Advanced hyperparameter optimization for improved spatial prediction of shallow landslides using extreme gradient boosting (XGBoost)

Bulletin of Engineering Geology and the Environment, Journal Year: 2022, Volume and Issue: 81(5)

Published: April 22, 2022

Language: Английский

---

Landslide Susceptibility mapping using random forest and extreme gradient boosting: A case study of Fengjie, Chongqing

Geological Journal, Journal Year: 2023, Volume and Issue: 58(6), P. 2372 - 2387

Published: Feb. 7, 2023

Landslide susceptibility analysis can provide theoretical support for landslide risk management. However, some analyses are not sufficiently interpretable. Moreover, the accuracy of many research methods needs to be improved. Therefore, this study supplement these deficiencies. This aims evaluation effects random forest (RF) and extreme gradient boosting (XGBoost) classifier models on susceptibility, compare their applicability in Fengjie County, Chongqing, a typical landslide‐prone area southwest China. Firstly, 1624 landslides information from 1980 2020 were obtained through field investigation, geospatial database 16 conditional factors had been constructed. Secondly, non‐landslide points selected form complete data set RF XGBoost established. Finally, under ROC curve (AUC) value, accuracy, F ‐score used two models. The results show that even though both classifiers have highly accurate model performs better. In comparison, has higher AUC value 0.866, its approximately 2% than XGBoost. land use, elevation, lithology County contribute occurrence landslides. is due human engineering activities (such as reclamation, housing construction) resulting low slope stability widely distributed sandstone, siltstone, mudstone layers owing permeability planes weakness.

Language: Английский

---

Landslide susceptibility prediction considering land use change and human activity: A case study under rapid urban expansion and afforestation in China

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 866, P. 161430 - 161430

Published: Jan. 6, 2023

Language: Английский

---

Integrating Machine Learning Ensembles for Landslide Susceptibility Mapping in Northern Pakistan

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(6), P. 988 - 988

Published: March 12, 2024

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

Language: Английский

---

An interpretable model for landslide susceptibility assessment based on Optuna hyperparameter optimization and Random Forest

Geomatics Natural Hazards and Risk, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 11, 2024

This study proposed an interpretable model that combines Random Forest (RF), Optuna hyperparameter optimization, and SHapley Additive exPlanations (SHAP) to achieve optimal landslide susceptibility evaluation provide explanations in the northwest region of Yunnan Province China. First, inventory 4447 landslides 23 related factors was considered for assessment. Subsequently, a hyperparameter-optimized RF developed using framework training dataset generate maps. The performance models were evaluated accuracy (ACC), precision (PPV), recall (TPR), F1-score (F1), Area Under Curve (AUC) based on Receiver Operating Characteristic. Furthermore, interpretability enhanced through implementation SHAP. demonstrated outstanding test set, achieving ACC 0.7792, PPV 0.7448, TPR 0.8769, F1 0.8055, AUC 0.8387. analysis revealed elevation, population density, distance from roads, normalized difference vegetation index primary influencing occurrences area. provides comprehensive evaluating specific regions offers invaluable insights prevention management disasters.

Language: Английский

---

Assessment of groundwater potential modeling using support vector machine optimization based on Bayesian multi-objective hyperparameter algorithm

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 132, P. 109848 - 109848

Published: Nov. 25, 2022

Language: Английский

---

Landslide Susceptibility Assessment Model Construction Using Typical Machine Learning for the Three Gorges Reservoir Area in China

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(9), P. 2257 - 2257

Published: May 7, 2022

The Three Gorges Reservoir region in China is the Yangtze River Economic Zone’s natural treasure trove. Its environment has an important role development. unique and fragile ecosystem River’s prone to disasters, including soil erosion, landslides, debris flows, earthquakes. Therefore, better alleviate these threats, accurate comprehensive assessment of susceptibility this area required. In study, based on collection relevant data existing research results, we applied machine learning models, logistic regression (LR), random forest model (RF), support vector (SVM) model, analyze landslide events whole study region. models identified five categories (i.e., topographic, geological, ecological, meteorological, human engineering activities), with nine independent variables, influencing susceptibility. accuracy derived from different raster cells was then verified by accuracy, recall, F1-score, ROC curve, AUC each model. results illustrate that algorithms ranked as SVM > RF LR. LR lowest generalization ability. performs well all regions area, value 0.9708 for entire indicating possesses a strong spatial ability highest robustness can be adapted real-time assessing regional

Language: Английский

---

Tempo-Spatial Landslide Susceptibility Assessment from the Perspective of Human Engineering Activity

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(16), P. 4111 - 4111

Published: Aug. 21, 2023

The expansion of mountainous urban areas and road networks can influence the terrain, vegetation, material characteristics, thereby altering susceptibility landslides. Understanding relationship between human engineering activities landslide occurrence is great significance for both prevention land resource management. In this study, an analysis was conducted on caused by Typhoon Megi in 2016. A representative area along eastern coast China—characterized development, deforestation, severe expansion—was used to analyze spatial distribution For purpose, high-precision Planet optical remote sensing images were obtain inventory related event. main innovative features are as follows: (i) newly developed patch generating land-use simulation (PLUS) model simulated analyzed driving factors land-cover (LULC) from 2010 2060; (ii) stacking strategy combined three strong ensemble models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Machine (LightGBM)—to calculate susceptibility; (iii) distance LULC maps short-term long-term dynamic examine impact susceptibility. results show that maximum built-up 2020 13.433 km2, mainly expanding forest cropland land, with 8.28 km2 5.99 respectively. predicted map 2060 shows a growth 45.88 distributed around government residences relatively flat terrain frequent socio-economic activities. factor contribution has higher than LULC. Stacking RF-XGB-LGBM obtained optimal AUC value 0.915 Furthermore, future network have intensified probability landslides occurring 2015. To our knowledge, first application PLUS models international literature. research serve foundation developing management guidelines reduce risk failures.

Language: Английский

---

Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(15), P. 3901 - 3901

Published: Aug. 7, 2023

Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly accurately is basis disaster prevention. Fengjie County, Chongqing, China, a typical landslide-prone area Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme (XGBoost), Light Machine (LightGBM), (AdaBoost). We construct new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, SHAP-OPT-AdaBoost) apply to extraction for first time. Firstly, high-resolution remote sensing images were preprocessed, non-landslide samples constructed, an initial feature set with 48 features was built. Secondly, SHAP used select contributions, important selected. Finally, Optuna, Bayesian optimization technique, utilized automatically models’ best hyperparameters. The experimental results show that accuracy (ACC) these SHAP-OPT above 92% training time less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved highest (96.26%). Landslide distribution County from 2013 2020 can be extracted by quickly.

Language: Английский

---

An innovative approach for predicting groundwater TDS using optimized ensemble machine learning algorithms at two levels of modeling strategy

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 351, P. 119896 - 119896

Published: Jan. 3, 2024

Language: Английский

---