Regional rainfall-induced landslide hazard warning based on landslide susceptibility mapping and a critical rainfall threshold

Geomorphology, Journal Year: 2022, Volume and Issue: 408, P. 108236 - 108236

Published: April 5, 2022

Language: Английский

---

Identifying the essential conditioning factors of landslide susceptibility models under different grid resolutions using hybrid machine learning: A case of Wushan and Wuxi counties, China

CATENA, Journal Year: 2022, Volume and Issue: 217, P. 106428 - 106428

Published: June 22, 2022

Language: Английский

---

Machine learning-based landslide susceptibility assessment with optimized ratio of landslide to non-landslide samples

Gondwana Research, Journal Year: 2022, Volume and Issue: 123, P. 198 - 216

Published: May 25, 2022

Language: Английский

---

Riverside Landslide Susceptibility Overview: Leveraging Artificial Neural Networks and Machine Learning in Accordance with the United Nations (UN) Sustainable Development Goals

Water, Journal Year: 2023, Volume and Issue: 15(15), P. 2707 - 2707

Published: July 27, 2023

Riverside landslides present a significant geohazard globally, posing threats to infrastructure and human lives. In line with the United Nations’ Sustainable Development Goals (SDGs), which aim address global challenges, professionals in field have developed diverse methodologies analyze, assess, predict occurrence of landslides, including quantitative, qualitative, semi-quantitative approaches. With advent computer programs, quantitative techniques gained prominence, computational intelligence knowledge-based methods like artificial neural networks (ANNs) achieving remarkable success landslide susceptibility assessments. This article offers comprehensive review literature concerning utilization ANNs for assessment, focusing specifically on riverside areas, alignment SDGs. Through systematic search analysis various references, it has become evident that emerged as preferred method these assessments, surpassing traditional The application aligns SDGs, particularly Goal 11: Cities Communities, emphasizes importance inclusive, safe, resilient, sustainable urban environments. By effectively assessing using ANNs, communities can better manage risks enhance resilience cities geohazards. While number ANN-based studies modeling grown recent years, overarching objective remains consistent: researchers strive develop more accurate detailed procedures. leveraging power incorporating relevant this survey focuses most commonly employed network mapping, contributing overall SDG agenda promoting development, resilience, disaster risk reduction. integration aims advance our knowledge understanding field. providing insights into effectiveness their research contributes development improved management strategies, planning, resilient face landslides.

Language: Английский

---

Ensemble learning framework for landslide susceptibility mapping: Different basic classifier and ensemble strategy

Geoscience Frontiers, Journal Year: 2023, Volume and Issue: 14(6), P. 101645 - 101645

Published: June 7, 2023

The application of ensemble learning models has been continuously improved in recent landslide susceptibility research, but most studies have no unified framework. Moreover, few papers discussed the applicability model mapping at township level. This study aims defining a robust framework that can become benchmark method for future research dealing with comparison different models. For this purpose, present work focuses on three basic classifiers: decision tree (DT), support vector machine (SVM), and multi-layer perceptron neural network (MLPNN) two homogeneous such as random forest (RF) extreme gradient boosting (XGBoost). hierarchical construction deep relied leading technologies (i.e., homogeneous/heterogeneous bagging, boosting, stacking strategy) to provide more accurate effective spatial probability occurrence. selected area is Dazhou town, located Jurassic red-strata Three Gorges Reservoir Area China, which strategic economic currently characterized by widespread risk. Based long-term field investigation, inventory counting thirty-three slow-moving polygons was drawn. results show do not necessarily perform better; instance, Bagging based DT-SVM-MLPNN-XGBoost performed worse than single XGBoost model. Amongst eleven tested models, Stacking RF-XGBoost model, ensemble, showed highest capability predicting landslide-affected areas. Besides, factor behaviors DT, SVM, MLPNN, RF reflected characteristics landslides reservoir area, wherein unfavorable lithological conditions intense human engineering activities water level fluctuation, residential construction, farmland development) are proven be key triggers. presented approach could used occurrence prediction similar regions other fields.

