A novel model for regional susceptibility mapping of rainfall-reservoir induced landslides in Jurassic slide-prone strata of western Hubei Province, Three Gorges Reservoir area

Long, Jingjing; Liu, Yong; Li, Changdong; Fu, Zhiyong; Zhang, Haikuan

doi:10.1007/s00477-020-01892-z

Cited by 28 publications

(6 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, period III (2011–2020) focuses on the improvement and combination of different numerical models, managing to represent the reality of the environment and the mechanical behavior of the landslides for their respective analysis in field and risk assessment [ 120 , 121 , 122 , 123 ]. In this way, at the end of this period, these investigations and improved models allow us to understand the behavior of different landslides types [ 124 , 125 , 126 ]. In addition, the geomorphological, tectonic and hydrodynamic processes involved in mass movement processes were explained in detail [ 127 , 128 ].…”

Section: Resultsmentioning

confidence: 99%

“…Studies focusing on this cluster have led to improved mapping, understanding, interpretation and prediction of landslides, such as the movement direction through the hydraulic gradient [ 172 ], the influence of rainfall, soil saturation [ 125 , 173 ] and continuous monitoring for preventive decisions in potential hazardous landslides [ 174 ].…”

Section: Resultsmentioning

confidence: 99%

“…In the decade 2001–2010, scientific research increased ( Figure 3 ), prioritizing the update of old studies such as the global rainfall threshold [ 113 ], the classification of landslides [ 109 ] and the generation of models [ 117 , 119 ], which in this period are essential for understanding and preventing landslides. Over the last decade (2011–2020), the increase in its scientific production has been stable, improving the development and combination of models generated in the previous period [ 125 , 126 ]. In this way, the analysis of landslides and the dynamic behavior of the debris flow, shallow landslides and their movement as a flow was perfected ( Figure 6 ).…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Worldwide Research Trends in Landslide Science

Carrión-Mero

Montalván-Burbano

Morante-Carballo

et al. 2021

IJERPH

View full text Add to dashboard Cite

Landslides are generated by natural causes and by human action, causing various geomorphological changes as well as physical and socioeconomic loss of the environment and human life. The study, characterization and implementation of techniques are essential to reduce land vulnerability, different socioeconomic sector susceptibility and actions to guarantee better slope stability with a significant positive impact on society. The aim of this work is the bibliometric analysis of the different types of landslides that the United States Geological Survey (USGS) emphasizes, through the SCOPUS database and the VOSviewer software, for the analysis of their structure, scientific production, and the close relationship with several scientific fields and its trends. The methodology focuses on: (i) search criteria; (ii) data extraction and cleaning; (iii) generation of graphs and bibliometric mapping; and (iv) analysis of results and possible trends. The study and analysis of landslides are in a period of exponential growth, focusing mainly on techniques and solutions for the stabilization, prevention, and categorization of the most susceptible hillslope sectors. Therefore, this research field has the full collaboration of various authors and places a significant focus on the conceptual evolution of the landslide science.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Worldwide Research Trends in Landslide Science

Carrión-Mero

Montalván-Burbano

Morante-Carballo

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…This approach and the loglikelihood distance method can group a mixture of categorical and continuous data (Carbone et al, 2019), (Yozza et al, 2016). Subsequently, this method has been used by several previous studies, including Vavougios et al (2016), Qin et al (2019), Long et al (2020). The advantage of the TSC procedure is the ability to automatically set the number of groups (Carbone et al, 2019) using Schwarz's Bayesian Information Criterion (BIC).…”

Section: Two-step Cluster Analysismentioning

confidence: 99%

The Pattern Recognition of Small-Scale Privately-Owned Forest in Ciamis Regency, West Java, Indonesia

