Prediction of Different Water Quality Parameters by Machine Learning Technique

Dissolved oxygen (DO) as one of the most fundamental parameters of water quality plays a vital role in aquatic life. This study was conducted to predict DO, biological oxygen demand (BOD), and chemical oxygen demand (COD) in an intensive rainbow trout rearing system with different biomass (B). The multilayer perceptron (MLP) and the radial basis function (RBF) neural networks were employed for evaluating the impacts of food parameters (crude protein (CP), consumed feed (CF)), fish parameters (different values of B, and weight gain (WG)), and water quality parameters including temperature (T) and flow rate (Q) on variation of DO, BOD, and COD concentrations. This study's results showed that although both MLP and RBF neural networks are capable to estimate DO, BOD, and COD concentrations, RBF neural network showed better performance compared to MLP neural network. The results of sensitivity analysis indicated that the parameter CF has the highest effect on DO concentration estimation. Independent variables CF, CP, WG, and B showed the highest to the lowest rank of impacts on BOD estimation, respectively. The results also illustrated a decreasing trend of the effects on the estimation error of COD changes simulation by all independent variables, including B, T, WG, CF, CP, and Q, respectively. RBF neural network based on better stability and generalization ability with average root mean square error (RMSE) and mean absolute percentage error (MAPE) values of less than 0.12 and 3% was superior to MLP in DO, BOD, and COD concentration prediction. Moreover, CF was identified as the most effective factor in estima12tion process. Based on the present study results, there are direct relationships between DO, BOD, and COD concentrations and water quality parameters, fish parameters, and food parameters. Food parameters relative to fish and water quality parameters imposed the greatest effects. Improvement in feeding process such as application of intelligence feeding methods and change in fish diet and feeding time can considerably reduce losses in production system. Graphical abstract.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

It is highly essential that municipal wastewater is treated before its discharge and reuse in order to meet the standard requirements for safe marine life and for farming and industries. It is beneficial to use reclaimed water, since availability of fresh water is inadequate. An investigation was conducted on the Jamnagar Municipal Corporation Sewage Treatment Plant (JMC-STP) to develop a feedforward artificial neural network (FF-ANN) model. It is an alternate for the modelling/ prediction of JMC-STP to circumvent over the versatile physical, chemical, and biological treatment process simulations. The models were developed to predict effluent quality parameters through influent characteristics. The parameters are pH, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total suspended solids (TSS), total Kjeldahl nitrogen (TKN), ammonium nitrogen (AN) and total phosphorus (TP). The correlation coefficient RTRAINING and RALL were calculated for all parametric models. The MAD (mean absolute deviation), MSE (mean square error), RMSE (root mean square error) and MAPE (mean absolute percentage error) were evaluated for FF-ANN models. This proves to be a useful tool for the plant management to optimize the treatment quality as it enhances the performance and reliability of the plant. The simulation results were validated through the measured values.

This study investigated environmental assessments of leachate containing formaldehyde from medium density fiberboard (MDF) disposed in laboratory-scale simulated landfills. Environmental impact assessment of leachate was conducted by measuring formaldehyde, toxicity, biochemical oxygen demand (BOD), chemical oxygen demand (COD), bacterial enumeration, and pH. Amount of formaldehyde in leachate from MDF in soil decreased to the level of soil only treatment by 28 days, and toxicity decreased as the amount of formaldehyde decreased. BOD and COD levels in leachate from the treatments containing MDF exceeded permissible discharge levels of BOD or COD throughout the experimental period. The pH levels of all treatment were within permissible discharge range except on day 0. Fewer bacteria were observed in leachate from MDF in soil treatment than other treatments (MDF only, cured UF resin in soil, and soil only). Consequently, the leachate from disposal of MDF in soil detrimentally affect on environment. However, soil buffered formaldehyde leaching and pH on leachate in this study. Waste MDF may be required the pre-water soaking treatment for leaching formaldehyde to reclaim on land.

