Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping

Park, Inhye; Choi, Jaewon; Lee, Moung Jin; Lee, Saro

doi:10.1016/j.cageo.2012.01.005

Cited by 50 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To prevent overlearning, the number of MFs of inputs and the number of training epochs should be selected optimally and carefully. Also, when selecting the number of MFs of the inputs, the physical meanings of the inputs should be considered by an expert (Oh and Pradhan 2011;Park et al 2012).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea

2015

Self Cite

View full text Add to dashboard Cite

Landslides susceptibility maps were constructed in Seorak mountain area, Korea, using an integration of frequency ratio and adaptive neuro-fuzzy inference system (ANFIS) in geographical information system (GIS) environment. Landslide occurrence areas were detected in the study by interpreting aerial photographs and field survey data. Landslide locations were randomly selected in a 50/50 ratio for training and validation of the models, respectively. Topography, geology, soil, and forest databases were also constructed. Maps relevant to landslide occurrence were assembled in a spatial database. Using the constructed spatial database, 17 landslide-related factors were extracted. The adaptive ANFIS model with different types of membership functions (MFs) was then applied for landslide susceptibility mapping in the study area. Two landslide susceptibility maps were prepared using the different MFs. The frequency ratio model was also applied to the landslide susceptibility mapping for comparing with the probabilistic ANFIS model. Finally, the resulting landslide susceptibility maps were validated using the landslide locations which were not used for training the ANFIS. The validation results showed 75.57 % accuracy using the generalized bell-shaped MF model, 74.94 % accuracy using the Sigmoidal 2 MF model and 73.07 % accuracy using frequency ratio model. These accuracy results show that an ANFIS can be an effective tool in landslide susceptibility mapping.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The detail formula of typical ANFIS with two inputs, two rules, one output (F), and five layers for the first-order Takagi-Sugeno (TS) fuzzy model can be referenced in Jang (1993), Sugeno (1985), Park et al (2012) (Fig. 6).…”

Section: Methodsmentioning

confidence: 99%

Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks have been applied also in scientific fields such as geology (Subbaiah, 2011;Xia-Ting, Young Jia, & Jian Guo, 1996;Zhu et al, 2013), hydrology (Adamowski & Chan, 2011;Ghose, Panda, & Swain, 2010;Kumar, Raghuwanshi, & Singh, 2010;Li, Shu, Liu, Yin, & Wen, 2012) or surface protection (Ambro zi c & Turk, 2003;Gruszczy nski, 2007;Jung, Cheon, & Choi, 2005;Kim, Lee, & Oh, 2008;Oh & Lee, 2011;Park, Choi, Jin Lee, & Lee, 2012;Pawlu s, 2007;Yang & Xia, 2013;Zhang, Liu, & Liu, 2011).…”

Section: Methodsmentioning

confidence: 97%

Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage

Hejmanowski

Witkowski

2015

Journal of Sustainable Mining

View full text Add to dashboard Cite

Drainage of underground mineArtificial neural networks MLP a b s t r a c t Based on the previous studies conducted by the authors, a new approach was proposed, namely the tools of artificial intelligence. One of neural networks is a multilayer perceptron network (MLP), which has already found applications in many fields of science. Sequentially, a series of calculations was made for different MLP neural network configuration and the best of them was selected. Mean square error (MSE) and the correlation coefficient R were adopted as the selection criterion for the optimal network. The obtained results were characterized with a considerable dispersion. With an increase in the amount of hidden neurons, the MSE of the network increased while the correlation coefficient R decreased.Similar conclusions were drawn for the network with a small number of hidden neurons.The analysis allowed to select a network composed of 24 neurons as the best one for the issue under question. The obtained final answers of artificial neural network were presented in a histogram as differences between the calculated and expected value.

show abstract

“…A geographical information system (GIS) was used as the basic analysis tool in this process because it can analyse small units and depict suitable vulnerability zones that may be addressed by spatial planning (Choi et al 2010;Lee et al , 2013. Sophisticated methods that use GIS for analysing natural disasters, including flooding, have been proposed in previous studies (Lee & Lee 2006;Park et al 2012;Tehrany et al 2014). A flowchart outlining our method is shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Application of fuzzy combination operators to flood vulnerability assessments in Seoul, Korea

Lee

Kang

Kim

2015

Geocarto International

View full text Add to dashboard Cite

The goal of this study was to apply, verify and compare fuzzy models with various fuzzy combination operators to analyze the vulnerability to flooding in Seoul, Korea, and to create flood vulnerability maps. We employed the IPCC concept of vulnerability, which comprises exposure to climate, sensitivity and the adaptive capacity, to identify factors that influence flooding. Eleven factors were compiled in a spatial database using geographical information system. The relative weight of each factor was converted into a fuzzy membership value, which was integrated to obtain a flood vulnerability index using five fuzzy combination operators (fuzzy AND, fuzzy OR, fuzzy algebraic sum, fuzzy algebraic product and fuzzy gamma). Overall, the fuzzy models were quite effective tools for flood vulnerability assessment. Of the five fuzzy combination operators, the fuzzy AND operator obtained the highest prediction accuracy of 88.68%. This study achieved better flood vulnerability assessments by employing and comparing fuzzy combination operators.

show abstract

Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping

Cited by 50 publications

References 21 publications

Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea

Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea

Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage

Application of fuzzy combination operators to flood vulnerability assessments in Seoul, Korea

Contact Info

Product

Resources

About