Siarudin¹,

Awang

Sadono

et al. 2022

View full text Add to dashboard Cite

Small-scale Privately-owned Forest (SSPF) has various patterns identification, based on the stand structure and species composition. The recognition and classification of the SSPF cropping patterns are required for further planning and policy development. Therefore, this study aims to classify the cropping pattern of SSPF in Ciamis Regency, West Java Province, Indonesia. The data were collected by observing the stand structure and species composition of 150 plots of land, encompassing three Sub-districts representing the central, northern, and southern regions of Ciamis Regency. The four categorical variables include tree species composition, age, spatial distribution, and intercropping pattern. While the two continuous variables were stand density and basal area. The patterns obtained were classified based on a Two-Step Cluster algorithm with log-likelihood distance measure, and auto clustering using Schwarz's Bayesian Information Criterion, validated by silhouette index. In addition, a multicollinearity test was conducted to reduce redundancy in using variable sets. The results showed that, the improvement of the cluster quality based on the silhouette index value, was achievable by excluding the tree spatial distribution variable, which exhibits multicollinearity. The cropping patterns were classified into three categories, namely tree crops, mixed-tree lots, and agrisilviculture for group-1, group-2, and group-3, respectively. Group-1 consisted of stands with one or two commercial tree species, and in several cases, were intercropped. Group-2 contained uneven-aged mixed-tree stands without any crops. While Group-3 consisted of an intercropping system of uneven-aged mixed-tree stands and crops. The results suggest further analysis, in order to relate the cropping patterns with the socio-economic characteristics of the landowners, as well as the strategies for the development of a sustainable SSPF.

show abstract

“…The ML methods include support vector For the unbalanced sample composed of a large proportion of non-landslides and small landslides, there are problems with having LSM. The single ML classifier cannot perform satisfactorily when dealing with unbalanced samples (Tanyu et al, 2021;Long et al, 2021;Yan et al, 2022). Ensemble learning is an effective method to solve the classification problem of sample imbalance.…”

Section: Introductionmentioning

confidence: 99%

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Yin

Wang

Cao

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. In recent years, several catastrophic landslide events have been observed throughout the globe, significantly affecting the loss of lives, infrastructure, everyday life and livelihood. To minimize the impact of landslides and issue early warnings, landslide susceptibility maps (LSM) are essential. Aim to improve the accuracy of LSM, this study applied a random selection of non-landslide samples and low accuracy of individual classifiers using machine learning (ML) techniques, coupled with ensemble learning and ML, for LSM. China's Zigui-Badong section of the Three Gorges Reservoir area (TGRA) was considered a case study. Twelve influencing factors were selected as inputs for modelling, and the relationship between each causal factor and landslide spatial development was quantitatively analyzed. A total of 179 landslides were identified in the present study. About 70 % of the landslide pixels were randomly considered for training, and the remaining 30 % were used for validation. The Logistic Regression model (LR) was applied to produce an initial susceptibility map, and the non-landslide samples were selected within the classified low-susceptibility area. Subsequently, two ML classifiers – the Classification and Regression Tree (CART), and the Multi-Layer Perceptron (MLP), and four coupling models – the CART-Bagging, CART-Boosting, MLP-Bagging, and MLP-Boosting, were utilized for LSM. Finally, the receiver operating characteristics (ROC) curve and statistical analysis were applied for accuracy assessment. The results show that elevation and distance to rivers were the main causal factors of landslide development in the study area. The modeling accuracy of LR-MLP was calculated approx. 0.901, which is higher than the LR-CART (0.889). The LR-MLP-Boosting performed the best with an accuracy of 0.986 followed by the LR-CART-Bagging (0.973), LR-CART-Boosting (0.981), and LR-MLP-Bagging (0.978). The accuracy has been improved compared with the NO-CART, NO-MLP, NO-CART-Bagging, NO-CART-Boosting, NO-MLP-Bagging, and NO-MLP-Boosting models. Four ensemble models outperformed their corresponding classifiers, while Boosting outperforms Bagging. Overall, the combination of ensemble learning and ML effectively improved the accuracy of LSM. The LR model can effectively constrain the selection range of non-landslide samples and enhance the quality of sample selection. Our results show promise to map susceptible landslides locations which will help to monitor for an early warning of the landside.

show abstract

A novel model for regional susceptibility mapping of rainfall-reservoir induced landslides in Jurassic slide-prone strata of western Hubei Province, Three Gorges Reservoir area

Cited by 28 publications

References 81 publications

Worldwide Research Trends in Landslide Science

Worldwide Research Trends in Landslide Science

The Pattern Recognition of Small-Scale Privately-Owned Forest in Ciamis Regency, West Java, Indonesia

Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping

Contact Info

Product

Resources

About