Qisen Jin^1,2, Xiaoping Wang¹, Feng Zhang², Yu Zeng², Jia Guo^3,4,5,*, Jiacheng Li^6,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.080077 - 13 August 2026

Abstract This paper presents a Sine-Lucas Oscillation Particle Swarm Optimization (SLOPSO) XGBoost algorithm for landslide susceptibility prediction. SLOPSO extends canonical PSO by introducing an oscillation factor constructed from a sine function and the Lucas number sequence into the position update, which raises swarm diversity and improves the global search. SLOPSO is then applied to tune six XGBoost hyperparameters using K-fold cross-validation accuracy as the fitness function. In experimental evaluation, SLOPSO-XGBoost reaches a mean test Accuracy of 0.8113, F1 of 0.8182, and AUC of 0.8856 over 10 independent runs, outperforming standard PSO-XGBoost and the default Random Forest, More >

Jerome Gacu^1,2,*, Dencel Edrian Cawaling¹, Edel Queen Fiestada¹, Diablell Maybanting¹, Jamica Bensurto¹, John Kevin Falogme¹, Jea Janelle Fontamillas¹, Janellene Edd Gadon¹, Samaica Fernandez¹, Maryjay Sagario³

Revue Internationale de Géomatique, Vol.35, pp. 373-407, 2026, DOI:10.32604/rig.2026.083180 - 18 June 2026

Abstract A landslide is the downslope movement of soil, rock, or debris driven by gravity, often triggered by natural or anthropogenic factors. The Philippines is highly susceptible to landslides due to its steep terrain, frequent typhoons, intense rainfall, and seismic activity, resulting in significant socioeconomic and environmental impacts. Despite increasing landslide occurrences in vulnerable coastal and mountainous municipalities in the Philippines, localized and integrated Geographic Information System (GIS)-based landslide risk assessments incorporating hazard, vulnerability, and exposure components remain limited in small island municipalities such as San Andres, Romblon. This study assesses landslide risk in the Municipality… More >

Md Minhazul Islam^1,2, Yunfei Yin^1,2,*, Md Tanvir Islam^1,2, Zheng Yuan^1,2, Argho Dey^1,2

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072550 - 12 January 2026

Abstract Automatic segmentation of landslides from remote sensing imagery is challenging because traditional machine learning and early CNN-based models often fail to generalize across heterogeneous landscapes, where segmentation maps contain sparse and fragmented landslide regions under diverse geographical conditions. To address these issues, we propose a lightweight dual-stream siamese deep learning framework that integrates optical and topographical data fusion with an adaptive decoder, guided multimodal fusion, and deep supervision. The framework is built upon the synergistic combination of cross-attention, gated fusion, and sub-pixel upsampling within a unified dual-stream architecture specifically optimized for landslide segmentation, enabling efficient… More >

Izzah Liyanamadihah Ibrahim¹, Nurhanisah Hashim^1,*, Ainon Nisa Othman^1,*, Noorfatekah Talib², Sarah Shaharuddin³

Revue Internationale de Géomatique, Vol.34, pp. 915-937, 2025, DOI:10.32604/rig.2025.072321 - 09 December 2025

Abstract This study aims to assess landslide susceptibility in Hulu Selangor, Selangor, Malaysia, an area that is exposed to rapid industrial and infrastructural growth. Six conditioning factors, such as slope, land use, lithology, road proximity, and river proximity, were integrated through the Analytic Hierarchy Process (AHP) in a GIS environment. The weights distribution analysis revealed slope (40.50%) and lithology (23.12%) as the most important factors, followed by river proximity (15.09%) and road proximity (13.76%). The developed susceptibility map was divided into five zones: very low (12.4%), low (18.7%), medium (35.6%), high (22.1%), and very high (11.2%).… More >

Jiao Chen¹, Xiao Wang^1,*, Zhiqin He¹, Yi Chen², Chao Ma¹

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5423-5450, 2025, DOI:10.32604/cmc.2025.067952 - 23 October 2025

Abstract This research proposes an innovative solution to the inherent challenges faced by landslide displacement prediction models based on data-driven methods, such as the need for extensive historical datasets for training, the reliance on manual feature selection, and the difficulty in effectively utilizing landslide historical data. We have developed a dual-channel deep learning prediction model that integrates multimodal decomposition and an attention mechanism to overcome these challenges and improve prediction performance. The proposed methodology follows a three-stage framework: (1) Empirical Mode Decomposition (EMD) effectively segregates cumulative displacement and feature factors; (2) We have developed a Double… More >

