Comparing the stream re-aeration coefficient estimated from ANN and empirical models / Comparaison d'estimations par un RNA et par des modèles empiriques du coefficient de réaération en cours d'eau

Abstract

Dissolved oxygen (DO) is one of the most useful indices of river's health and the stream re-aeration coefficient is an important input to computations related to DO. Normally, this coefficient is expressed as a function of several variables, such as mean stream velocity, shear stress velocity, bed slope, flow depth, and Froude number. However, in free surface flows, some of these variables are interrelated, and it is possible to obtain simplified stream re-aeration equations. In recent years, different functional forms have been advanced to represent the re-aeration coefficient for different data sets. In the present study, the artificial neural network (ANN) technique has been applied to estimate the re-aeration coefficient (K 2 ) using data sets measured at different reaches of the Kali River in India and values obtained from the literature. Observed stream/channel velocity, bed slope, flow depth, cross-sectional area and re-aeration coefficient data were used for the analysis. Different combinations of variables were tested to obtain the re-aeration coefficient using an ANN. The performance of the ANN was compared with other estimation methods. It was found that the re-aeration coefficient estimated by using an ANN was much closer to the observed values as compared with the other techniques.

Investigation of Deoxygenation Rate Determination in Cikakembang River, West Java, Indonesia

“…River discharge was obtained through calculations using flow velocity data, yielding values of 0.86 m 3 s -1 during rainy season and 0.252 m 3 s -1 during dry season. In this model, the value of the reaeration coefficient (k a ) used the equation from Jha et al (2004), while the dispersion coefficient (Ex) used the equation from Iwasa and Aya (1991); Jain and Jha (2005); Peruzzi et al (2021). Based on previous studies, combining these two coefficients provided adequate analysis results and was suitable for Cikakembang River (Polisar, 2023).…”

Prediction of suspended sediment loading by means of hybrid artificial intelligence approaches

“…Recently, researchers have looked for easier, cheaper and more reliable methods to estimate the SSL and decided to use this model (Ardıclıoglu et al 2007;Cigizoglu 2001;Tayfur and Guldal 2006). The ANN practices have been used in many branches of water supply applications successfully (Cigizoglu 2001;Cobaner 2011;Jain and Jha 2005;Kisi 2006; Schulze et al 2005), and it has been thought to give encouraging outcomes, especially in modeling the suspended sediment (Alp and Cigizoglu 2007;Ardıclıoglu et al 2007;Cigizoglu 2004;Jain 2001;Kisi 2008;Tayfur 2002;Tayfur and Guldal 2006;Zhu et al 2007). Tayfur and Guldal (2006) found an ANN model to estimate the daily amount of SSL in rivers.…”

Hybrid fuzzy and optimal modeling for water quality evaluation

“…It is a multiuse and powerful tool for modeling complex processes and characterizing uncertainty in water quality evaluation. Examples include combining the fuzzy sets theory and grey systems theory [Chang et al, 1996]; self-organizing maps and fuzzy sets theory [Lu and Lo, 2002]; ANN embedded Monte Carlo method [Zou et al, 2002]; and ANN and empirical models [Jain and Jha, 2005]. Another way to develop a hybrid model is to combine informational entropy theory, especially the principle of maximum entropy (POME), and engineering fuzzy set theory (EFST).…”