Yuan Jianbo, Li Yongjian
School of Mechanical Engineering, Yancheng Institute of Technology, Yancheng, 224051, Jiangsu Province, China.
Environ Monit Assess. 2025 Feb 1;197(2):219. doi: 10.1007/s10661-025-13627-0.
Water quality prediction is crucial for water resource management, as accurate forecasting can help identify potential issues in advance and provide a scientific basis for sustainable management. To predict key water quality indicators, including chemical oxygen demand (COD), suspended solids (SS), total phosphorus (TP), pH, total nitrogen (TN), and ammonia nitrogen (NH₃-N), we propose a novel model, CA-TCN-BiGRU, which combines channel attention mechanisms with temporal convolutional networks (TCN) and bidirectional gated recurrent units (BiGRU). The model, which uses a multi-input multi-output (MIMO) architecture, is capable of simultaneously predicting multiple water quality indicators. It is trained and tested using data from a wastewater treatment plant in Huizhou, China. This study investigates the impact of data preprocessing and the channel attention mechanism on model performance and compares the predictive capabilities of various deep learning models. The results demonstrate that data preprocessing significantly improves prediction accuracy, while the channel attention mechanism enhances the model's focus on key features. The CA-TCN-BiGRU model outperforms others in predicting multiple water quality indicators, particularly for COD, TP, and SS, where MAE and RMSE decrease by approximately 23% and 26%, respectively, and R2 improves by 5.85%. Moreover, the model shows strong robustness and real-time performance across different wastewater treatment plants, making it suitable for short-term (1-3 days) water quality prediction. The study concludes that the CA-TCN-BiGRU model not only achieves high accuracy but also offers low computational overhead and fast inference speed, making it an ideal solution for real-time water quality monitoring.
水质预测对于水资源管理至关重要，因为准确的预测有助于提前识别潜在问题，并为可持续管理提供科学依据。为了预测关键水质指标，包括化学需氧量（COD）、悬浮固体（SS）、总磷（TP）、pH值、总氮（TN）和氨氮（NH₃-N），我们提出了一种新型模型CA-TCN-BiGRU，该模型将通道注意力机制与时间卷积网络（TCN）和双向门控循环单元（BiGRU）相结合。该模型采用多输入多输出（MIMO）架构，能够同时预测多个水质指标。它使用来自中国惠州一家污水处理厂的数据进行训练和测试。本研究调查了数据预处理和通道注意力机制对模型性能的影响，并比较了各种深度学习模型的预测能力。结果表明，数据预处理显著提高了预测准确性，而通道注意力机制增强了模型对关键特征的关注。CA-TCN-BiGRU模型在预测多个水质指标方面优于其他模型，特别是对于COD、TP和SS，其中平均绝对误差（MAE）和均方根误差（RMSE）分别下降了约23%和26%，决定系数（R2）提高了5.85%。此外，该模型在不同污水处理厂中表现出强大的鲁棒性和实时性能，适用于短期（1-3天）水质预测。研究得出结论，CA-TCN-BiGRU模型不仅实现了高精度，而且计算开销低、推理速度快，是实时水质监测的理想解决方案。
