Improving landslide susceptibility prediction through ensemble Recursive Feature Elimination and meta-learning framework DOI Creative Commons

Krishnagopal Halder,

Amit Kumar Srivast,

Anitabha Ghosh

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Март 8, 2024

Abstract Landslides pose significant threats to local ecological environments, causing loss of life and economic damage. This research focuses on enhancing landslide susceptibility prediction in West Bengal's Sub-Himalayan region using an innovative ensemble Recursive Feature Elimination (RFE) meta-learning framework. Seven advanced machine learning models- Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extremely Randomized Trees (ExtraTrees), Gradient Boosting (GB), Extreme (XGBoost), Meta Classifier (MC) - were utilized alongside Remote Sensing Geographic Information System techniques. Through feature selection, the identifies most conditioning factors. Evaluation metrics, including accuracy AUC ROC curve, demonstrate ensemble's superior predictive ability. Based findings, models perform well with LR (AUC = 0.935), SVM 0.972), RF 0.983), ExtraTrees 0.985), GB 0.987), XGBoost 0.987). However, MC performed better than individual 0.987. The study's implications for land-use planning disaster management are discussed by establishing a new benchmark mapping, this offers promising approach addressing similar environmental challenges worldwide, facilitating informed decision-making mitigation efforts geologically sensitive areas.

Язык: Английский

Improving landslide susceptibility prediction through ensemble recursive feature elimination and meta-learning framework DOI Creative Commons

Krishnagopal Halder,

Amit Kumar Srivastava,

Anitabha Ghosh

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 12, 2025

Abstract Landslides pose significant threats to ecosystems, lives, and economies, particularly in the geologically fragile Sub-Himalayan region of West Bengal, India. This study enhances landslide susceptibility prediction by developing an ensemble framework integrating Recursive Feature Elimination (RFE) with meta-learning techniques. Seven advanced machine learning models- Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting (GB), Extreme (XGBoost), a Meta Classifier (MC) were applied using Remote Sensing GIS tools identify key landslide-conditioning factors classify zones. Model performance was assessed through metrics such as accuracy, precision, recall, F1 score, AUC ROC curve. Among models, achieved highest accuracy (0.956) (0.987), demonstrating superior predictive ability. XGBoost, RF also performed well, accuracies 0.943 values 0.987 (GB XGBoost) 0.983 (RF). (ET) exhibited (0.946) among individual models 0.985. SVM LR, while slightly less accurate (0.941 0.860, respectively), provided valuable insights, achieving 0.972 LR 0.935. The effectively delineated into five zones (very low, moderate, high, very high), high concentrated Darjeeling Kalimpong subdivisions. These are influenced intense rainfall, unstable geological structures, anthropogenic activities like deforestation urbanization. Notably, ET, RF, GB, XGBoost demonstrated efficiency feature selection, requiring fewer input variables maintaining performance. establishes benchmark for mapping, providing scalable adaptable geospatial hazard prediction. findings hold implications land-use planning, disaster management, environmental conservation vulnerable regions worldwide.

Язык: Английский

Процитировано

3
Flood risk modelling by the synergistic approach of machine learning and best-worst method in Indus Kohistan, Western Himalaya DOI Creative Commons
Ashfaq Ahmad, Jiangang Chen, Xiaohong Chen

и другие.

Geomatics Natural Hazards and Risk, Год журнала: 2025, Номер 16(1)

Опубликована: Фев. 25, 2025

Язык: Английский

Процитировано

1
A physics-informed machine learning solution for landslide susceptibility mapping based on three-dimensional slope stability evaluation DOI
Yunhao Wang, Luqi Wang, Wengang Zhang

и другие.

Journal of Central South University, Год журнала: 2024, Номер unknown

Опубликована: Авг. 5, 2024

Язык: Английский

Процитировано

8
Identifying potential debris flow hazards after the 2022 Mw 6.8 luding earthquake in southwestern China DOI
Ming Chen, Ming Chang,

Qiang Xu

и другие.

Bulletin of Engineering Geology and the Environment, Год журнала: 2024, Номер 83(6)

Опубликована: Май 20, 2024

Язык: Английский

Процитировано

6
Investigating the dynamic nature of landslide susceptibility in the Indian Himalayan region DOI
Ankur Sharma, Har Amrit Singh Sandhu

Environmental Monitoring and Assessment, Год журнала: 2024, Номер 196(3)

Опубликована: Фев. 13, 2024

Язык: Английский

Процитировано

4
Spatiotemporal dynamics of landslide susceptibility under future climate change and land use scenarios DOI Creative Commons
Kashif Ullah, Yi Wang, Penglei Li

и другие.