This article uses machine learning techniques as fuzzy and neuro-fuzzy ANFISs, to develop and compare prediction models capable of relating pregnant women’s exposure to air pollutants, such as Nitrogen Dioxide and Particulate Matter, the mother’s age, and the number of prenatal consultations to the incidence of premature birth. In the current literature, studies can be found that relate prematurity to the exposure of pregnant women to NO2, O3, and PM10; to Toluene and benzene, mainly in the window 5 to 10 days before birth; and to PM10 in the week before birth. Both models used logistic regression to quantify the effects of pollutants as a result of premature birth. Datasets from Brazil—Departamento de Informatica do Sistema Único de Saúde (DATASUS) and Companhia Ambiental do Estado de São Paulo (CETESB)—were used, covering the period from 2016 to 2018 and comprising women living in the city of São José dos Campos (SP), Brazil. In order to evaluate and compare the different techniques used, evaluation metrics were calculated, such as correlation (r), coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and Mean Absolute Error (MAE). These metrics are widely used in the literature due to their ability to evaluate the robustness and efficiency of prediction models. For the RMSE, MAPE, MSE, and MAE metrics, lower values indicate that prediction errors are smaller, demonstrating better model accuracy and confidence. In the case of (r) and R2, a positive and strong result indicates alignment and better performance between the real and predicted data. The neuro-fuzzy ANFIS model showed superior performance, with a correlation (r) of 0.59, R2 = 0.35, RMSE = 2.83, MAPE = 5.35%, MSE = 8.00, and MAE = 1.70, while the fuzzy model returned results of r = 0.20, R2 = 0.04, RMSE = 3.29, MSE = 10.81, MAPE = 6.67%, and MAE = 2.01. Therefore, the results from the ANFIS neuro-fuzzy system indicate greater prediction capacity and precision in relation to the fuzzy system. This superiority can be explained by integration with neural networks, allowing data learning and, consequently, more efficient modeling. In addition, the findings obtained in this study have potential for the formulation of public health policies aimed at reducing the number of premature births and promoting improvements in maternal and neonatal health.

The Internet of Things (IoT) based water quality monitoring system, mostly uses cost-effective sensors with a faster response time. Few water quality parameters such as Chemical Oxygen Demand (COD), Biological Oxygen Demand (BOD), Chlorine (Cl), and Total Phosphorous, hard to be measured online, soft sensing techniques are used as an alternate solution to this. This paper studies different Machine Learning (ML) models to prefer a suitable one that can identify the non-linearity of the dependency and establish a correlation between input and output parameters to design a COD soft sensor. The selected models are deployed in the proposed IoT architecture to predict the COD in real-time. More than 16000 data samples from the river Ganga with ten independent water quality parameters are collected and tested to validate the proposed IoT architecture. The paper compares the results of a few best performing ML algorithms like Multiple Linear Regression, Multilayer Perceptron, Support Vector Machine, Random Forest and K-Nearest Neighbour (KNN). Where, KNN technique proves to be the most efficient one in the prediction of COD in terms of response time and other performance matrices like R, R2, MSE, MAE, and RMSE. Finally, the preferred model (KNN) with the IoT setup is deployed and tested at the Sewage Treatment Plant (STP) outlet of the authors’ institute to verify the accuracy of the COD in real-time.

Enhancing riverine load prediction of anthropogenic pollutants: Harnessing the potential of feed-forward backpropagation (FFBP) artificial neural network (ANN) models

This paper aims to: (1) develop models based on adaptive neuro-fuzzy inference system (ANFIS) able to predict five-day biochemical oxygen demand (BOD5) in Ouizert reservoir; (2) demonstrate the capability of the ANFIS in the practical issues of water quality management; (3) choose the optimal combination of input variables to improve the model performance; (4) compare two ANFIS partition methods, namely subtractive clustering called ANFIS-SC and grid partitioning, called ANFIS-GP. The models were developed using experimental data which were gathered during a ten-year period, at a mean monthly time step (scale). The input data used are total inorganic nitrogen, chemical oxygen demand (COD), total dissolved solid, dissolved oxygen and phosphate; the output is five-day biochemical oxygen demand (BOD5). Results reveal that ANFIS-SC models gave a higher correlation coefficient, a lower root mean square errors (RMSE) and mean absolute errors than the corresponding ANFIS-GP models. We can conclude that ANFIS-SC has supremacy over ANFIS-GP in terms of performance criteria and prediction accuracy for BOD5 estimation. The results showed that COD is the more effective variable for BOD5 estimating than other parameters, hence COD is the major driving factor for BOD5 modelling through ANFIS.