Nurul A. Asram¹, Eran S. S. Md Sadek^2,*

Revue Internationale de Géomatique, Vol.34, pp. 619-637, 2025, DOI:10.32604/rig.2025.065667 - 06 August 2025

Abstract Landslides are a frequent geomorphological hazard in tropical regions, particularly where steep terrain and high precipitation coincide. This study evaluates landslide susceptibility in the Jelapang area of Perak, Malaysia, using Shannon Entropy-weighted bivariate models (i.e., Frequency Ratio, Information Value, and Weight of Evidence), in comparison with Logistic Regression. Seven conditioning factors were selected based on their geomorphological relevance and tested for multicollinearity: slope gradient, slope aspect, curvature, vegetation cover, lineament density, terrain ruggedness index, and flow accumulation. Each model generated susceptibility maps, which were validated using Receiver Operating Characteristic curves and Area Under the Curve… More >

Naveen Chandra¹, Himadri Vaidya^2,3, Suraj Sawant⁴, Shilpa Gite^5,6, Biswajeet Pradhan^7,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 3351-3375, 2025, DOI:10.32604/cmes.2025.064395 - 30 June 2025

Abstract Landslide hazard detection is a prevalent problem in remote sensing studies, particularly with the technological advancement of computer vision. With the continuous and exceptional growth of the computational environment, the manual and partially automated procedure of landslide detection from remotely sensed images has shifted toward automatic methods with deep learning. Furthermore, attention models, driven by human visual procedures, have become vital in natural hazard-related studies. Hence, this paper proposes an enhanced YOLOv5 (You Only Look Once version 5) network for improved satellite-based landslide detection, embedded with two popular attention modules: CBAM (Convolutional Block Attention Module) More >

Duc-Dam Nguyen¹, Nguyen Viet Tiep^2,*, Quynh-Anh Thi Bui¹, Hiep Van Le¹, Indra Prakash³, Romulus Costache^4,5,6,7, Manish Pandey^8,9, Binh Thai Pham¹

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.1, pp. 467-500, 2025, DOI:10.32604/cmes.2024.056576 - 17 December 2024

Abstract This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand, India, using advanced ensemble models that combined Radial Basis Function Networks (RBFN) with three ensemble learning techniques: DAGGING (DG), MULTIBOOST (MB), and ADABOOST (AB). This combination resulted in three distinct ensemble models: DG-RBFN, MB-RBFN, and AB-RBFN. Additionally, a traditional weighted method, Information Value (IV), and a benchmark machine learning (ML) model, Multilayer Perceptron Neural Network (MLP), were employed for comparison and validation. The models were developed using ten landslide conditioning factors, which included slope, aspect, elevation, curvature, land cover, geomorphology,… More >

Maan Habib^1,*, Ahed Habib², Mohammad Abboud³

Revue Internationale de Géomatique, Vol.33, pp. 247-271, 2024, DOI:10.32604/rig.2024.053857 - 07 August 2024

Abstract Digital elevation models (DEMs) are essential tools in environmental science, particularly for hazard assessments and landscape analyses. However, their application across multiple environmental hazards simultaneously remains in need for a multi-aspect critical assessment to promote their effectiveness in comprehensive risk management. This paper aims to review and critically assess the application of DEMs in mapping and managing specific environmental hazards, namely floods, landslides, and coastal erosion. In this regard, it seeks to promote their utility of hazard maps as key tools in disaster risk reduction and environmental planning by employing high-resolution DEMs integrated with advanced More >

Shiwei Zhao^1,*, Hao Chen², Jidong Zhao¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.25, No.2, pp. 1-1, 2023, DOI:10.32604/icces.2023.09965

Abstract With global warming, thaw-induced landslides occur more frequently in permafrost, which not only threaten the safety of infrastructures as general geohazards but also worsen global warming due to carbon release. This work presents a novel computational framework to model thaw-induced landslides from a multiscale perspective. The proposed approach can capture the thermal-mechanical (TM) response of frozen soils at the particulate scale by using discrete element method (DEM). The micromechanics-based TM model is superior to capturing the sudden crash of soil skeletons caused by thaw-induced cementation loss between soil grains. The DEM-simulated TM response is then More >