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

Abstract

The study of water surface profiles is beneficial to various applications in water resources management. In this study, two artificial intelligence (AI) models named the artificial neural network (ANN) and genetic programming (GP) were employed to estimate the length of six steady GVF profiles for the first time. The AI models were trained using a database consisting of 5154 dimensionless cases. A comparison was carried out to assess the performances of the AI techniques for estimating lengths of 330 GVF profiles in both mild and steep slopes in trapezoidal channels. The corresponding GVF lengths were also calculated by 1-step, 3-step, and 5-step direct step methods for comparison purposes. Based on six metrics used for the comparative analysis, GP and the ANN improve five out of six metrics computed by the 1-step direct step method for both mild and steep slopes. Moreover, GP enhanced GVF lengths estimated by the 3-step direct step method based on three out of six accuracy indices when the channel slope is higher and lower than the critical slope. Additionally, the performances of the AI techniques were also investigated depending on comparing the water depth of each case and the corresponding normal and critical grade lines. Furthermore, the results show that the more the number of subreaches considered in the direct method, the better the results will be achieved with the compensation of much more computational efforts. The achieved improvements can be used in further studies to improve modeling water surface profiles in channel networks and hydraulic structure designs.

MATLAB‐based program for computation of open‐channel flow profiles

“…The calculation formula can be expressed as [32]: $$$\Delta {s}_{1-2}=\frac{{E}_{S2}-{E}_{S1}}{r(i-\bar{J})},$$$where E s , 1(2) and r represents the specific energy, sections 1(2) and directional coefficient(when Section 1 is upstream, r is equal to 1, otherwise −1), respectively. In this method, solving the distance between specific water depths is the core problem, and various attempts to solve this problem can be divided into the following five groups: (1) semianalytical methods, (2) analytical solutions, (3) numerical schemes, (4) artificial intelligence (AI) models, and (5) optimization techniques [19]. The Newton iteration method starts from the control section with known water depth and calculates the water depth of the next section one by one.…”

Application of MGGP, ANN, MHBMO, GRG, and Linear Regression for Developing Daily Sediment Rating Curves

“…To be more precise, GP provides the opportunity of determining a prediction model with the aid of a tree-like structure and the GA search engine, while this application cannot be done with the exclusive use of GA and inevitably requires further coding on GA [32]. As a result, the fundamental steps of GP are those presumed in GA. As the classical GP has been paid quite considerable attention by researchers in different fields of research [33], a few modified variants of this ML method were developed. MGGP, as a modified version of GP, is capable of developing an estimation model between known input and output vectors.…”

Investigating Terrestrial Water Storage Response to Meteorological Drought in the Canadian Prairies

“…This index is recommended by the World Meteorological Organization (WMO). It was developed by [53] to quantify the rainfall shortage and to assess the drought state. It is based on the probability notions and is faithful to the spatial variability aspect of the drought [26,53].…”