Sun Jingjing, Guan Xin, Sun Xiaojun, Cao Xiaojing, Tan Yepei, Liao Jiarong
School of Public Administration, Guangzhou University, Guangzhou, 510006, China.
Guangzhou Xinhua University, Dongguan, 523133, China.
Sci Rep. 2024 Dec 28;14(1):31525. doi: 10.1038/s41598-024-83277-8.
With the accelerated urbanization and economic development in Northwest China, the efficiency of urban wastewater treatment and the importance of water quality management have become increasingly significant. This work aims to explore urban wastewater treatment and carbon reduction mechanisms in Northwest China to alleviate water resource pressure. By utilizing online monitoring data from pilot systems, it conducts an in-depth analysis of the impacts of different wastewater treatment processes on water quality parameters. This work pays particular attention to their impact on key indicators such as Chemical Oxygen Demand (COD), NH-N, Total Phosphorus (TP), and Total Nitrogen (TN), and the application of predictive models. The work first establishes a Random Forest Regression (RFR) model. The RFR algorithm integrates Bagging ensemble learning and random subspace theory to construct multiple decision trees and aggregate their predictions, thereby enhancing the model's prediction accuracy and stability. Using bootstrap sampling, the RFR model generates multiple training subsets from the original data and randomly selects subsets of variables to construct regression trees. Its performance in predicting various water quality indicators is then evaluated. The results show that the RFR model exhibits excellent performance, achieving high levels of prediction accuracy and stability for all indicators. For example, the R for COD prediction is 0.99954, while the R values for NH-N, TP, and TN predictions reach 0.99989. Compared to five other models, the RFR model demonstrates the best performance across all water quality indicator predictions. This work provides critical support for optimizing wastewater treatment technologies and developing water resource management policies. These findings also offer essential theoretical and empirical insights for the future improvement of urban wastewater treatment technologies and water resource management decision-making.
随着中国西北地区城市化进程的加速和经济的发展，城市污水处理效率和水质管理的重要性日益凸显。这项工作旨在探索中国西北地区的城市污水处理和碳减排机制，以缓解水资源压力。通过利用试点系统的在线监测数据，深入分析不同污水处理工艺对水质参数的影响。这项工作特别关注其对化学需氧量（COD）、氨氮（NH-N）、总磷（TP）和总氮（TN）等关键指标的影响以及预测模型的应用。该工作首先建立了随机森林回归（RFR）模型。RFR算法整合了Bagging集成学习和随机子空间理论，构建多个决策树并汇总其预测结果，从而提高模型的预测准确性和稳定性。利用自助抽样，RFR模型从原始数据中生成多个训练子集，并随机选择变量子集来构建回归树。然后评估其在预测各种水质指标方面的性能。结果表明，RFR模型表现出色，对所有指标均实现了高水平的预测准确性和稳定性。例如，COD预测的R值为0.99954，而NH-N、TP和TN预测的R值达到0.99989。与其他五个模型相比，RFR模型在所有水质指标预测中表现最佳。这项工作为优化污水处理技术和制定水资源管理政策提供了关键支持。这些发现也为未来城市污水处理技术的改进和水资源管理决策提供了重要的理论和实证见解。
