Decision Tree-Based Modeling of the Aeration Effectiveness of Circular Plunging Jets

Diksha Puri; Daeho Lee; Dhananjay Vasant Khankal; Mohindra Singh Thakur; Faisal M Alfaisal; Shamshad Alam; Raj Kumar; Mohammad Amir Khan

doi:10.1021/acsomega.3c03375

Decision Tree-Based Modeling of the Aeration Effectiveness of Circular Plunging Jets

ACS Omega. 2023 Oct 9;8(42):38950-38960. doi: 10.1021/acsomega.3c03375. eCollection 2023 Oct 24.

Authors

Diksha Puri¹, Daeho Lee², Dhananjay Vasant Khankal³, Mohindra Singh Thakur⁴, Faisal M Alfaisal⁵, Shamshad Alam⁵, Raj Kumar², Mohammad Amir Khan⁶

Affiliations

¹ School of Environmental Science, Shoolini University, Solan 173229, Himachal Pradesh, India.
² Department of Mechanical Engineering, Gachon University, Seongnam 13120, South Korea.
³ Department of Mechanical Engineering, Sinhgad College of Engineering, Pune 411041, Maharashtra, India.
⁴ Department of Civil Engineering, Shoolini University, Solan 173229, Himachal Pradesh, India.
⁵ Department of Civil Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia.
⁶ Department of Civil Engineering, Galgotia College of Engineering, Greater Noida 201310, India.

Abstract

Since soft computing has gained a lot of attention in hydrological studies, this study focuses on predicting aeration efficiency (E₂₀) using circular plunging jets employing soft computing techniques such as reduced error pruning tree (REPTree), random forest (RF), and M5P. The study undertaken required the development and validation of models, which were achieved using 63 experimental data values with input variables, such as angle of inclination of tilt channel (α), number of plunging jets (J_N), discharge of each jet (Q), hydraulic radius of each jet (HR), and Froude number (Fr. No), to evaluate the aeration efficiency (E₂₀), which served as the output variable. To evaluate the effectiveness of the developed models, three different statistical indices were used such as the coefficient of correlation (CC), root-mean-square error (RMSE), and mean absolute error (MAE), and it was found that all of the applied techniques possessed good forecasting ability since their correlation coefficient values were greater than 0.8. Upon testing, it was discovered that the M5P model outperformed other soft computing-based models in its ability to predict E₂₀, as demonstrated by its correlation coefficient value of 0.9564 and notably low values of MAE (0.0143) and RMSE (0.0193).