A hybrid model using machine learning methods and GIS for potential rockfall source identification from airborne laser scanning data

Fanos, Ali Mutar; Pradhan, Biswajeet; Mansor, Shattri; Yusoff, Zainuddin; Abdullah, Ahmad Fikri

doi:10.1007/s10346-018-0990-4

Cited by 49 publications

(20 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In terms of ensemble approaches, several single classifiers have been combined using ensemble frameworks including random subspace [44], random forest [45,46], Bagging [47], AdaBoost [48], MultiBoost [49], and so on [37,[50][51][52]. Currently, some novel ensemble techniques have been proposed and applied in landslide susceptibility assessment, flood susceptibility mapping, and groundwater potential analysis [41,53,54].…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

2019

View full text Add to dashboard Cite

The main aim of this study was to compare the performances of the hybrid approaches of traditional bivariate weights of evidence (WoE) with multivariate logistic regression (WoE-LR) and machine learning-based random forest (WoE-RF) for landslide susceptibility mapping. The performance of the three landslide models was validated with receiver operating characteristic (ROC) curves and area under the curve (AUC). The results showed that the areas under the curve obtained using the WoE, WoE-LR, and WoE-RF methods were 0.720, 0.773, and 0.802 for the training dataset, and were 0.695, 0.763, and 0.782 for the validation dataset, respectively. The results demonstrate the superiority of hybrid models and that the resultant maps would be useful for land use planning in landslide-prone areas.

show abstract

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

2019

View full text Add to dashboard Cite

show abstract

“…The inventory of landslides data has been prepared from different sources, including remote sensing, field survey measurement, and historical records. High-resolution aerial photography and SPOT panchromatic images were used in the previous study for visual inspections of landslides [14]. Landslides occur in vegetation area can be measured through satellite images, field measurements and historical records have collected these landslides [14].…”

Section: Methodsology Landslide Inventory Mapmentioning

confidence: 99%

“…High-resolution aerial photography and SPOT panchromatic images were used in the previous study for visual inspections of landslides [14]. Landslides occur in vegetation area can be measured through satellite images, field measurements and historical records have collected these landslides [14]. Multiple field measurements were carried out using Global Navigation Satellite System (GNSS) device where Malaysia Survey Department gives the real-time corrections.…”

Section: Methodsology Landslide Inventory Mapmentioning

confidence: 99%

Landslide Susceptibility Modelling for Agricultural Activities in Hilly Areas

Ishak*,

Sidek,

Wayayok

et al. 2019

IJRTE

View full text Add to dashboard Cite

The slope failure risk assessment of a particular area can be prepared by considering the data available. Many attempts have been made to classify the risk where evaluations are made in rating or in grading the slopes based on their characteristics and erosion problems. The assessments were done for geo-hazard such as erosion and landslide recognized in planning and guidance. Most of the hazard risk analyses require detailed knowledge of the geo- environmental predisposition factors and initial events that led to failure. The results of these analyses consist of identification and mapping of all erosion induced landslide phenomenon and are often translated in the form of maps, which is the fundamental step of the hazard assessment. The ranking of susceptibility areas and the delineation of probable failure areas are among essential features relevant to the production of these maps. In this study, Landslide Susceptibility Modelling was developed by taking into consideration all the landslide susceptibility factors in Cameron Highlands. The landslide susceptibility map was produced based on the historical records of a landslide in that area for 20 years and the frequency ratio model was developed using mapoverlaying techniques. The susceptibility map offers substantial benefits as a regional-scale tool over earlier susceptibility maps and Cameron Highland landslide- susceptible terrain zoning. The susceptibility map has the advantage of assisting with the implementation of suitable efforts to prevent landslides.

show abstract

“…To date, such compilations are somewhat cumbersome and time‐consuming, and must be dealt with very carefully. Although semi‐automated processes facilitating feature extraction are already in use (Aubry, Maturana, Efros, Russell, & Sivic, 2014; Chen, Chen, & Tseng, 2016; Chen et al, 2018; Fanos, Pradhan, Mansor, Yusoff, & bin Abdullah, 2018; Garosi, Sheklabadi, Conoscenti, Pourghasemi, & Van Oost, 2019; Goshen & Shimshoni, 2008; Hartley & Zisserman, 2003), they primarily refer to maps and photographs, leaving aside illustrations and paintings. More importantly, they devote less attention to synthesizing various features originating from different types of visual sources on a unified GIS‐based framework.…”

Section: Giscience and The Study Of Palestinementioning

confidence: 99%

Advancing the historical geography of late Ottoman and British Mandate Palestine using GIScience: A review

Zohar

2020

Transactions in GIS

View full text Add to dashboard Cite

Late Ottoman Empire and Mandate Palestine are two important periods preceding independent Israel, characterized by increased attention to Palestine along with modernization processes and substantial landscape changes. Significant increase is also noted in survey and mapping, resulting in a wealth of visual sources. However, while textual sources were used intensively in various studies, the latter were analyzed to a much lesser extent. A major discipline based on the study of visual sources is historical geography. However, lately it seems that historical geography worldwide seeks for new approaches while struggling to retain dominancy in an environment becoming more computerized and technological. In this article I review the opportunities, pitfalls, and challenges of incorporating GIScience into the historical geography of late Ottoman and Mandate Palestine. Accordingly, it is suggested that a proper integration will contribute a substantial theoretical and methodological novelty while boosting the discipline of historical geography as well as other social sciences and humanities disciplines.

show abstract

A hybrid model using machine learning methods and GIS for potential rockfall source identification from airborne laser scanning data

Cited by 49 publications

References 48 publications

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

Landslide Susceptibility Modelling for Agricultural Activities in Hilly Areas

Advancing the historical geography of late Ottoman and British Mandate Palestine using GIScience: A review

Contact Info

Product

Resources

About