A Graph–Transformer Method for Landslide Susceptibility Mapping DOI Creative Commons
Zhang Qing, Yi He, Yalei Zhang

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 14556 - 14574

Published: Jan. 1, 2024

Landslide susceptibility mapping (LSM) is of great significance for regional land resource planning and disaster prevention reduction. The machine learning (ML) method has been widely used in the field LSM. However, existing LSM model fails to consider correlation between landslide disaster-prone environment (DPE) lacks global information, resulting a high false alarm rate Therefore, we propose an with GraphTransformer that considers DPE characteristics information. Firstly, analysis importance are employed on nine contributing factors (LCFs), dataset generated by combining remote sensing image interpretation verification. Secondly, graph constrained similarity relationship constructed realize DPE. Then, Transformer module introduced construct Graph-Transformer Finally, analyzed, accuracy proposed compared evaluated. experimental results show effectively improves models weakens influence environmental differences models. Compared convolutional network (GCN), sample aggregate (GraphSAGE), attention (GAT) models, AUC value more than 2.05% higher under relationship. In addition, 8.8% traditional ML conclusion, our framework can get better evaluation most methods, its provide effective ways key technical support investigation control

Language: Английский

Landslide susceptibility assessment using information quantity and machine learning integrated models: a case study of Sichuan province, southwestern China DOI

Pengtao Zhao,

Ying Wang, Yi Xie

et al.

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(2)

Published: Jan. 18, 2025

Language: Английский

Citations

1
Optimizing landslide susceptibility mapping using integrated forest by penalizing attributes model with ensemble algorithms DOI
Wei Chen, Chao Wang, Xia Zhao

et al.

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(2)

Published: Feb. 1, 2025

Language: Английский

Citations

0
Landslide Susceptibility Assessment Using the Geographical-Optimal-Similarity Model DOI Creative Commons
Yonghong Xiao, Guolong Li, Wei Lu

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1843 - 1843

Published: Feb. 11, 2025

As a critical predisaster warning tool, landslide susceptibility assessment is crucial in disaster prevention and mitigation efforts. However, earlier methods for assessing have often ignored the impact of similarities geographical attributes, restricting their feasibility regions with diverse characteristics. The geographical-optimal-similarity (GOS) model effectively captures similarity relations within geospatial data can isolate region-specific features, thus overcoming this challenge. Consequently, method was developed by integrating information value (IV) GOS model. Huangshan City Anhui Province, China, selected as study region. This research used 11 remote sensing feature factors 657 historical points, combined IV model, to construct dataset prediction using findings indicate that, compared conventional such random forest, logistic regression, radial basis function classifier, enhances area under curve (AUC) 2.81% 8.92%, reaching 0.846. demonstrates superior performance confirms effectiveness accuracy assessment. Furthermore, basic-configuration-similarity (BCS) increases AUC 9.64%, achieving approach substantially diminishes effects accuracy, revealing upgraded applicability evaluations. Landslides are primarily influenced rainfall vegetation cover. High-susceptibility zones predominantly located areas high precipitation low In contrast, low-susceptible non-susceptible found flat cover farther from fault lines. majority region lies landslide-prone zones, comprising only 12.43% total area. Historical landslides largely concentrated moderate- high-susceptibility accounting 92.24% all occurrences. Landslide density level, 0.15 per square kilometre zones. brings forward reliable strategy establishing spatial relationship between attribute susceptibility, bolstering method’s adaptability across various regions.

Language: Английский

Citations

0
Predicting the Spatial Distribution of Geological Hazards in Southern Sichuan, China, Using Machine Learning and ArcGIS DOI Creative Commons
Ruizhi Zhang,

Dayong Zhang,

Bo Shu

et al.