Language: Английский

---

An updating of landslide susceptibility prediction from the perspective of space and time

Geoscience Frontiers, Journal Year: 2023, Volume and Issue: 14(5), P. 101619 - 101619

Published: April 20, 2023

Due to the similarity of conditioning factors, aggregation feature landslides and multi-temporal landslide inventory, spatial temporal effects need be considered in susceptibility prediction (LSP). The ignorance this issue will result some biases time-invariance susceptibility. Hence, a novel framework has been proposed update by simultaneously considering at regional scale. In framework, inventory Chongyi County divided into pre- fresh-landslide inventories. According LSP results predicted support vector machine (SVM) model using slope unit-based factors pre-landslide normalized distance index (NSDI) is calculated quantitatively represent correlation between surrounding units develop SVM-NSDI model. Furthermore, SVM-Updating model, which incorporates could developed results. Subsequently, confusion matrix, area under receiver operating characteristic curve (AUC) frequency ratio (FR) accuracy are used evaluate performance above models. F1-score values SVM, models 0.776, 0.816 0.831, respectively. AUC 0.869, 0.903 0.914 FR accuracies 0.795, 0.853 0.873. It can concluded that time-variant variable, updated as well inventory. This study provides new over time also more accurate for decision-makers.

Language: Английский

---

Machine-learning based landslide susceptibility modelling with emphasis on uncertainty analysis

Geoscience Frontiers, Journal Year: 2023, Volume and Issue: 14(6), P. 101657 - 101657

Published: June 29, 2023

Landslide susceptibility maps are vital tools used by decision-makers to adopt mitigation strategies for future calamities. In this context, research on landslide modelling has become a topic of relevance and is in constant evolution. Though various machine-learning techniques (MLTs) have been identified modelling, the uncertainty inherent models rarely considered. The present study attempts quantify associated with prediction developing new methodological framework based ensembles eight MLTs. This methodology tested at highlands southern Western Ghats region (Kerala, India), where landslides frequently occurring. Fourteen conditioning factors as part study, their association was correlated 671 historic area. four ensemble such mean probabilities, median weighted committee average. probability proved be best model average 800 standalone MLTs, viz., receiver operating characteristics, true skill statistics, area under curve corresponding validation scores. Thereafter, an analysis carried out coefficient variation. A confident map generated represent distinct zonation areas definite scales. Nearly 74% past fall higher susceptibility-low category. It also inferred that micro-level MLTs may improve efficiency help accurately identifying landslide-prone future. thus can ready reference planners formulation adaptation micro-scales.

Language: Английский

---

Refined and dynamic susceptibility assessment of landslides using InSAR and machine learning models

Geoscience Frontiers, Journal Year: 2024, Volume and Issue: 15(6), P. 101890 - 101890

Published: July 9, 2024

Landslide susceptibility assessment is crucial in predicting landslide occurrence and potential risks. However, traditional methods usually emphasize on larger regions of landsliding rely relatively static environmental conditions, which exposes the hysteresis refined-scale temporal dynamic changes. This study presents an improved approach by integrating machine learning models based random forest (RF), logical regression (LR), gradient boosting decision tree (GBDT) with interferometric synthetic aperture radar (InSAR) technology comparing them to their respective original models. The results demonstrated that combined improves prediction accuracy reduces false negative positive errors. LR-InSAR model showed best performance at both regional smaller scale, particularly when identifying areas high very susceptibility. Modeling were verified using data from field investigations including unmanned aerial vehicle (UAV) flights. great significance accurately assess help reduce prevent risk.

Language: Английский

---

How do the landslide and non-landslide sampling strategies impact landslide susceptibility assessment? — A catchment-scale case study from China

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2024, Volume and Issue: 16(3), P. 877 - 894

Published: Jan. 12, 2024

The aim of this study is to investigate the impacts sampling strategy landslide and non-landslide on performance susceptibility assessment (LSA). area Feiyun catchment in Wenzhou City, Southeast China. Two types landslides samples, combined with seven strategies, resulted a total 14 scenarios. corresponding map (LSM) for each scenario was generated using random forest model. receiver operating characteristic (ROC) curve statistical indicators were calculated used assess impact dataset strategy. results showed that higher accuracies achieved when core as positive from very low zone or buffer zone. reveal influence strategies accuracy LSA, which provides reference subsequent researchers aiming obtain more reasonable LSM. ©2023 Institute Rock Soil Mechanics, Chinese Academy Sciences. Production hosting by Elsevier B.V. This an open access article under CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Language: Английский

---

Advanced integration of ensemble learning and MT-InSAR for enhanced slow-moving landslide susceptibility zoning

Engineering Geology, Journal Year: 2024, Volume and Issue: 331, P. 107436 - 107436

Published: Feb. 9, 2024

Language: Английский

---