Bridge backwater estimation: A Comparison between artificial intelligence models and explicit equations

Abstract

Estimation of bridge backwater has been one of practical challenges in hydraulic engineering for decades. In this study, Genetic Programming (GP) has been applied for estimating bridge backwater for the first time based on the conducted literature review. Furthermore, two new explicit equations are developed for predicting bridge afflux using Genetic Algorithm (GA) and hybrid MHBMO-GRG algorithm. The performances of these models are compared with Artificial Neural Network (ANN) and several explicit equations available in the literature considering both laboratory and field data. Based on five considered performance evaluation criteria, the two new explicit equations outperform the ones available in the literature. Furthermore, GP and ANN achieve the 2 best results in favor of four out of five considered criteria for train and test data, respectively. To be more specific, ANN improves the MSE and R 2 values of the explicit equation developed using GA by 44% and 12% for the test data while GP enhances the corresponding values by 62% and 9% for the train data. Finally, the results demonstrate that not only artificial intelligence models considerably improve bridge afflux estimation than the explicit equations but also the suggested equations significantly improve the accuracy of the available explicit ones.

COVID-19 Outbreak: Application of Multi-gene Genetic Programming to Country-based Prediction Models

“…In essence, MGGP consists of several genes, which corresponds to each GP tree (13). Basically, GP and MGGP comprise of a tree-based architecture that provides an implementation of various functions and variables in light of finding a suitable expression between input and output data (14).…”

Assessment of Artificial Intelligence Models for Estimating Lengths of Gradually Varied Flow Profiles

“…Artificial neural network (ANN) is a well-documented AI model and has been successfully applied to various problems in water resources and hydraulic engineering [34,35]. Basically, it consists of three layers, named as input, hidden, and output layers, while each layer includes some components called neurons.…”

“…GP has a tree-like structure in which a variety of mathematical functions and variables may be adopted to seek for an appropriate relationship between the input and output data. As a result of these characteristics, Discipulus [37] software, which has been used for applying GP in the literature [35], was exploited to many problems in the fields' water resources and hydraulic engineering. e input data given to this program include u and N, while the output data were F(u, N).…”

Review of new flow friction equations: Constructing Colebrook’s explicit correlations accurately

“…The first five approximations of 𝜔(𝑥) − 𝑥; Eqs. (8)(9)(10)(11)(12) are based on the series expansion of about infinity by Corless et al [6,45]. These approximations are expressed in terms of 𝑠 𝑖 (𝑥) functions from Eqs.…”

“…Praks and Brkić [8] already developed approximations of the Colebrook equation based on symbolic regression analyses. Symbolic regression is a classic interpretable machine learning method by bridging input data using mathematical expressions composed of some basic functions [9][10][11][12][13][14][15][16]. The study by Praks and Brkić [8] deals with symbolic regression with raw data based on the Colebrook equation solved iteratively and not through the Wright ω-function.…”