Biochemical oxygen demand prediction in wastewater treatment plant by using different regression analysis models

BAKİ, Osman Tuğrul; Akdemir, Banu Yilmaz Ummukulsum Ozel; Aras, Egemen; Akdemir, Ümmükülsüm Özel; Yilmaz, Banu

doi:10.5004/dwt.2019.24158

Cited by 11 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies (Baki et al, 2019; Dogan et al, 2009; Oliveira‐Esquerre et al, 2002) used ML techniques such as classical regression analysis (CRA), multivariate adaptive regression splines (MARS), artificial bee colony (ABC), teaching‐learning based optimization (TLBO), ANN, and PCA for predicting BOD in water systems that resulted in an R 2 value within a range of 0.36–0.87. The algorithms used in this study are some of the strongest ML algorithms with diverse working mechanisms.…”

Section: Resultsmentioning

confidence: 99%

“…Other studies (Ahmed et al, 2019; Babbar & Babbar, 2017; Bui et al, 2020; Chen et al, 2020; Hameed et al, 2017; Sakizadeh, 2016; Wang et al, 2017) used ML techniques to predict water quality based on water quality index (WQI). Some specific ML methods have been explored for the prediction of BOD (Baki et al, 2019; Dogan et al, 2009; Fathima et al, 2014; Khaled et al, 2018; Kim et al, 2020; Noori et al, 2015; Solgi et al, 2017). Emamgholizadeh et al (2013) applied ANN and ANFIS models for predicting BOD 5 , COD, and DO in a river system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of 5‐day biochemical oxygen demand in the Buriganga River of Bangladesh using novel hybrid machine learning algorithms

Nafsin

2022

Water Environment Research

View full text Add to dashboard Cite

Biochemical oxygen demand (BOD) is one of the most important variables indicating stream pollution with a severe condition of organic loading and maintaining aquatic life in ecosystems. Advanced monitoring techniques such as machine learning (ML) methods have been developed for an accurate, reliable, and cost-effective prediction of BOD. This study investigated the effectiveness of four stand-alone ML algorithms, namely, artificial neural network (ANN), support vector machine (SVM), random forest (RF), and gradient boosting machine (GBM), and six novel hybrid algorithms, namely, RF-SVM, ANN-SVM, GBM-SVM, RF-ANN, GBM-ANN, and RF-GBM, in predicting BOD of the Buriganga river system of Bangladesh. The feature importance analysis of RF algorithm indicated that chemical oxygen demand (COD), total dissolved solids (TDS), conductivity, total solids (TS), suspended solids (SS), and turbidity are the most influential parameters for predicting BOD 5 . The significance of this study is the application of the novel hybrid models that resulted in higher prediction success; RF-SVM with the highest R 2 value (0.908). The employed novel hybrid ML models can be particularly useful for efficient and systematic data management, water pollution control, and prevention in developing countries such as Bangladesh. Practitioner Points• Investigated the efficiency of four stand-alone and six novel hybrid ML models for predicting BOD in a river of Bangladesh.• The significance of this study is the application of the six novel hybrid models that resulted in higher prediction success.• The best three prediction models were RF-SVM, ANN-SVM, and GBM-SVM with a prediction success of 91%, 89.6%, and 88.8% respectively.• ML models indicated COD, conductivity, TDS, TS, SS, and turbidity as the most influential variables for predicting BOD.• The novel hybrid models can be useful for developing countries for efficient systematic data management, pollution control, and prevention strategies.Nabila Nafsin is a member of the Water Environment Federation (WEF).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of 5‐day biochemical oxygen demand in the Buriganga River of Bangladesh using novel hybrid machine learning algorithms

Nafsin

2022

Water Environment Research

View full text Add to dashboard Cite

show abstract

“…Among its advantages are its ability to identify non-linear relationships in the data, to generate simple and more easily interpreted models from a large number of input variables, to show their relative importance, and to be computationally efficient compared to other techniques [12][13][14]. In the field of WWTPs, it has recently been used in different studies to predict the biochemical and chemical oxygen demand, the nitrogen, phosphorus and total suspended solids concentration [7,15], the activated sludge sedimentation capacity [15] or cost reduction [16].…”