Most water management methodologies require comprehensive studies and thus, entail voluminous data, time, and scientific expertise. Sensorial evaluation techniques were thus, considered as these represent methods with minimal cost and can involve the local communities. This study applied the Sarno River Visual Assessment Protocol (SRVAP), a modified version of the Stream Visual Assessment Protocol developed by the United States Department of Agriculture, to Sarno River, Italy and tested its reliability as a river assessment tool. SRVAP scores has a statistically significant positive correlation with Chemical Oxygen Demand (COD) and shows that local knowledge is important and increases the viability of incorporating public participation in the evaluation. Correlation between SRVAP and organic content greatly increased barring seasonal variability and a significant positive relationship was found between SRVAP score and Biochemical Oxygen Demand (BOD) and COD during spring, as well as during summer. The resulting regression equations may be used as rapid estimates of COD and BOD levels in Sarno River for the seasons of spring and summer.

Water is essential for living things, and thus international regulations or standards are set to reduce and prevent pollution. The purpose of this study was to evaluate water quality and to compare the concentration by variables over a two-year period. Sampling was conducted for one month at five sites along the Wangsukcheon river in Gyeonggi-do, Korea. General measurements (dissolved oxygen, DO), pH, temperature, electrical conductivity (EC) were taken using a YSI 556. The biochemical oxygen demand (BOD), chemical oxygen demand (COD), and suspended solids (SSs) were analyzed manually according to the standard method. The concentration of most elements was lower in 2013 than in 2012. Most of the time, the patterns of concentration for the five sites increased from summer to winter. In addition, the levels of COD, BOD, total nitrogen (TN), total phosphorus (TP), and EC at site E were higher than at the other sites. In the correlation analysis results, TN and EC were positively correlated, but DO and temperature (TEM) were negatively correlated. Therefore, this study suggests that some management is required to clean the water and improve the quality at downriver locations in the winter season.

Performance evaluation of machine learning techniques in predicting cumulative absolute velocity

The rapid evolution of Internet of Things (IoT) applications demands advancements in wireless communication technologies to handle increasing data rates and connectivity requirements. This article presents our novel research on utilizing machine learning techniques to enhance the efficiency of MIMO antennas for Wireless Communication and IoT applications in the Terahertz (THz) frequency band. Our research assesses antenna performance using various methodologies, including simulation and RLC equivalent circuit models. The proposed design operates at 6.51 THz, 7.48 THz, and 8.46 THz, with bandwidths of 0.7 THz, 0.69 THz, and 0.89 THz, respectively. It features a maximum gain of 13.53 dBi and compact dimensions of 160 × 75 μm2. Additionally, it demonstrates excellent isolation, exceeding −32 dB, −44 dB, and −45 dB across these bands, with over 96.5% efficiency in all operating bands. By designing a similar RLC circuit in ADS and simulating it, we validated the results obtained from CST. Both CST and ADS simulators produced comparable reflection coefficients. Furthermore, several machine learning algorithms were applied to test the design. Various metrics, including variance score, R-squared, mean squared error (MSE), mean absolute error (MAE), and root mean square error (RMSE), were used to evaluate the machine learning models. Among the five models analyzed, the Gradient Boosting Regression model exhibited the lowest error rates (4.94% MAE, 6.60% MSE, and 4.13% RMSE) and achieved the highest accuracy, exceeding 98% in predicting isolation. Considering all these factors, it is evident that this antenna is an excellent choice for the THz band in 6G wireless communication.

