the purposes of future planning.

show abstract

“…The above studies comprehensively adjusted their results through corresponding coupling methods, enhancing the accuracy of the respective models. Overall, most existing research focuses on using speci c methods to associate models for susceptibility assessment in designated regions(Jia, Dai, and Yang 2019; Sun et al 2023). Fewer studies provide a sound rationale and thorough analysis and delve into the comprehensive impact of evaluation factors on rockfall.…”

Section: Introductionmentioning

confidence: 99%

Susceptibility Assessment of Rockfall in Karst Regions based on Information Entropy and Multi-Model Coupling

Xie,

Peng,

et al. 2023

Preprint

View full text Add to dashboard Cite

Rockfall is one of the primary geological hazards in karst regions. In order to study the susceptibility distribution patterns of rockfall disasters in karst areas, the research areain Xincheng County is selected in this study and data are collected at 172 historical rockfall points under different geological environments. Various factors, including aspect, slope, elevation, terrain relief, plan curvature, profile curvature, landform type, roughness, coefficient of variation, lithology, fault distance, rainfall, distance to rivers, NDVI (Normalized Difference Vegetation Index), and distance to roads, are employed to construct four coupling models, e.g. IV-RF, IV-CHAID, IV-MLP and IV-SVM. Through comparative analysis of the accuracy and reliability of these models, the optimal evaluation model is determined. The results indicate the corresponding AUC (Area Under the Curve) values for the four models, IV-MLP, IV-CHAID, IV-RF, and IV-SVM, are 0.854, 0.86, 0.862, and 0.888, respectively. For prediction of rockfall in karst areas, rainfall, profile curvature, and coefficient of variation are identified as the most significant factors, accounting for 21%, 18%, and 11%, respectively. These factors indirectly promote water movement in karst areas, consequently influencing rockfall occurrences.

show abstract

Landslide Susceptibility Mapping Based on Interpretable Machine Learning from the Perspective of Geomorphological Differentiation

Cited by 30 publications

References 65 publications

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Remote Sensing and GIS in Landslide Management: An Example from the Kravarsko Area, Croatia

Susceptibility Assessment of Rockfall in Karst Regions based on Information Entropy and Multi-Model Coupling

Contact Info

Product

Resources

About