Section: Methodsmentioning

confidence: 99%

“…The initial pre-treatment phase is of great importance for the proper functioning of WWTP (wastewater treatment plants) [1]; however, as indicated by several authors [2,3], the next steps of these facilities have been studied further given their great impact on water recovery. Parameters such as pH, chemical oxygen demand (COD), biochemical oxygen demand (BOD) and suspended solids (SS) in later stages have been the subject of numerous studies [4][5][6][7]. In contrast, the pretreatment stage has been studied much less, and efficient operation is considered to primarily depend on a good initial plant design and proper operations management.…”

Section: Introductionmentioning

confidence: 99%

Sand Content Prediction in Urban WWTPs Using MARS

Pérez

Fernández

et al. 2020

Water

View full text Add to dashboard Cite

The pre-treatment stage of wastewater treatment plants (WWTP), where most of the larger waste, including sand and fat, is removed, is of great importance for the performance and durability of these plants. This work develops a model that predicts the sand content that reaches the plant. For this purpose, data were collected from one operation year of the Villapérez Wastewater Treatment Plant located in the northeast of the city of Oviedo (Asturias, Spain) and the MARS (Multivariate Adaptive Regression Splines) method was used for modelling. The accuracy of the MARS model developed using the determination coefficient is R2 = 0.74 for training data and R2 = 0.70 in validation data. These results indicate that it is possible to predict trend changes in sand production as a function of input variables changes such as flow rate, pH, ammonia, etc. This will prevent the plant from possible operational problems, as actions could be taken, such as starting up more pre-treatment lines or emptying the containers, so that the arrival of the sand can be assumed without any problem. In this way, the possibility of letting sand contents over the established limits pass that could affect the following processes of the treatment plant is avoided.

show abstract

“…Recent investigations have focused on the development of numerical models using machine learning techniques for estimating the Biological Oxygen Demand for 5 days (BOD5) of wastewater [18,19], but those models are complicated and difficult to use. However, none of the previous studies have used the Design of Experiments (DOE) technique to produce an adequate model for predicting the parameters of wastewater.…”

Section: Introductionmentioning

confidence: 99%

Wastewater Assessment and Biochemical Oxygen Demand Value Prediction from Mining Operations: A Case Study

Zenati

Djellali

Sarker

2023

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Wastewater is a byproduct of industrial or household waste processes, and its contamination level must be determined before treatment. Discharges of liquid effluents generated by mining operations, one of the most prevalent forms of industrial waste water, pose a risk to human health and the environment. This study evaluates the physicochemical quality of industrial liquid effluent discharges from the Boukhadra mine (Algeria). Samples were collected from the washing water to identify the level of contamination of these liquid discharges and to measure physicochemical parameters such as temperature (T), hydrogen potential (pH), Electrical Conductivity (EC), Suspended Solids (SS), Chemical Oxygen Demand (COD), Biological Oxygen Demand for 5 days (BOD5), Oils and Greases (O&G), iron (Fe+2) and Kjeldahl Nitrogen (NTK). It was found that the concentration values of those effluents exceeded the maximum contamination limits specified by international industrial waste standards. A simple and reliable prediction model was developed to estimate DBO5, based on MES, COD, and O&G, by using classical regression analysis and fitting Design of Experiments (DOE) methodology. When comparing the analytical results, it was found that the quadratic model provided a better estimation, with a high correlation coefficient (R2) of 0.9976. The parameters determined in this study will enable engineers to quickly estimate the degree of wastewater contamination and choose adequate treatment strategies.

show abstract

Biochemical oxygen demand prediction in wastewater treatment plant by using different regression analysis models

Cited by 11 publications

References 39 publications

Prediction of 5‐day biochemical oxygen demand in the Buriganga River of Bangladesh using novel hybrid machine learning algorithms

Prediction of 5‐day biochemical oxygen demand in the Buriganga River of Bangladesh using novel hybrid machine learning algorithms

Sand Content Prediction in Urban WWTPs Using MARS

Wastewater Assessment and Biochemical Oxygen Demand Value Prediction from Mining Operations: A Case Study

Contact Info

Product

Resources

About