Establishing an ANN-Based Risk Model for Ground Subsidence Along Railways
Source abstract
Abstract
Ground subsidence occurrences have drastically increased in the Seoul area of the Republic of Korea. The structural defects of underground utilities were found to be the primary cause of ground subsidence based on several field investigations. This paper presents a risk model that assesses the probability of occurrence of ground subsidence along railways. In this study, support vector machine (SVM) and multi-layer perceptron (MLP) approaches were successfully employed to develop an artificial neural network (ANN)-based risk model. The risk model, in conjunction with a database composed of underground utilities and geological boring data along urban railway networks, was utilized to develop a hazard map system. A limited field experimental program was conducted for the purpose of verification, resulting in a promising tool to effectively maintain railway networks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Rock Mechanics and Modeling · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Railroad Electrical and Electronics Engineering, Korea National University of Transportation, Uiwang-si, Gyeonggi-do 16106, Korea
Department of Railroad Infrastructure System Engineering, Korea National University of Transportation, Uiwang-si, Gyeonggi-do 16106, Korea
Funding
Korea Rail Network Authority
References (17)
Show source-provided references
1. Seoul Metropolitan Government (2015). Investigation of Underground Cavity Mechanism, Research Report.
2. Geospatial Modeling for Sinkholes Hazard Map based on GIS&RS Data
3. Morphogenesis of hypogenic caves10.1016/j.geomorph.2008.09.013 ↗
4. (2018, September 20). USGS, Available online: https://www.usgs.gov/faqs/what-difference-between-a-sinkhole-and-land-subsidence?qt-news_science_products=0#qt-news_science_products.
5. Improving sinkhole hazard models incorporating magnitude–frequency relationships and nearest neighbor analysis10.1016/j.geomorph.2011.05.020 ↗
6. Sinkholes in the Salt-bearing evaporate karst of the Ebro River valley upstream of Zaragoza city (NE Spain) Geomorphological mapping and analysis as a basis for risk management10.1016/j.geomorph.2008.12.018 ↗
7. Land subsidence risk assessment and protection in mined-out regions10.5194/piahs-372-145-2015 ↗
8. Park, J.K., Cho, D.H., Hossain, M.S., and Oh, J. (2018). Assessment of Settlement Profile Caused by Underground Box Structure Installation with an Artificial Neural Network Model. J. Transp. Res. Board.10.1177/0361198118756901 ↗
9. Park, H.I. (2011). Study for Application of Artificial Neural Networks in Geotechnical Problems. Artificial Neural Networks-Application, IntechOpen.
10. Genetic outlier detection for a robust support vector machine10.5391/IJFIS.2015.15.2.96 ↗
11. Lee, H., Hong, S., and Kim, E. (2009). A new genetic feature selection with neural network ensemble. Int. J. Comput. Math., 1105–1117.10.1080/00207160701724760 ↗
12. Oh, J., Kim, J., Choi, J., and Kim, K. (2016). Smart Evaluation of Railroad Roadbed with Respect to the Ground Subsidence, Korea Rail Network Authority. Final Research Report No. 2017-50102-002.
13. Mechanical and chemical reinforcements for the installation of underground utilities to mitigate underground cavity10.9798/KOSHAM.2017.17.3.257 ↗
14. Oh, K., Lee, H., Hong, S., and Kim, E. (2006, January 20–24). Side view face recognition as an aid to gait recognition. Proceedings of the Joint 3rd International Conference on Soft Computing and Intelligent Systems and 7th International Symposium on Advanced Intelligent Systems, Japan Society for Fuzzy Theory and Intelligent Informatics, Tokyo, Japan.
15. Hagan, M.T., Demuth, H.B., and Beale, H. (1995). Neural Network Design, PWS Publishing Company.
16. Suen, C.Y., Nadal, C., Mai, T., Legaulr, R., and Lam, L. Recognition of handwritten numerals based on the concept of multiple experts, In Proceedings of the 1st International Workshop on Frontiers Handwriting Recognition: Montreal, QC, Canada, 2–3 April 1990; pp.
17. Mamaqani, B. (2014). Numerical Modeling of Ground Movements Associated with Trenchless Box Jacking Technique. [Ph.D. Thesis, The University of Texas].