Nguyen X Cuong, Nguyen T Phuong, Lam V Son, Le Phuoc-Cuong, Vo T Dieu Hien, Hoang Thu-Huong Thi, Chung W Jin, Chang S Woong, Nguyen D Duc
Institute of Research and Development, Duy Tan University, Da Nang 550000, Viet Nam; Faculty of Environmental and Chemical Engineering, Duy Tan University, Da Nang 550000, Viet Nam.
Faculty of Environmental Engineering Technology, Hue University, Quang Tri Branch, Viet Nam.
Sci Total Environ. 2024 Jan 10;907:168142. doi: 10.1016/j.scitotenv.2023.168142. Epub 2023 Oct 26.
Constructed wetlands (CWs) are a widely utilized nature-based wastewater treatment method for various effluents. However, their application has been more focused on pilot and full-scale CWs with substantial surface areas and extended operation times, which hold greater relevance in practical scenarios. This study used kinetics, linear regression (LR), and machine learning (ML) models to estimate effluent ammonium in pilot and full-scale CWs. From screening 1476 papers, 24 pilot and full-scale CW studies were selected to extract data containing 15 features and 975 data points. Nine models were fit to this data, revealing that linear models were less effective in capturing CW effluent compared to nonlinear ML algorithms. For training data, the Monod kinetic model predicted the poorest performance with an RMSE of 41.84 mg/L and R of 0.34, followed by simple LR (RMSE 24.29 mg/L and R 0.77) and multiple LR (RMSE 22.63 mg/L and R 0.80). In contrast, Cubist and Random Forest achieved high performances, with an average RMSE of 12.01 ± 5.38 and an average R of 0.93 ± 0.07 for Cubist, and an average RMSE of 15.94 ± 10.69 and an average R of 0.91 ± 0.08 for RF. The trained Random Forest performed the best for new data, with an R of 0.93 and RMSE of 13.48 mg/L. This ML-based model is a valuable tool for efficiently estimating effluent ammonium concentration in pilot and full-scale CWs, thereby facilitating the design of systems.
人工湿地（CWs）是一种广泛应用的基于自然的废水处理方法，可用于处理各种废水。然而，其应用更多地集中在具有较大表面积和较长运行时间的中试规模和全尺寸人工湿地上，这些在实际场景中具有更大的相关性。本研究使用动力学、线性回归（LR）和机器学习（ML）模型来估算中试规模和全尺寸人工湿地中的出水铵含量。从筛选的1476篇论文中，选择了24项中试规模和全尺寸人工湿地研究，以提取包含15个特征和975个数据点的数据。九个模型对这些数据进行了拟合，结果表明，与非线性ML算法相比，线性模型在捕捉人工湿地出水方面效果较差。对于训练数据，莫诺德动力学模型的预测性能最差，均方根误差（RMSE）为41.84mg/L，决定系数（R）为0.34，其次是简单线性回归（RMSE为24.29mg/L，R为0.77）和多元线性回归（RMSE为22.63mg/L，R为0.80）。相比之下，Cubist和随机森林模型表现出色，Cubist的平均RMSE为12.01±5.38，平均R为0.93±0.07；随机森林模型的平均RMSE为15.94±10.69，平均R为0.91±0.08。训练后的随机森林模型对新数据的预测效果最佳，R为0.93，RMSE为13.48mg/L。这种基于ML的模型是有效估算中试规模和全尺寸人工湿地出水铵浓度的宝贵工具，从而有助于系统设计。
