Assessment of removal rate coefficient in vertical flow constructed wetland employing machine learning for low organic loaded systems

Soti, Abhishek; Singh, Saurabh; Verma, Vishesh; Kulshreshtha, Niha Mohan; Brighu, Urmila; Kalbar, Pradip P.; Gupta, Akhilendra Bhushan

doi:10.1016/j.biortech.2023.128909

Cited by 4 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deeper beds (>0.5 m) enhance anoxic/anaerobic conditions, suited for the removal of specific pollutants. , Controlling the media depth at the design stage can help in the HFCW design for specific treatment needs. The classification of HFCWs based on temperature ranges (0–10, 10–15, 15–20, and 20–30 °C) helps understand the impact of temperature on CW performance . Temperature influences the microbial activity, reaction rates, and solubility of gases in water, which are all critical factors in the treatment processes within HFCWs.…”

Section: Results and Discussionmentioning

confidence: 99%

“…The k values of HFCWs can be calculated using the P - k - C * approach (eq ). k = 0.365 × P Q i A [ ( C normali − C * C e f f − C * ) 1 / P − 1 ] where C eff = effluent concentration (mg/L), C i = influent concentration (mg/L), C * = background concentration (mg/L), Q i = influent flow rate (m 3 /d), k = first-order areal rate coefficient (m/d), P = number of cells in series, dimensionless, and A = total wetland area (m 2 ).…”

Section: Methodsmentioning

confidence: 99%

“…The classification of HFCWs based on temperature ranges (0−10, 10−15, 15−20, and 20−30 °C) helps understand the impact of temperature on CW performance. 23 Temperature influences the microbial activity, reaction rates, and solubility of gases in water, which are all critical factors in the treatment processes within HFCWs. Lower temperatures (0−10 °C; Northern parts of Europe and America and parts of Asia) can slow down microbial metabolism and, consequently, the rate of pollutant degradation.…”

Section: Effect Of Design Parameters On Kmentioning

confidence: 99%

“…Lower temperatures (0−10 °C; Northern parts of Europe and America and parts of Asia) can slow down microbial metabolism and, consequently, the rate of pollutant degradation. 22,23 The moderate temperature range (10−20 °C; Southern Europe and the Americas, East Asia) is typically considered optimal for a balance between microbial activity and the viscosity of water, affecting the flow and aeration within the system. Higher temperatures (20−30 °C; Southern China, parts of Australia, and the northern and coastal areas of the Mediterranean) can enhance microbial activity and treatment efficiency but may also lead to increased evapotranspiration and potential oxygen depletion.…”

Section: Effect Of Design Parameters On Kmentioning

confidence: 99%

“…Higher temperatures (20−30 °C; Southern China, parts of Australia, and the northern and coastal areas of the Mediterranean) can enhance microbial activity and treatment efficiency but may also lead to increased evapotranspiration and potential oxygen depletion. 23,37 By classifying HFCWs according to these temperature brackets, it is possible to better understand and predict the performance of such systems under varying environmental conditions, thereby optimizing their design and operation for specific climatic regions. 23,41 The other classifications of HFCWs were carried out based on the depth of filter media (<0.2, 0.2−0.5, and >0.5 m) and temperature (0−10, 10−15, 15−20, and 20−30 °C).…”

Section: Effect Of Design Parameters On Kmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Application for Nutrient Removal Rate Coefficient Analyses in Horizontal Flow Constructed Wetlands

Singh,

Soti,

Kulshreshtha

et al. 2024

ACS EST Water

Self Cite

View full text Add to dashboard Cite

Land area optimization for horizontal flow constructed wetlands (HFCWs) with a low organic loading rate (OLR) needs special considerations as the microflora changes dramatically with the OLR. The P-k-C* approach does not lead to an accurate calculation of k-values in these wetlands. In this research, nonlinear machine learning models [Support Vector Regression (SVR), Random Forest (RF), and Artificial Neural Networks (ANN)] are applied to predict realistic k-values. Data from 37 low-OLR HFCWs (n = 544) were analyzed, and the k-values calculated for these wetlands were found to vary markedly (0.059−0.249 with an average of 0.113 ± 0.090 m/day). The classification of k-values based on the OLR, applied loading rate, and media depth leads to the reduction in standard deviations (SDs) from 83.40 to 35.27%. kvalues with the least SDs are needed for optimal design for low-OLR CWs. The SVR, RF, and ANN models were tested, and the best prediction efficiency on testing datasets was achieved through the ANN model with R 2 (k TKN )= 0.768 (RMSE = 0.067) for total Kjeldahl nitrogen (TKN), R 2 (k TN )= 0.835 (RMSE = 0.043) for total nitrogen (TN), and R 2 (k TP ) = 0.723 (RMSE = 0.087) for total phosphorus (TP). The outcome was validated using primary data from HFCWs, which also confirmed the superiority of the ANNbased model, which can be used for design customization of low-OLR HFCWs.

show abstract

Section: Results and Discussionmentioning

confidence: 99%