Hypochlorite which is generated electrolytically from seawater under optimized conditions was evaluated for its (i) bacterial sensitivity to Escherichia coli in comparison to commercial bleaches and (ii) utilization in the treatment of sanitary effluent. Effective bacterial growth inhibition occurs using the hypochlorite containing seawater. Waste water samples from sewage treatment plant, from two sampling points, i.e., one after primary treatment (Sample 1) and the second prior to the discharge of the effluent into the river (Sample 2) were analyzed. Sample 1 was subjected to the hypochlorite treatment and Sample 2 was used to assess the treatment work's efficiency. Quality parameters namely Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Dissolved Solids (DS), Suspended Solids (SS) were monitored at each sampling point. The addition of hypochlorite to sample at point 1 lowered the BOD and COD levels and improved the water quality.

Biological approaches and coagulation are frequently used to reduce the chemical oxygen demand (COD) for treatment of ceramic effluent water. The technology known as the moving bed biofilm reactor (MBBR) can accomplish this goal. Further, the process of emulsification-aided innovative MBBR using biosurfactants can be proposed for ceramic effluent treatment. In a step-by-step upgrading scheme, biosurfactants and a consortia of halophilic and halotolerant microbial culture was utilized for the treatment of the effluent water. Over the course of 21 days, a progressive decrease in COD of up to 95.79% was achieved. Over the next 48 h period, the biochemical oxygen demand (BOD) was reduced by 98.3%, while total suspended solids (TSS) decreased by 79.41%. With the use of this innovative MBBR technology, biofilm formation accelerated, lowering the COD, BOD, and TSS levels. This allows treated water to be used for further research on recycling it back into the ceramics sector and repurposing it for agricultural purposes. PRACTITIONER POINTS: Implementation of modified MBBR technology for the treatment of effluent water. Biosurfactants could reduce in the organic and inorganic loads. Increase in MLSS values with COD removal observed. The plant operations without the use of chemical coagulants was effective with biosurfactants. Biofilm formation on carriers was scraped and thepresence of surfactin and rhamnolipid was confirmed.

This study investigated the efficacy of membrane bioreactor (MBR) technology in treating saline industrial wastewater, focusing on the impact of the organic loading rate (OLR) and the food-to-microorganism (F/M) ratio on treatment performance. This research utilized saline industrial wastewater from Al-Hasa, which had salinity levels ranging from 5000 to 6900 mg/L. It explored treatment processes at varying Chemical Oxygen Demand (COD) concentrations of 800, 1400, and 2000 mg/L, corresponding to an OLR of 0.80 ± 0.05, 1.41 ± 0.07, and 1.98 ± 0.12 g COD/L, respectively. The average F/M ratios used were 0.20, 0.36, and 0.50 g COD/g MLSS·d, maintaining a constant Sludge Residence Time (SRT) of 12 days, a hydraulic retention time (HRT) of 24 h (hrs.), and a flux of 10 L/m2·h. The MBR system demonstrated high COD removal efficiencies, averaging 95.7 ± 1.6%, 95.5 ± 0.4%, and 96.1 ± 0.3%, alongside Biochemical Oxygen Demand (BOD) removal rates of 98.3 ± 0.2%, 99.8 ± 0.1%, and 98.5 ± 0.1%, respectively. However, an increased OLR led to elevated residual COD and BOD levels in the treated effluent, with COD concentrations reaching 34.2 ± 12.8, 63.3 ± 5.9, and 76.5 ± 5.4 mg/L, respectively. This study also reveals a significant decline in ammonia and Total Kjeldahl Nitrogen (TKN) removal efficiencies as OLR increases, dropping from 96.1 ± 0.5% to 80.2 ± 0.9% for ammonia and from 83.8 ± 3.4% to 65.8 ± 2.3% for TKN. Furthermore, higher OLRs significantly contribute to membrane fouling and elevate the transmembrane pressure (TMP), indicating a direct correlation between OLRs and operational challenges in MBR systems. The findings suggest that for optimal performance within the Saudi disposal limits for industrial wastewater, the MBR system should operate at an F/M ratio of ≤0.33 g COD/g of Mixed Liquor Suspended Solid (MLSS)·d. This study underscores the critical role of the OLR and F/M ratio in treating saline industrial wastewater using MBR technology, providing valuable insights for enhancing treatment efficiency and compliance with environmental standards.