Assessing the relationship between landslide susceptibility and land cover change using machine learning DOI Open Access

Duy Nguyen Huu,

Tung Vu Cong,

Petre Brețcan

et al.

VIETNAM JOURNAL OF EARTH SCIENCES, Journal Year: 2024, Volume and Issue: unknown

Published: May 2, 2024

Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying landslide occurrence probability within is essential supporting decision-makers or developers establishing effective strategies for reducing damage. This study aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), Bagging (BA) assessing connection land cover change susceptibility Da Lat City, Vietnam. 202 locations 13 potential drivers became input data model. Various statistical indices, root mean square error (RMSE), area under curve (AUC), absolute (MAE), were used evaluate proposed models. Our findings indicate that model was better than other models, as shown by AUC value 0.94, followed LightGBM (AUC=0.91), KNN (AUC=0.87), (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² 30 very high areas. approach can be applied test regions might represent necessary tool use planning reduce landslides.

Language: Английский

Advances in Sand Cat Swarm Optimization: A Comprehensive Study DOI

Ferzat Anka,

Nazim Aghayev

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 3, 2025

Language: Английский

Citations

3
Application of Artificial Intelligence and Remote Sensing for Landslide Detection and Prediction: Systematic Review DOI Creative Commons
Stephen Akosah, Ivan Gratchev, Donghyun Kim

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(16), P. 2947 - 2947

Published: Aug. 12, 2024

This paper systematically reviews remote sensing technology and learning algorithms in exploring landslides. The work is categorized into four key components: (1) literature search characteristics, (2) geographical distribution research publication trends, (3) progress of algorithms, (4) application techniques models for landslide susceptibility mapping, detections, prediction, inventory deformation monitoring, assessment, extraction management. selections were based on keyword searches using title/abstract keywords from Web Science Scopus. A total 186 articles published between 2011 2024 critically reviewed to provide answers questions related the recent advances use technologies combined with artificial intelligence (AI), machine (ML), deep (DL) algorithms. review revealed that these methods have high efficiency detection, hazard mapping. few current issues also identified discussed.

Language: Английский

Citations

9
Comprehensive review of remote sensing integration with deep learning in landslide forecasting and future directions DOI

Nilesh Suresh Pawar,

Kul Vaibhav Sharma

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: March 10, 2025

Language: Английский

Citations

1
Application of hybrid model-based machine learning for groundwater potential prediction in the north central of Vietnam DOI
Huu Duy Nguyen,

Van Hong Nguyen,

Quan Vu Viet Du

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(2), P. 1569 - 1589

Published: Jan. 12, 2024

Language: Английский

Citations

6
Advances in Artificial Rabbits Optimization: A Comprehensive Review DOI

Ferzat Anka,

Nazim Agaoglu,

Sajjad Nematzadeh

et al.

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 7, 2024

Language: Английский

Citations

5
Predictive Analysis of Slope Stability via Metaheuristic Algorithms Helping Neural Networks DOI
Yuqi Su, Ruren Li

Geological Journal, Journal Year: 2025, Volume and Issue: unknown

Published: April 29, 2025

ABSTRACT Attaining a firm slope stability analysis holds eminent importance in civil and geotechnical projects. This study is concerned with the indirect assessment of slopes using improved versions artificial neural networks (ANN). Two novel metaheuristic techniques, namely seeker optimization algorithm (SOA) electromagnetic field (EFO) are employed for optimising ANN that aims at predicting factor safety (FOS). hybrids EFO‐ANN SOA‐ANN, as well single conventional ANN, trained tested valid dataset collected from earlier literature. First, examining input factors showed unit weight material ( γ ) most important one, followed by internal friction ϕ ), average angle β cohesion c height H pore water pressure coefficient r u ). Upon monitoring performance this model stops training after some epochs because divergence solution, whereas issue was resolved EFO SOA hybrid models. Consequently, significant improvements were achieved both testing accuracies. By comparison, while more successful task, SOA‐ANN presented reliable prediction FOS. The competency these models also verified through (a) comparison literature (b) applying them to another real‐world binary stability/failure. An explicit predictive formula derived which recommended convenient approximator FOS analysis.

Language: Английский

Citations

0
Smart Hotspot Detection Using Geospatial Artificial Intelligence: A Machine Learning Approach to Reduce Flood Risk DOI Creative Commons
Seyed M. H. S. Rezvani,

Alexandre Gonçalves,

Maria João Falcão Silva

et al.

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 115, P. 105873 - 105873

Published: Oct. 2, 2024

Language: Английский

Citations

2
Assessing the relationship between landslide susceptibility and land cover change using machine learning DOI Open Access

Duy Nguyen Huu,

Tung Vu Cong,

Petre Brețcan

et al.

VIETNAM JOURNAL OF EARTH SCIENCES, Journal Year: 2024, Volume and Issue: unknown

Published: May 2, 2024

Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying landslide occurrence probability within is essential supporting decision-makers or developers establishing effective strategies for reducing damage. This study aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), Bagging (BA) assessing connection land cover change susceptibility Da Lat City, Vietnam. 202 locations 13 potential drivers became input data model. Various statistical indices, root mean square error (RMSE), area under curve (AUC), absolute (MAE), were used evaluate proposed models. Our findings indicate that model was better than other models, as shown by AUC value 0.94, followed LightGBM (AUC=0.91), KNN (AUC=0.87), (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² 30 very high areas. approach can be applied test regions might represent necessary tool use planning reduce landslides.

Language: Английский

Citations

1