Land, Journal Year: 2025, Volume and Issue: 14(3), P. 577 - 577

Published: March 10, 2025

Geological hazards in Southern Sichuan have become increasingly frequent, posing severe risks to local communities and infrastructure. This study aims predict the spatial distribution of potential geological using machine learning models ArcGIS-based analysis. A dataset comprising 2700 known hazard locations Yibin City was analyzed extract key environmental topographic features influencing susceptibility. Several were evaluated, including random forest, XGBoost, CatBoost, with model optimization performed Sparrow Search Algorithm (SSA) enhance prediction accuracy. produced high-resolution susceptibility maps identifying high-risk zones, revealing a distinct pattern characterized by concentration mountainous areas such as Pingshan County, Junlian Gong while plains exhibited relatively lower risk. Among different types, landslides found be most prevalent. The results further indicate strong overlap between predicted zones existing rural settlements, highlighting challenges resilience these areas. research provides refined methodological framework for integrating geospatial analysis prediction. findings offer valuable insights land use planning mitigation strategies, emphasizing necessity adopting “small aggregations multi-point placement” approach settlement Sichuan’s regions.

Language: Английский

Citations

0
Geospatial SHAP interpretability for urban road collapse susceptibility assessment: a case study in Hangzhou, China DOI Creative Commons

Bofan Yu,

Hui Li, Huaixue Xing

et al.

Geomatics Natural Hazards and Risk, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 15, 2025

Language: Английский

Citations

0
Stacking Ensemble Technique Using Optimized Machine Learning Models with Boruta–XGBoost Feature Selection for Landslide Susceptibility Mapping: A Case of Kermanshah Province, Iran DOI Creative Commons

Zeynab Yousefi,

Ali Asghar Alesheikh,

Ali Jafari

et al.

Information, Journal Year: 2024, Volume and Issue: 15(11), P. 689 - 689

Published: Nov. 2, 2024

Landslides cause significant human and financial losses in different regions of the world. A high-accuracy landslide susceptibility map (LSM) is required to reduce adverse effects landslides. Machine learning (ML) a robust tool for LSM creation. ML models require large amounts data predict landslides accurately. This study has developed stacking ensemble technique based on optimization enhance accuracy an while considering small datasets. The Boruta–XGBoost feature selection was used determine optimal combination features. Then, intelligent accurate analysis performed prepare using dynamic hybrid approach Adaptive Fuzzy Inference System (ANFIS), Extreme Learning (ELM), Support Vector Regression (SVR), new algorithms (Ladybug Beetle Optimization [LBO] Electric Eel Foraging [EEFO]). After model optimization, weight combine outputs increase reliability LSM. combinations were optimized LBO EEFO. Root Mean Square Error (RMSE) Area Under Receiver Operating Characteristic Curve (AUC-ROC) parameters assess performance these models. dataset from Kermanshah province, Iran, 17 influencing factors evaluate proposed approach. Landslide inventory 116 points, combined Voronoi entropy method applied non-landslide point sampling. results showed higher with EEFO AUC-ROC values 94.81% 94.84% RMSE 0.3146 0.3142, respectively. can help managers planners reliable LSMs and, as result, associated events.

Language: Английский

Citations

3
A Graph–Transformer Method for Landslide Susceptibility Mapping DOI Creative Commons
Zhang Qing, Yi He, Yalei Zhang

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 14556 - 14574

Published: Jan. 1, 2024

Landslide susceptibility mapping (LSM) is of great significance for regional land resource planning and disaster prevention reduction. The machine learning (ML) method has been widely used in the field LSM. However, existing LSM model fails to consider correlation between landslide disaster-prone environment (DPE) lacks global information, resulting a high false alarm rate Therefore, we propose an with GraphTransformer that considers DPE characteristics information. Firstly, analysis importance are employed on nine contributing factors (LCFs), dataset generated by combining remote sensing image interpretation verification. Secondly, graph constrained similarity relationship constructed realize DPE. Then, Transformer module introduced construct Graph-Transformer Finally, analyzed, accuracy proposed compared evaluated. experimental results show effectively improves models weakens influence environmental differences models. Compared convolutional network (GCN), sample aggregate (GraphSAGE), attention (GAT) models, AUC value more than 2.05% higher under relationship. In addition, 8.8% traditional ML conclusion, our framework can get better evaluation most methods, its provide effective ways key technical support investigation control

Language: Английский

Citations

2