Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic
By the assist of remotely sensed data, this study examines the viability of slope stability monitoring using two novel conventional models. The proposed models are considered to be the combination of neuro-fuzzy (NF) system along with invasive weed optimization (IWO) and elephant herding optimizatio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/21/4636 |
| _version_ | 1798034673122672640 |
|---|---|
| author | Hossein Moayedi Dieu Tien Bui Loke Kok Foong |
| author_facet | Hossein Moayedi Dieu Tien Bui Loke Kok Foong |
| author_sort | Hossein Moayedi |
| collection | DOAJ |
| description | By the assist of remotely sensed data, this study examines the viability of slope stability monitoring using two novel conventional models. The proposed models are considered to be the combination of neuro-fuzzy (NF) system along with invasive weed optimization (IWO) and elephant herding optimization (EHO) evolutionary techniques. Considering the conditioning factors of land use, lithology, soil type, rainfall, distance to the road, distance to the river, slope degree, elevation, slope aspect, profile curvature, plan curvature, stream power index (SPI), and topographic wetness index (TWI), it is aimed to achieve a reliable approximation of landslide occurrence likelihood for unseen environmental conditions. To this end, after training the proposed EHO-NF and IWO-NF ensembles using training landslide events, their generalization power is evaluated by receiving operating characteristic curves. The results demonstrated around 75% accuracy of prediction for both models; however, the IWO-NF achieved a better understanding of landslide distribution pattern. Due to the successful performance of the implemented models, they could be promising alternatives to mathematical and analytical approaches being used for discerning the relationship between the slope failure and environmental parameters. |
| first_indexed | 2024-04-11T20:47:32Z |
| format | Article |
| id | doaj.art-c8ee9130779147e6b850aa3aa2054130 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T20:47:32Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c8ee9130779147e6b850aa3aa20541302022-12-22T04:03:59ZengMDPI AGSensors1424-82202019-10-011921463610.3390/s19214636s19214636Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy LogicHossein Moayedi0Dieu Tien Bui1Loke Kok Foong2Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, VietnamGeographic Information System Group, Department of Business and IT, University of South-Eastern Norway, N-3800 Bø i Telemark, NorwayInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamBy the assist of remotely sensed data, this study examines the viability of slope stability monitoring using two novel conventional models. The proposed models are considered to be the combination of neuro-fuzzy (NF) system along with invasive weed optimization (IWO) and elephant herding optimization (EHO) evolutionary techniques. Considering the conditioning factors of land use, lithology, soil type, rainfall, distance to the road, distance to the river, slope degree, elevation, slope aspect, profile curvature, plan curvature, stream power index (SPI), and topographic wetness index (TWI), it is aimed to achieve a reliable approximation of landslide occurrence likelihood for unseen environmental conditions. To this end, after training the proposed EHO-NF and IWO-NF ensembles using training landslide events, their generalization power is evaluated by receiving operating characteristic curves. The results demonstrated around 75% accuracy of prediction for both models; however, the IWO-NF achieved a better understanding of landslide distribution pattern. Due to the successful performance of the implemented models, they could be promising alternatives to mathematical and analytical approaches being used for discerning the relationship between the slope failure and environmental parameters.https://www.mdpi.com/1424-8220/19/21/4636remote sensinginvasive weed optimizationslope stability monitoring |
| spellingShingle | Hossein Moayedi Dieu Tien Bui Loke Kok Foong Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic Sensors remote sensing invasive weed optimization slope stability monitoring |
| title | Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic |
| title_full | Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic |
| title_fullStr | Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic |
| title_full_unstemmed | Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic |
| title_short | Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic |
| title_sort | slope stability monitoring using novel remote sensing based fuzzy logic |
| topic | remote sensing invasive weed optimization slope stability monitoring |
| url | https://www.mdpi.com/1424-8220/19/21/4636 |
| work_keys_str_mv | AT hosseinmoayedi slopestabilitymonitoringusingnovelremotesensingbasedfuzzylogic AT dieutienbui slopestabilitymonitoringusingnovelremotesensingbasedfuzzylogic AT lokekokfoong slopestabilitymonitoringusingnovelremotesensingbasedfuzzylogic |