Landslide susceptibility prediction modelling based on semi‐supervised XGBoost model DOI

Qiangqiang Shua,

Hongbin Peng,

Jingkai Li

et al.

Geological Journal, Journal Year: 2024, Volume and Issue: 59(9), P. 2655 - 2667

Published: March 8, 2024

In the process of landslide susceptibility prediction (LSP) modelling, there are some problems in model dataset relating to and non‐landslide samples, such as sample errors, subjective randomness low accuracy selection. order solve above problems, a semi‐supervised machine learning for LSP is innovatively proposed. Firstly, Yanchang County Shanxi Province, China, taken study area. Secondly, frequency ratio values 12 environmental factors (elevation, slope, aspect, etc.) randomly selected twice non‐landslides used form initial datasets. Thirdly, an extreme gradient boosting (XGBoost) adopted training testing datasets, so produce maps (LSMs) which divided into very low, moderate, high levels. Next, samples LSMs with levels excluded improve unlabelled ensure samples. These new obtained reimported XGBoost construct (SSXGBoost) model. Finally, accuracy, kappa coefficient statistical indexes assess performance SSXGBoost models. Results show that has remarkably better than Conclusively, proposed effectively overcomes needs be further improved difficult select accurately.

Language: Английский

Single landslide risk assessment considering rainfall‐induced landslide hazard and the vulnerability of disaster‐bearing body DOI
Faming Huang,

K Y Liu,

Zhiyong Li

et al.

Geological Journal, Journal Year: 2024, Volume and Issue: 59(9), P. 2549 - 2565

Published: May 26, 2024

Quantitative calculation of single landslide risk has great significance for the prevention and treatment landslides, through analysing slope stability under different rainfall recurrence periods. In this study, past 40 years in Xun'wu County China is counted during return periods 10, 20 50 are calculated to form three conditions. Then, Cheng'nan by Geo‐Studio 2007 software, probability occurrence obtained Monte Carlo theory these Next, field investigation employed obtain statistical results buildings personnel affected area landslide. Finally, economic loss casualty conditions calculated. It was demonstrated that: (1) Under conditions, safety factor decreased gradually, rate decrease slower first 3 days faster middle period there still a downward trend after end rain. (2) The were 1.77%, 2.97% 1.61%, respectively. Besides, index highest condition 20‐years period. (3) 122,700‐yuan 4.11 people, 205,900‐yuan 6.89 as well 11,600‐yuan 3.74

Language: Английский

Citations

7
Performance of logistic regression and support vector machine conjunction with the GIS and RS in the landslide susceptibility assessment: Case study in Nakhon Si Thammarat, southern Thailand DOI Creative Commons
Kiattisak Prathom,

C. Sujitapan

Journal of King Saud University - Science, Journal Year: 2024, Volume and Issue: 36(8), P. 103306 - 103306

Published: June 17, 2024

The occurrence of landslides has risen in the past few decades, particularly mountainous regions worldwide, including Nakhon Si Thammarat, southern Thailand. Despite various methods being employed for initial management landslide disasters, none have proven universally effective. goal this research is to create and assess susceptibility maps (LSMs) within area by employing support vector machine (SVM) logistic regression, together with Geographic Information System (GIS) Remote Sensing (RS) techniques. Eleven factors contributing were identified as topographic, environmental, geological influences. 365 aimlessly selected into training (70%) testing (30%) datasets. four LSMs indicated that approximately 13%–20% study exhibit a high corresponding elevation relatively steep slope angles. To evaluate compare LSM models, AUC value dataset 0.977, 0.975, 0.958, 0.967 0.973, 0.969, 0.956, 0.964 SVM radial basis function (rbf) kernel, polynomial deg 2, linear kernel regression respectively. Among these SVMs rbf demonstrated highest prediction rate. However, it requires significant amount time choose best parameters achieving accuracy prediction. In summary, are applicable at regional level enhance hazards.

Language: Английский

Citations

6
A Deep Neural Network Framework for Landslide Susceptibility Mapping by Considering Time-Series Rainfall DOI Creative Commons
Binghai Gao, Yi He, Xueye Chen

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 5946 - 5969

Published: Jan. 1, 2024

Landslide susceptibility mapping (LSM) is of great significance in geohazard early warning and prevention. The existing LSM methods mostly used traditional static landslide conditioning factors (LCFs), which only considered the spatial features single-pixel neighborhoods could not extract time-series dynamic developing landslides, resulting low accuracy insufficient reliability LSM. To solve this problem, study proposes to introduce rainfall based on construct an integrated neural network (TSDNN) model for A convolutional adding time-distributed convolution (TDCNN) a bidirectional long short-term memory (Bi-LSTM) are utilized features, multiscale (MSCNN) LCFs. In study, multicollinearity analysis GeoDetector analyze Multiple evaluation metrics proposed performance. results indicate that overall has improved by introducing factors, area actual predicted more refined. indicates significant advantages TSDNN over models (CNN, MSCNN, random forest (RF)) when processing combined data. This notably evident enhanced 12.9%,10.7%, 11.4% compared CNN, MSCNN RF receiver operating characteristic curve (ROC) analysis, respectively. Moreover, two typical areas containing three recent events validate model. framework considering can provide new ideas key technical support disaster

Language: Английский

Citations

5
Advanced risk assessment framework for land subsidence impacts on transmission towers in salt lake region DOI

Bijing Jin,

Taorui Zeng, Tengfei Wang

et al.

