Unraveling the evolution of landslide susceptibility: a systematic review of 30-years of strategic themes and trends

Dong, Aonan; Dou, Jie; Fu, Yonghu; Zhang, Ruiqi; Xing, Ke

doi:10.1080/10106049.2023.2256308

Cited by 9 publications

(3 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSA indicates the landslide-prone areas that can be used by policy-makers, and general public to avoid catastrophic landslides. It represents a fundamental step toward assessing landslide hazards and developing mitigation strategies (Dong et al, 2023). Therefore, conducting landslide susceptibility modeling and mapping research is essential.…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Analysis and Hazard Zonation in Nuwakot District, Nepal

Karna

2024

J. Geoinformatics, Nep.

View full text Add to dashboard Cite

Landslide mostly occurred in highly rugged topography, erosional steeply sloping land form and fragile geological structural in mountainous region. Landslide susceptibility describe the likelihood relation of occurring landslide in an area controlled with their local terrain condition. Landslide susceptibility analysis (LSA) work is used to determine the spatial distribution of landslides prone area and applicable to predict the future landslides occurrences, which is vital for averting and mitigating regional landslide disasters. LSA. In this study, LSA is carried with the bivariate analysis incorporating twelve causative factors of landslide. The frequency ratio (FR) technique were used for computing the relative frequency (RF) as priority rank and entropy index (E) as weight of causative factor. Result of LSA shows that the probability of occurring landslides is 80 percent, with 27 percent of that risk being high risk, 38 percent being medium risk, and 15 percent being low risk. The prediction accuracy of the model is 87.89 percent, showing reliable and satisfactorily validation rates with good accuracy. So, the present study demonstrates that the quantitative assessment methods explored may have a promising potential for landslide assessment and prediction in the high hill and Himalaya regions.

show abstract

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Analysis and Hazard Zonation in Nuwakot District, Nepal

Karna

2024

J. Geoinformatics, Nep.

View full text Add to dashboard Cite

show abstract

“…A commonly used ML algorithm in landslide susceptibility and hazard mapping is the Random Forest (RF) (e.g. Stumpf and Kerle 2011;Zhang et al 2020;Liu et al 2022;Dong et al 2023). In comparison with other ML algorithms, it also yields satisfying results (e.g.…”

Section: Introductionmentioning

confidence: 99%

A modular framework for FAIR shallow landslide susceptibility mapping based on machine learning

Edrich,

Yildiz,

Roscher

et al. 2024

Preprint

View full text Add to dashboard Cite

Machine learning has grown in popularity in the past few years for susceptibility and hazard mapping tasks. Necessary steps for the generation of a susceptibility or hazard map are repeatedly implemented in new studies. We present a Random Forest classifier-based landslide susceptibility and hazard mapping framework to facilitate future mapping studies using machine learning. The framework, as a piece of software, follows the FAIR paradigm, and hence is set up as a transparent, reproducible and modularly extensible workflow. It contains pre-implemented steps from conceptualisation to map generation, such as the generation of input datasets. The framework can be applied to different areas of interest using different environmental features and is also flexible in terms of the desired scale and resolution of the final map. To demonstrate the functionality and validity of the framework, and to explore the challenges and limitations of Random Forest-based susceptibility and hazard mapping, we apply the framework to a test case. This test case conveys the influence of the training dataset on the generated susceptibility maps in terms of feature combination, influence of non-landslide instances and representativeness of the training data with respect to the area of interest. A comparison of the test case results with the literature shows that the framework works reliably. Furthermore, the results obtained in this study complement the findings of previous studies that demonstrate the sensitivity of the training process to the training data, particularly in terms of its representativeness.

show abstract

“…Applied models can be grouped into four categories: physical, heuristic, statistical, and machine learning [19]. Physical models require accurate site characterization and are more suitable for slope-scale analysis and mapping [20]. Heuristic methods mostly rely on expert knowledge and expertise, focusing on the importance of the field survey to prevent statistic bias, and can be used in areas where detailed geotechnical information and/or reliable, accurate, and complete landslide inventories are missing [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Rockfall Susceptibility Assessment and Landscape Evolution of San Nicola Island (Tremiti Islands, Southern Adriatic Sea, Italy)

Cinosi,

Piattelli,

Paglia

et al. 2023

Geosciences

View full text Add to dashboard Cite

San Nicola Island, pertaining to the Tremiti Archipelago (Southern Adriatic Sea, Italy), is widely affected by cliff retreat and gravitational phenomena which severely threaten its monumental historical and natural value. In this study, geomorphological features of the area were derived following a stepwise approach, combining multitemporal stereoscopic aerial photo interpretations with morphometric analyses and detailed field surveys. A rockfall susceptibility map was created following a heuristic approach based on morphometric and geothematic parameters, accounting for slope, slope aspect, outcropping lithologies, structural discontinuities density, distance from landslide scarps, and presence of anthropic caves. Cliff sectors set on dolomitic limestones feature the highest susceptibility values, especially along the southeastern sector; medium values, instead, are found along the island flanks and along scarps located within the inner sectors; and the lowest values are detected on summit tabular surfaces. The achieved results were compared with historical maps and seismic data derived from local and national archives and catalogues, respectively. These analyses allowed us to define the role played by litho-structural and tectonic features on landslide occurrence and distribution, and their interplay in driving landscape evolution over centuries. Finally, this work represents a valuable scientific tool to support geomorphological studies for landslide hazard assessment and proper territorial planning in any other small insular areas, showing similar geological–geomorphological features and landscape values.

show abstract

Unraveling the evolution of landslide susceptibility: a systematic review of 30-years of strategic themes and trends

Cited by 9 publications

References 106 publications

Landslide Susceptibility Analysis and Hazard Zonation in Nuwakot District, Nepal

Landslide Susceptibility Analysis and Hazard Zonation in Nuwakot District, Nepal

A modular framework for FAIR shallow landslide susceptibility mapping based on machine learning

Rockfall Susceptibility Assessment and Landscape Evolution of San Nicola Island (Tremiti Islands, Southern Adriatic Sea, Italy)

Contact Info

Product

Resources

About