Landslide Susceptibility Mapping by Neuro-Fuzzy Approach in a Landslide-Prone Area (Cameron Highlands, Malaysia)

Pradhan, Biswajeet; Sezer, Ebru Akçapınar; Gökçeoğlu, Candan; Buchroithner, Manfred

doi:10.1109/tgrs.2010.2050328

Cited by 247 publications

(93 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, the fuzzy algebra model was used to integrate ground subsidence hazard maps, withthis model being used most frequently in analysis landslide susceptibility mapping [28][29][30][31][32]. Ercanoglu and Gokceoglu [28,29] proposed an assessment of landslide susceptibility for landslide prone areas using fuzzy relationships, Pradhan et al [30] and Sezer et al [31] used neuro-fuzzy models to analysese landslide susceptibility, and Akgun et al [32] applied Mamdani fuzzy algorithm for the assessment of landslide susceptibility mapping. This study focused on the former coal mining area of Samcheok City, Korea.…”

Section: Introductionmentioning

confidence: 99%

Ensemble of ground subsidence hazard maps using fuzzy logic

Park

Lee

Lee³

2014

Open Geosciences

View full text Add to dashboard Cite

Hazard maps of ground subsidence around abandoned underground coal mines (AUCMs) in Samcheok, Korea, were constructed using fuzzy ensemble techniques and a geographical information system (GIS). To evaluate the factors related to ground subsidence, a spatial database was constructed from topographic, geologic, mine tunnel, land use, groundwater, and ground subsidence maps. Spatial data, topography, geology, and various ground-engineering data for the subsidence area were collected and compiled in a database for mapping groundsubsidence hazard (GSH). The subsidence area was randomly split 70/30 for training and validation of the models. The relationships between the detected ground-subsidence area and the factors were identified and quantified by frequency ratio (FR), logistic regression (LR) and artificial neural network (ANN) models. The relationships were used as factor ratings in the overlay analysis to create ground-subsidence hazard indexes and maps. The three GSH maps were then used as new input factors and integrated using fuzzy-ensemble methods to make better hazard maps. All of the hazard maps were validated by comparison with known subsidence areas that were not used directly in the analysis. As the result, the ensemble model was found to be more effective in terms of prediction accuracy than the individual model.

show abstract

Section: Introductionmentioning

confidence: 99%

Ensemble of ground subsidence hazard maps using fuzzy logic

Park

Lee

Lee³

2014

Open Geosciences

View full text Add to dashboard Cite

show abstract

“…Their compilation of more than 21 years of landslide inventory resulted in a total of 324 landslides in their study area of 293 km 2 (Pradhan, 2010;Pradhan and Lee, 2010;Pradhan et al, 2010). 55 landslides were located in our study area of 100 km 2 .…”

Section: Landslide Interpretability Of Als-derived Dtmsmentioning

confidence: 80%

“…Pradhan, 2010;Pradhan et al, 2010;Pradhan and Lee, 2010a). However, the training data of these susceptibility studies are based on historic inventories of landslide occurrences.…”

Section: Landslide Susceptibility Mappingmentioning

confidence: 99%

“…It was produced based on visual interpretation of archived aerial photographs with scales ranging from 1:10,000 to 1:50,000, satellite images, e.g. SPOT 5 panchromatic, IKONOS, RADARSAT, landslide archives over the past 21 years, and several field-campaigns (Pradhan and Lee, 2010;Pradhan et al, 2010). This inventory has been used for regional landslide susceptibility mapping (Pradhan and Lee, 2010;Pradhan et al, 2010;Pradhan, 2010) and landslide hazards analysis (Pradhan and Youssef, 2010;Pradhan, 2010).…”

Section: Landslide Inventory Mappingmentioning

confidence: 99%

“…Several studies have been carried out to model landslide susceptibility in Malaysia (Pradhan, 2010;Pradhan et al, 2010;Pradhan and Lee, 2010a). Predicting areas that are susceptible to landslides requires insight in the process-controlling factors, the geo-environmental conditions, the availability of a historic record and an indication of the accuracy of these data.…”

Section: Landslide Susceptibility Mapping Based On Als Datamentioning

confidence: 99%

See 2 more Smart Citations

Airborne laser scanning : for forested landslides investigation in temperate and tropical invironments

Razak¹

View full text Add to dashboard Cite

Assessment of land cover and land use change impact on soil loss in a tropical catchment by using multitemporal SPOT‐5 satellite images and Revised Universal Soil Loss Equation model

et al. 2018

Self Cite

View full text Add to dashboard Cite

Soil erosion is a common land degradation problem and has disastrous impacts on natural ecosystems and human life. Therefore, researchers have focused on detection of land cover–land use changes (LCLUC) with respect to monitoring and mitigating the potential soil erosion. This article aims to appraise the relationship between LCLUC and soil erosion in the Cameron Highlands (Malaysia) by using multitemporal satellite images and ancillary data. Land clearing and heavy rainfall events in the study area has resulted in increased soil loss. Moreover, unsustainable development and agricultural practices, mismanagement, and lack of land use policies increase the soil erosion rate. Hence, the main contribution of this study lies in the application of appropriate land management practices in relation to water erosion through identification and prediction of the impacts of LCLUC on the spatial distribution of potential soil loss in a region susceptible to natural hazards such as landslide. The LCLUC distribution within the study area was mapped for 2005, 2010, and 2015 by using SPOT‐5 temporal satellite imagery and object‐based image classification. A projected land cover–land use map was also produced for 2025 through integration of Markov chain and cellular automata models. An empirical‐based approach (Revised Universal Soil Loss Equation) coupled with geographic information system was applied to measure soil loss and susceptibility to erosion over the study area for four periods (2005, 2010, 2015, and 2025). The model comprises five parameters, namely, rainfall factor, soil erodibility, topographical factor, conservation factor, and support practice factor. Results exhibited that the average amount of soil loss increased by 31.77 t ha−1 yr−1 from 2005 to 2015 and was predicted to dramatically increase in 2025. The results generated from this research recommends that awareness of spatial and temporal patterns of high soil loss risk areas can help deploy site‐specific soil conservation measures and erosion mitigation processes and prevent unsystematic deforestation and urbanization by the authorities.

show abstract

Landslide Susceptibility Mapping by Neuro-Fuzzy Approach in a Landslide-Prone Area (Cameron Highlands, Malaysia)

Cited by 247 publications

References 51 publications

Ensemble of ground subsidence hazard maps using fuzzy logic

Ensemble of ground subsidence hazard maps using fuzzy logic

Airborne laser scanning : for forested landslides investigation in temperate and tropical invironments

Assessment of land cover and land use change impact on soil loss in a tropical catchment by using multitemporal SPOT‐5 satellite images and Revised Universal Soil Loss Equation model

Contact Info

Product

Resources

About