Estimating effluent turbidity in the drinking water flocculation process with an improved random forest model

Wang, Dongsheng; Chang, Xuefeng; Ma, Kaiwei; Li, Zhixuan; Deng, Lianqing

doi:10.2166/ws.2021.213

Cited by 8 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Turbidity. Turbidity is a description of the state of water and whether solids are suspended in it or not [33]. The turbidity of water can be calculated by the light emitting characteristics of water, which represents the quality of waste discharge in regard to the colloidal matter.…”

Section: Methodsmentioning

confidence: 99%

Prediction of Quality of Water According to a Random Forest Classifier

Alomani¹,

Alhawiti²,

Alhakamy³

2022

IJACSA

View full text Add to dashboard Cite

Potable or drinking water is a daily life necessity for humans. The safety of this water is a concern in many regions around the world, since polluted waters are increasing and causing the spread of disease among populations. Continuous management and evaluation of the water which is meant for drinking is very essential and must be taken seriously. Often, the quality of water is evaluated through regular laboratory testing and analysis which can be tiresome and time consuming. On the other hand, advanced technologies using big data with the help of machine learning can have better results in terms of potability evaluation. For this reason, several studies have been conducted on predicting the quality of water and the several factors and classification that affect the prediction model. In this study, a random forest model was developed using PySpark classification to predict the potability of river water by relying on ten different features: pH, hardness, presence of solids, presence of chloramines, presence of sulfate, conductivity, organic carbon, trihalomethanes, turbidity, and finally potability. In addition, The developed model was able to predict water potability classification with a 1.0 accuracy, and 1.0 F1-score.

show abstract

Section: Methodsmentioning

confidence: 99%

Prediction of Quality of Water According to a Random Forest Classifier

Alomani¹,

Alhawiti²,

Alhakamy³

2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…In all, eight different genera (Fig. 3) of bacteria were isolated and identi ed as: Aeromonas (9), Bacillus (2), Corynebacterium (13) Although Escherichia coli was not detected in any of the ve rivers sampled, this fact does not depict complete absence of the organisms or other enteric bacteria, the high level of observed BOD and COD implies possible presence of faecal contamination which probably was not just detected in the water at the time of sampling. This nding correlates with the ndings of Odonkor and Addo (2018) in a study conducted in Ghana, where no E. coli strain was isolated from river water sources.…”

Section: Diversity Of Bacterial Species In Water Samples Of Riversmentioning

confidence: 99%

Bacterial isolates from Drinking water river sources exhibit multi-drug resistant trait

Popoola,

Ogwerel,

Oladipo

2024

Preprint

View full text Add to dashboard Cite

Freshwater habitat is a natural reservoir for antimicrobial resistance (AMR). AMR is known to pose serious human, animal, and environmental public health threats. This study aimed at evaluating the physicochemical and microbiological properties of five selected rivers (Apitipiti 1, Apitipiti 2, Apitipiti 3, Sogidi, and Aba Apa Akinmorin) in Oyo town, Nigeria, as well as the antibiotic resistance pattern of isolated bacterial species, using conventional methods. Most physicochemical parameters were within WHO and NIS permissible limits. Of the rivers, Sogidi had the highest microbial load (6.36 log CFU/mL) while Apititipiti 1 had the lowest (5.76 log CFU/mL). A total of thirty-three (32) bacterial species were isolated and identified as: Aeromonas (9), Bacillus (2), Corynebacterium (13), Lactobacillus (1), Pseudomonas (2), Staphylococcus (4), and Streptococcus (1). Pearson’s correlation matrix indicated that there were significant (p<0.05) interactions among pH, electrical conductivity, temperature, sulphate and chloride salts, BOD and COD. Of all these, 81.8 % were multidrug-resistant, with Corynebacterium kutscheri and Aeromonas spp. isolated from Apitipiti 2 and Aba Apa Akinmorin rivers respectively, exhibiting a relatively high antibiotic resistance of 90.9 %. This study reveals that these rivers maybe unfit for consumption as multidrug-resistant bacteria of public health risk were associated with them.

show abstract

“…Below are some examples showing the application of ML methods. Wang et al [6] conducted research on the estimation of effluent turbidity in the drinking water flocculation process. They used an improved random forest (IRF) model that consisted of both long-term and short-term components.…”

Section: Figure 3 Concentrations Of Manganese Iron and Ammonium In Ra...mentioning

confidence: 99%

“…Also, models based on ML methods have a certain degree of interpretability, and appropriate analysis methods are capable of mining the hidden physical meaning and chemical or some other information to deepen the understanding of water treatment processes methods [4], [5]. Some applications of ML can be seen in research made by Wang et al [6] where effluent turbidity in the drinking water flocculation process was estimated with an improved random forest model. In research made by Kim and Parnichkun [7] prediction of settled water turbidity and optimal coagulant dosage in drinking water treatment plant was done using a hybrid model of kmeans clustering and adaptive neuro-fuzzy inference system.…”

Section: Introductionmentioning

confidence: 99%

Prediction models for manganese, iron and ammonium in raw water for a drinking water treatment plant Butoniga (croatia)

Volf,

Krbavčić,

Sušanj Čule

et al. 2023

Eng. rev. (Online)

View full text Add to dashboard Cite

Drinking water treatment plant Butoniga is one of the main water supply facilities for potable water in Istria (Croatia). Water for treatment process is captured from the Butoniga reservoir which is a small and relatively shallow reservoir. As such, the reservoir is very sensitive to eutrophication and degradation processes caused by climate change and human activities in the watershed. In summer months during tourist season, when at highest water demand and lowest water level at the reservoir, the water temperature is the most critical parameter during treatment process. To capture colder water, raw water for treatment is taken from the lowest water intake, i.e. from the deepest layer in the Butoniga reservoir. This layer has another problem, namely increased concentrations of manganese, iron and ammonium under lower pH values. This study provides prediction models for manganese, iron and ammonium for seven days in advance, which are some of the most critical parameters during summer months and have significant influence on treatment process of raw water. For modelling purposes, machine learning software Weka was used to build models in form of model trees. Obtained prediction models for manganese, iron and ammonium have high accuracy compared to the measured data with a good prediction of the peak values. Therefore, obtained models can help in optimization of the treatment processes at the treatment plant, which are depending on the quality of raw water in Butoniga reservoir.

show abstract

Estimating effluent turbidity in the drinking water flocculation process with an improved random forest model

Cited by 8 publications

References 43 publications

Prediction of Quality of Water According to a Random Forest Classifier

Prediction of Quality of Water According to a Random Forest Classifier

Bacterial isolates from Drinking water river sources exhibit multi-drug resistant trait

Prediction models for manganese, iron and ammonium in raw water for a drinking water treatment plant Butoniga (croatia)

Contact Info

Product

Resources

About