A probabilistic deep learning approach to enhance the prediction of wastewater treatment plant effluent quality under shocking load events

被引:2
作者
Yin, Hailong [1 ,2 ]
Chen, Yongqi [1 ,2 ]
Zhou, Jingshu [1 ,2 ]
Xie, Yifan [3 ]
Wei, Qing [1 ,2 ]
Xu, Zuxin [1 ,2 ]
机构
[1] Shanghai Inst Pollut Control & Ecol Secur, Shanghai 200092, Peoples R China
[2] Tongji Univ, Key Lab Urban Water Supply Water Saving & Water En, State Key Lab Pollut Control & Resource Reuse, Shanghai 200092, Peoples R China
[3] Tsinghua Univ, Sch Environm, Beijing 100084, Peoples R China
来源
WATER RESEARCH X | 2025年 / 26卷
基金
中国国家自然科学基金;
关键词
Wastewater treatment plant; Machine learning model; Deep learning; Effluent water quality; Shocking load; MODEL;
D O I
10.1016/j.wroa.2024.100291
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Sudden shocking load events featuring significant increases in inflow quantities or concentrations of wastewater treatment plants (WWTPs), are a major threat to the attainment of treated effluents to discharge quality standards. To aid in real-time decision-making for stable WWTP operations, this study developed a probabilistic deep learning model that comprises encoder-decoder long short-term memory (LSTM) networks with added capacity of producing probability predictions, to enhance the robustness of real-time WWTP effluent quality prediction under such events. The developed probabilistic encoder-decoder LSTM (P-ED-LSTM) model was tested in an actual WWTP, where bihourly effluent quality prediction of total nitrogen was performed and compared with classical deep learning models, including LSTM, gated recurrent unit (GRU) and Transformer. It was found that under shocking load events, the P-ED-LSTM could achieve a 49.7% improvement in prediction accuracy for bihourly real-time predictions of effluent concentration compared to the LSTM, GRU, and Transformer. A higher quantile of the probability data from the P-ED-LSTM model output, indicated a prediction value more approximate to real effluent quality. The P-ED-LSTM model also exhibited higher predictive power for the next multiple time steps with shocking load scenarios. It captured approximately 90% of the actual over-limit discharges up to 6 hours ahead, significantly outperforming other deep learning models. Therefore, the P-ED-LSTM model, with its robust adaptability to significant fluctuations, has the potential for broader applications across WWTPs with different processes, as well as providing strategies for wastewater system regulation under emergency conditions.
引用
收藏
页数:9
相关论文
共 58 条
[1]   Deep learning in wastewater treatment: a critical review [J].
Alvi, Maira ;
Batstone, Damien ;
Mbamba, Christian Kazadi ;
Keymer, Philip ;
French, Tim ;
Ward, Andrew ;
Dwyer, Jason ;
Cardell-Oliver, Rachel .
WATER RESEARCH, 2023, 245
[2]   A combined experimental and density functional theory study of metformin oxy-cracking for pharmaceutical wastewater treatment [J].
Badran, Ismail ;
Manasrah, Abdallah D. ;
Nassar, Nashaat N. .
RSC ADVANCES, 2019, 9 (24) :13403-13413
[3]   Soft Sensor of the Key Effluent Index in the Municipal Wastewater Treatment Process Based on Transformer [J].
Chang, Peng ;
Zhang, Shirao ;
Wang, Zichen .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2024, 20 (03) :4021-4028
[4]   Forecasting of Wastewater Treatment Plant Key Features Using Deep Learning-Based Models: A Case Study [J].
Cheng, Tuoyuan ;
Harrou, Fouzi ;
Kadri, Farid ;
Sun, Ying ;
Leiknes, Torove .
IEEE ACCESS, 2020, 8 (08) :184475-184485
[5]   Development of a wide-range soft sensor for predicting wastewater BOD5 using an eXtreme gradient boosting (XGBoost) machine [J].
Ching, P. M. L. ;
Zou, X. ;
Wu, Di ;
So, R. H. Y. ;
Chen, G. H. .
ENVIRONMENTAL RESEARCH, 2022, 210
[6]  
Cho KYHY, 2014, Arxiv, DOI [arXiv:1406.1078, DOI 10.48550/ARXIV.1406.1078]
[7]  
Chung JY, 2014, Arxiv, DOI [arXiv:1412.3555, DOI 10.48550/ARXIV.1412.3555]
[8]   Prediction of effluent concentration in a wastewater treatment plant using machine learning models [J].
Guo, Hong ;
Jeong, Kwanho ;
Lim, Jiyeon ;
Jo, Jeongwon ;
Kim, Young Mo ;
Park, Jong-Pyo ;
Kim, Joon Ha ;
Cho, Kyung Hwa .
JOURNAL OF ENVIRONMENTAL SCIENCES, 2015, 32 :90-101
[9]  
Hou Q., 2024, EGUsphere, V2024, P1, DOI [10.5194/egusphere-2023-2685, DOI 10.5194/EGUSPHERE-2023-2685]
[10]   Optimized convolutional neural networks for fault diagnosis in wastewater treatment processes [J].
Hu, Tong ;
Zhang, Yuchen ;
Wang, Xinyuan ;
Sha, Jiulong ;
Dai, Hongqi ;
Xiong, Zhixin ;
Wang, Dongsheng ;
Zhang, Fengshan ;
Liu, Hongbin .
ENVIRONMENTAL SCIENCE-WATER RESEARCH & TECHNOLOGY, 2024, 10 (02) :364-375