Environmental Research Letters, Год журнала: 2024, Номер 19(12), С. 124016 - 124016

Опубликована: Окт. 23, 2024

Abstract Mountainous landslides are expected to worsen due environmental changes, yet few studies have quantified their future risks. To address this gap, we conducted a comprehensive analysis of the eastern Hindukush region Pakistan. A geospatial database was developed, and logistic regression employed evaluate baseline landslide susceptibility for 2020. Using latest coupled model intercomparison project 6 models under three shared socioeconomic pathways (SSPs) cellular automata-Markov model, projected rainfall land use/land cover patterns 2040, 2070, 2100, respectively. Our results reveal significant changes in use patterns, particularly long-term (2070 2100). Future then predicted based on these projections. By high-risk areas increase substantially all SSP scenarios, with largest increases observed SSP5-8.5 (56.52%), SSP2-4.5 (53.55%), SSP1-2.6 (22.45%). will rise by 43.08% (SSP1-2.6), 40.88% (SSP2-4.5), 12.60% (SSP5-8.5). However, minimal compared baseline, 9.45% 1.69% 7.63% These findings provide crucial insights into relationship between risks support development climate risk mitigation, planning, disaster management strategies mountainous regions.

Язык: Английский

Процитировано

4
Landslide Susceptibility Mapping in Complex Topo‐Climatic Himalayan Terrain, India Using Machine Learning Models: A Comparative Study of XGBoost, RF and ANN DOI Creative Commons
Shubham Badola, Manish Pandey, Varun Narayan Mishra

и другие.

Geological Journal, Год журнала: 2025, Номер unknown

Опубликована: Март 20, 2025

ABSTRACT Landslides present a significant danger to both infrastructure and human lives in the challenging terrain of Himalayas. Therefore, it is crucial accurately map areas prone landslides facilitate informed decision‐making proactive planning, allowing for effective management this hazard. Since landslide occurrences are accentuated by floods through toe erosion, wildfires research aims integrate machine learning techniques with analysis multiple hazards, such as forest fires, novel conditioning factors create comprehensive susceptibility. Geospatial was conducted examine relationship between 19 elements, including related flood fire susceptibility, which contribute occurrence landslides. This study tested efficacy three models mapping landslide‐prone areas: eXtreme Gradient Boost (XGBoost), Random Forest (RF) Artificial Neural Network (ANN). These can identify complex correlations patterns among resulting more accurate regions A regression performed evaluate multicollinearity confirm association dependent independent variables. The revealed variance inflation factor within acceptable bounds, providing validation correlation. ROC–AUC curve approach used assess models' accuracy. Among tested, XGB exhibited highest accuracy at 94%, followed RF 92% ANN 77%. results offer insightful information about how combine data from various hazard forecast work be instrumental local authorities disaster organisations prioritising resources, implementing mitigation plans enhancing resilience against threats.

Язык: Английский

Процитировано

0
A modeling framework for assessing the future changes in the occurrence of extreme rain-induced landslides DOI
Xinlong Zhang, Qigen Lin,

Manhoi Lok

и другие.

Gondwana Research, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Microgrids Efficiency Improvement for National Electricity Network Leveraging Beluga Whale Optimization DOI Creative Commons

Dianzuo Li,

Wei Feng,

Mohammadreza Fathi

и другие.

Heliyon, Год журнала: 2024, Номер unknown, С. e30018 - e30018

Опубликована: Апрель 1, 2024

Managing of real-time energy in microgrids connected to grid is a relatively new technology that becoming increasingly popular the industry. It enables connect with each other and wider electrical increase efficiency improve resiliency while reducing costs emissions. also grid-connected dynamically adjust changing conditions, allowing for upgraded infrastructure improved security. However, identifying an accurate efficient approach management critical. In this regards, paper introduces modified metaheuristic, Boosted Beluga Whale Optimizer (BBWO), application optimize battery controlling CM (community microgrid). This amendment involves changes cost function so it better captures charging/discharging operations. A dynamic penalty then suggested sake further improves function. The effectiveness determined through case study, operational over 96h time horizon. From results, battery's cycles provides lower expenses $29.70 96-hour Further, proposed innovative encourages optimal charging from RESs utility could reduce objective significantly. was demonstrated constantly trying maintain full charge, which requires expenditure $33.14 electricity. still less than original cost, but allows high levels be maintained across all periods. Additionally, prevents any issues stemming low maximizes life battery. Overall, regularized BBWO algorithm, offered adapted needs society, suitable solution management.

Язык: Английский

Процитировано

3
Predicting urban landslides in the hilly regions of Bangladesh leveraging a hybrid machine learning model and CMIP6 climate projections DOI Creative Commons
Md Ashraful Islam,

Musabbir Ahmed Arrafi,

Mehedi Hasan Peas

и другие.

Geosystems and Geoenvironment, Год журнала: 2025, Номер unknown, С. 100354 - 100354

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0