Seasonal Short‐Term Prediction of Dissolved Oxygen in Rivers via Nature‐Inspired Algorithms

Abstract

This study challenges the use of three nature-inspired algorithms as learning frameworks of the adaptive-neuro-fuzzy inference system (ANFIS) machine learning model for short-term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography-based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R 2 parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R 2 ), root-mean-square error (RMSE), Nash-Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all-nature-inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS-PSO and ANFIS-BOA provide slightly better results than the other ANFIS models.

Evaluation of some Physical and Chemical Properties of Ground Water in Alshirqat District, Salaheddin province, Iraq

“…507), chloride P≤ 0.01 (r = 0.355), and magnesium P≤ 0.01 (r = 0.359). The high level of sodium made most ground water samples unsuitable for human uses (Alexander et al,2019;Fadaee et al,2020). Our results are like other reports (Amen et al, 2019;Mahdiand Al-Juboory,2021;Nisaf and Jwad,2015;Salih et al,2019).…”

“…There are significant negative correlation P≤ 0.05 between dissolved oxygen of ground water sample and temperature of areas around the wells (r= -0.367), and temperature of areas around the wells (r= -0.367). This is reflecting the growth of microorganism with increase of temperature (Alkam et al,2009;Fadaee et al,2020;Jabari and, Al -Beity ,2021). The dissolved oxygen is important criteria in water to dissolve the organic material and oxidation of toxin and bad odor (Mahdiand Al-Juboory,2021), Our results are like other reports (Abdul Jabarand AL-Obaedy,2011;Mahdiand Al-Juboory,2021;Salaudeen et al,2018).…”

Online sequential extreme learning machine in river water quality (turbidity) prediction: a comparative study on different data mining approaches

“…The advancements in novel computational tools and machine learning circumvent this limitation in modelling hydrological and environmental engineering (Adnan et al ., 2020; Fadaee et al ., 2020; Zounemat‐Kermani et al ., 2020). Such applications include a wide variety of problems including the prediction of hydrological variables such as precipitation, evaporation, streamflow and environmental hazards (Choubin et al ., 2019a; 2019b).…”

Factors driving the implementation of the ‘Local New Year’ policy to prevent COVID-19 in China

“…Cp method is proposed by Mallows’ Cp. Mallows used Cp value to evaluate the optimal combination of a linear regression model based on the assumption of ordinary least square method (Fadaee et al, 2020 ). It is based on the original regression model, and the Cp statistical value of a sub-regression model can be defined as: …”