A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Modelling Stage–Discharge Relationship using Data-Driven Techniques
Discharge measurement in rivers is a challenging job for hydraulic engineers. A graph of stage vs. discharge represents the stage–discharge relationship, also known as rating curve. Once a relationship is established, it can be used for prediction of discharge from stage. For various hydrological applications, the accurate information about flow value in rivers is very important. In this paper, the stage–discharge relationship is modelled using three different data-driven techniques, namely non-linear regression (NLR), artificial neural networks (ANN) and model tree (MT). Artificial intelligence technique like ANN allows knowledge processing and can be used as forecasting tool. The applicability and performance of the so-called M5 model tree machine-learning technique show that MTs, being analogous to piecewise linear functions, have certain advantages compared to ANNs – they are more transparent and hence acceptable by decision-makers, are very fast in training and always converge. In the present work, it was seen that the accuracy of M5 trees is at par with ANNs and both were better than NLR.
Modelling Stage–Discharge Relationship using Data-Driven Techniques
Discharge measurement in rivers is a challenging job for hydraulic engineers. A graph of stage vs. discharge represents the stage–discharge relationship, also known as rating curve. Once a relationship is established, it can be used for prediction of discharge from stage. For various hydrological applications, the accurate information about flow value in rivers is very important. In this paper, the stage–discharge relationship is modelled using three different data-driven techniques, namely non-linear regression (NLR), artificial neural networks (ANN) and model tree (MT). Artificial intelligence technique like ANN allows knowledge processing and can be used as forecasting tool. The applicability and performance of the so-called M5 model tree machine-learning technique show that MTs, being analogous to piecewise linear functions, have certain advantages compared to ANNs – they are more transparent and hence acceptable by decision-makers, are very fast in training and always converge. In the present work, it was seen that the accuracy of M5 trees is at par with ANNs and both were better than NLR.
Modelling Stage–Discharge Relationship using Data-Driven Techniques
Londhe, Shreenivas (author) / Panse-Aglave, Gauri (author)
ISH Journal of Hydraulic Engineering ; 21 ; 207-215
2015-05-04
9 pages
Article (Journal)
Electronic Resource
English
Predictive modelling of the stage–discharge relationship using Gene-Expression Programming
| DOAJ | 2021
Modeling Stage-Discharge Relationship Using Artificial Neural Network
| British Library Conference Proceedings | 2005
Stage-Discharge Relations for Low-Gradient Tidal Streams Using Data-Driven Models
| Online Contents | 2006
Stage-Discharge Relations for Low-Gradient Tidal Streams Using Data-Driven Models
| British Library Online Contents | 2006