Prediction of Hydraulic Blockage at Culverts using Lab Scale Simulated Hydraulic Data
- 29 May 2022
- journal article
- research article
- Published by Taylor & Francis in Urban Water Journal
- Vol. 19 (7) , 686-699
Abstract
Blockage of culverts causes reduction in hydraulic capacity and is one of the main contributors to trigger urban flooding. However, the highly non-linear nature of debris interaction during the flood and lack of blockage-related data from actual flooding events make conventional numerical modelling almost impossible. Literature investigating blockage phenomena reports blockage as a complex hydraulic process, which suggests exploring adaptive solutions using latest technologies. In this context, motivated by the success of data-driven algorithms, in this article, four data driven models (i.e., K-NN, ANN, SVR, 1D-CNN) are implemented to predict the hydraulic blockage at culverts. A new numerical Hydraulics-Lab Blockage Dataset (HBD) is established from a series of lab-scale hydraulic experiments. From the experimental investigations, the ANN model was reported as the best with a R2 score of 0.95. A potential use-case of presented research for real-world application is also discussed to demonstrate the practical feasibility.Keywords
This publication has 39 references indexed in Scilit:
- A physical model study of culvert blockage by large urban debrisAustralasian Journal of Water Resources, 2015
- Analysis of the performance of debris screens at culvertsProceedings of the Institution of Civil Engineers - Water Management, 2014
- The non-impact of debris blockages on the August 1998 Wollongong floodingAustralasian Journal of Water Resources, 2012
- A flume experiment on the formation of wood jams in riversWater Resources Research, 2008
- What are artificial neural networks?Nature Biotechnology, 2008
- Artificial Neural Networks2005
- Distorted Froude‐scaled flume analysis of large woody debrisEarth Surface Processes and Landforms, 2001
- Adaptive soft k-nearest-neighbour classifiersPattern Recognition, 2000
- A training algorithm for optimal margin classifiers1992
- The Nearest Neighbor Classification Rule with a Reject OptionIEEE Transactions on Systems Science and Cybernetics, 1970