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 177, P. 106058 - 106058

Published: May 2, 2024

Language: Английский

Citations

5
Refined landslide inventory and susceptibility of Weining County, China, inferred from machine learning and Sentinel‐1 InSAR analysis DOI
Xuguo Shi,

Dianqiang Chen,

Jianing Wang

et al.

Transactions in GIS, Journal Year: 2024, Volume and Issue: 28(6), P. 1594 - 1616

Published: June 28, 2024

Abstract Landslides are widely distributed mountainous geological hazards that threaten economic development and people's daily lives. Interferometric synthetic aperture radar (InSAR) with comprehensive coverage high‐precision ground displacement monitoring abilities frequently utilized for regional‐scale active slope detection. Moreover, InSAR measurements characterize dynamics integrated conventional topographic, hydrological, landslide conditioning factors (LCFs) susceptibility mapping (LSM). Weining County in southwest China, complex conditions, steep terrain, frequent tectonic activities, is prone to catastrophic failures. In this study, we refined the inventory of using one ascending descending Sentinel‐1 dataset acquired during 2015–2021 through a small baseline subset (SBAS InSAR) analysis. We then combine LOS from both datasets multidimensional SBAS obtain time series two‐dimensional (2D) displacements kinematics slopes. Hot spot cluster analysis (HCA) was carried out on 2D rate maps highlight clustered deformed areas suppress noisy signals occurred single pixels. Two hundred fifty‐eight landslides (including 71 identified study) used construct 76,412 positive samples LSM. our HCA maps, instead LCFs form an LCF_HCA set feed support vector machine (SVM), Random Forest (RF), extreme Gradient Boosting (XGBoost) Light Gradient‐Boosting Machine (LightGBM) models. A LCF (LCF_CON) (LCF_2D) have also been adapted comparison. The performance tree‐based ensemble methods distinctly outperforms SVM model. meantime, models' performances superior other 2 sets all evaluation metrics. ranks increased compared feature importance analysis, which might lead better models set. With continuous accumulation SAR images, dynamic characteristics can offer us opportunities understand enhance

Language: Английский

Citations

5
Near-surface soil hydrothermal response feedbacks landslide activity and mechanism DOI

Xiao Ye,

Hong‐Hu Zhu,

Bing Wu

et al.

Engineering Geology, Journal Year: 2024, Volume and Issue: 341, P. 107690 - 107690

Published: Aug. 22, 2024

Language: Английский

Citations

5
Integrating Knowledge Graph and Machine Learning Methods for Landslide Susceptibility Assessment DOI Creative Commons

Qirui Wu,

Zhong Xie,

Miao Tian

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(13), P. 2399 - 2399

Published: June 29, 2024

The suddenness of landslide disasters often causes significant loss life and property. Accurate assessment disaster susceptibility is great significance in enhancing the ability accurate prevention. To address problems strong subjectivity selection indicators low efficiency process caused by insufficient application a priori knowledge assessment, this paper, we propose novel framework combing domain graph machine learning algorithms. Firstly, combine unstructured data, extract based on Unified Structure Generation for Universal Information Extraction Pre-trained model (UIE) fine-tuned with small amount labeled data to construct graph. We use Paired Relation Vectors (PairRE) characterize graph, then target area characterization factor recommendation calculating spatial correlation, attribute similarity, Term Frequency–Inverse Document Frequency (TF-IDF) metrics. select optimal feature combination among six typical (ML) models interpretable mapping. Experimental validation analysis are carried out three gorges (TGA), results show effectiveness factors recommended learning, overall accuracy after adding associated reaching 87.2%. methodology proposed research better contribution data-driven susceptibility.

Language: Английский

Citations

4
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

4
Domain Knowledge-Guided Intelligent Recognition of Multi-Type Potential Landslides DOI
Qinghao Liu, Hui Li,

Qing Lan

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: 310, P. 112979 - 112979

Published: Jan. 5, 2025

Language: Английский

Citations

0
Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks DOI Creative Commons
Xiangqi Lei, Hanhu Liu, Zhe Chen

et al.

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: Feb. 19, 2025

Language: Английский

Citations

0