Development of a wide-range soft sensor for predicting wastewater BOD5 using an eXtreme gradient boosting (XGBoost) machine

Ching, Phoebe Mae L.; Zou, X.; Wu, Di; So, Richard H. Y.; Chen, G.H.

doi:10.1016/j.envres.2022.112953

Cited by 47 publications

(23 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each leaf in a tree represents a numerical weight, and each sample is assigned to a set of leaves based on the values of its input variables. The model’s estimated output for that sample is obtained by adding the sum of the leaves assigned to that sample for each regression tree [ 18 ]. Detailed information about XGBoost is presented in Supplementary Text S2 .…”

Section: Methodsmentioning

confidence: 99%

“…XGBoost, as an ensemble model, makes estimations using the average of a large number of simple models and is capable of capturing complex information of data. It has been widely used in water quality predictions [ 18 , 19 , 20 ]. However, few studies about these two deep learning methods focused on predicting the natural degradation of DCE in groundwater.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

Xia

Jiang

Kong

et al. 2022

IJERPH

View full text Add to dashboard Cite

Chlorinated aliphatic hydrocarbons (CAHs) are widely used in agriculture and industries and have become one of the most common groundwater contaminations. With the excellent performance of the deep learning method in predicting, LSTM and XGBoost were used to forecast dichloroethene (DCE) concentrations in a pesticide-contaminated site undergoing natural attenuation. The input variables included BTEX, vinyl chloride (VC), and five water quality indicators. In this study, the predictive performances of long short-term memory (LSTM) and extreme gradient boosting (XGBoost) were compared, and the influences of variables on models’ performances were evaluated. The results indicated XGBoost was more likely to capture DCE variation and was robust in high values, while the LSTM model presented better accuracy for all wells. The well with higher DCE concentrations would lower the model’s accuracy, and its influence was more evident in XGBoost than LSTM. The explanation of the SHapley Additive exPlanations (SHAP) value of each variable indicated high consistency with the rules of biodegradation in the real environment. LSTM and XGBoost could predict DCE concentrations through only using water quality variables, and LSTM performed better than XGBoost.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

Xia

Jiang

Kong

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…The splitting algorithm [ 26 ] based on the above function is used to find the best split in Xgboost by

…”

Section: The Fused Classification Algorithm Based On Xgboost For Thre...mentioning

confidence: 99%

Improved Multiclassification of Schizophrenia Based on Xgboost and Information Fusion for Small Datasets

Zhu

Shen

Zhang

2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

To improve the performance in multiclass classification for small datasets, a new approach for schizophrenic classification is proposed in the present study. Firstly, the Xgboost classifier is introduced to discriminate the two subtypes of schizophrenia from health controls by analyzing the functional magnetic resonance imaging (fMRI) data, while the gray matter volume (GMV) and amplitude of low-frequency fluctuations (ALFF) are extracted as the features of classifiers. Then, the D-S combination rule of evidence is used to achieve fusion to determine the basic probability assignment based on the output of different classifiers. Finally, the algorithm is applied to classify 38 healthy controls, 16 deficit schizophrenic patients, and 31 nondeficit schizophrenic patients. 10-folds cross-validation method is used to assess classification performance. The results show the proposed algorithm with a sensitivity of 73.89%, which is higher than other classification algorithms, such as supported vector machine (SVM), logistic regression (LR), K -nearest neighbor (KNN) algorithm, random forest (RF), BP neural network (NN), classification and regression tree (CART), naive Bayes classifier (NB), extreme gradient boosting (Xgboost), and deep neural network (DNN). The accuracy of the fusion algorithm is higher than that of classifier based on the GMV or ALFF in the small datasets. The accuracy rate of the improved multiclassification method based on Xgboost and fusion algorithm is higher than that of other machine learning methods, which can further assist the diagnosis of clinical schizophrenia.

show abstract

“…The treated water (Test 1) shows a reduction in organic pollution in terms of COD with an abatement rate of 89% with COD content of 104 mg/l, a value which complies with the regulations in force (500 mg /l) while the initial COD of the sample before treatment is around 934 mg/l. This maximum reduction in the organic load is explained by the significant adsorption properties of hearth ashes and fly ash which contains a high content of silica, an important adsorbent with a high electrical polarity and mineral elements, in particular oxides of iron and aluminum (Ching et al 2022;Bellarbi et al 2017).…”

Section: Abatement Of Cod Bod5 and Suspended Mattermentioning

confidence: 99%

“…The wastewater was considered of the most important sources of surface water and groundwater pollution, especially for agricultural soils. The detergent manufacturing industry is one of the most water consumption industries and generates waste consisting of organic and inorganic molecules, usually with color problems, high concentrations of BOD5, COD, suspended solids, and high toxicity (Ching et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Monitoring treatment of industrial wastewater using conventional methods and Impedance spectroscopy

Hafidi

Mortadi

Graich

et al. 2022

Preprint

View full text Add to dashboard Cite

In this work, we treated wastewater from the detergent manufacturing industry on natural carriers and by-products from a coal-fired thermal power plant. The filtration was carried out by infiltration- percolation using a vertical cylindrical column manufactured in our laboratory. The main parameters analyzed before and after treatment are: suspended matter (SM), chemical oxygen demand (COD), biochemical oxygen demand (BOD5) and pH. This treatment system achieved a reduction of 89% COD, 73% BOD5, 54% SS and (66-99%) heavy metals. The COD/BOD5 rejection ratio before treatment, which was greater than 4.24, has become less than 1.73. Thus, impedance measurements of the wastewater before and after treatment were carried out. The results of the electrical parameters deduced from the impedance spectra show a good correlation with the parameters obtained by the classical methods.

show abstract

Development of a wide-range soft sensor for predicting wastewater BOD5 using an eXtreme gradient boosting (XGBoost) machine

Cited by 47 publications

References 36 publications

Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

Prediction of Dichloroethene Concentration in the Groundwater of a Contaminated Site Using XGBoost and LSTM

Improved Multiclassification of Schizophrenia Based on Xgboost and Information Fusion for Small Datasets

Monitoring treatment of industrial wastewater using conventional methods and Impedance spectroscopy

Contact Info

Product

Resources

About