Continuous Water Quality Prediction Method Based on Stacked Long Short-Term Memory Neural Networks

ZHANG Jianqi; FENG Leyuan; LI Donghe; YANG Qingyu

doi:10.7652/xjtuxb202506010

您当前的位置：

首页 >

文章列表页 >

Continuous Water Quality Prediction Method Based on Stacked Long Short-Term Memory Neural Networks

Special Topic　Intelligent Prediction | 更新时间：2025-08-26

- Continuous Water Quality Prediction Method Based on Stacked Long Short-Term Memory Neural Networks
- Journal of Xi’an Jiaotong University Vol. 59, Issue 6, Pages: 93-102(2025)
- 作者机构：
  
  1.西安交通大学自动化科学与工程学院， 710049，西安
  2.西安航天自动化股份有限公司， 710065，西安
  3.西安交通大学精密微纳制造技术全国重点实验室， 710049，西安
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202506010
  CLC： TP31
- Received：26 December 2024，
  
  Online First：25 February 2025，
  
  Published：10 June 2025
- 稿件说明：
移动端阅览
ZHANG Jianqi, FENG Leyuan, LI Donghe, et al. Continuous Water Quality Prediction Method Based on Stacked Long Short-Term Memory Neural Networks[J]. Journal of Xi’an Jiaotong University, 2025, 59(6): 93-102.
DOI：

ZHANG Jianqi, FENG Leyuan, LI Donghe, et al. Continuous Water Quality Prediction Method Based on Stacked Long Short-Term Memory Neural Networks[J]. Journal of Xi’an Jiaotong University, 2025, 59(6): 93-102. DOI： 10.7652/xjtuxb202506010.

摘要

针对水环境监测中的水质参数异常、预测精度低等问题，提出了一种基于堆叠长短期记忆神经网络(SLSTM)的水质参数预测模型，以解决时序数据不完整带来的挑战。首先，分析了缺失或异常的水质数据时序特征，并基于堆叠长短期记忆网络设计了水质预测的深度神经网络模型；其次，采用逐点预测和多步预测方法对所提模型进行对比实验验证；最后，为了量化模型的预测性能，引入平均绝对百分比误差(MAPE)和均方根误差(RMSE)两类指标，评估SLSTM模型相对于支持向量回归(SVR)和自回归综合移动平均(ARIMA)模型的优越性。实验结果表明，在短期(24 h)和长期(48 h)水质余氯预测中，SLSTM的预测精度显著高于其他两类模型：在多步预测中，SLSTM的MAPE至少比SVR降低了9.15%；逐点预测中，SLSTM的RMSE至少比SVR降低了31.25%。此外，相较于ARIMA模型，SLSTM能够更有效地捕捉水质数据的非线性变化趋势，提升预测稳定性。研究不仅验证了SLSTM在水质参数预测中的有效性，还为水环境监测领域提供了新的视角和工具。

Abstract

Aiming at the issues of abnormal water quality parameters and low prediction accuracy in water environment monitoring

this paper proposes a water quality parameter prediction model based on stacked long short-term memory neural network (SLSTM) to tackle the challenge of incomplete time series data. First

the timing characteristics of missing or abnormal water quality data were analyzed

and a deep neural network model for water quality prediction was designed based on stacked long short-term memory networks. Second

point-by-point prediction and multistep prediction methods were used to validate the proposed model in comparative experiments. Lastly

in order to quantify the prediction performance of the model

two types of metrics were introduced

namely

the mean absolute percentage error (MAPE) and the root-mean-square error (RMSE) to assess the superiority of the SLSTM model over the support vector regression (SVR) and autoregressive integrated moving average (ARIMA) models. The experimental results showed that the prediction accuracy of SLSTM was significantly higher than that of the other two models in short-term (24 h) and long-term (48 h) chlorine residual prediction: the MAPE of SLSTM was at least 9.15% lower than that of SVR for multistep prediction

and the RMSE of SLSTM was at least 31.25% lower than that of SVR for point-by-point prediction. In addition

compared with the ARIMA model

SLSTM can capture the nonlinear trend of water quality data more effectively and improve the prediction stability. This study not only verifies the effectiveness of SLSTM in water quality parameter prediction

but also provides new perspectives and tools for the field of water environment monitoring.

关键词

Keywords

references

程婉清 , 袁定波 , 熊鹏 , 等 . 基于多种机器学习算法的水质指数预测模型构建与评估 [J ] . 环境科学学报 , 2023 , 43 ( 11 ): 144 - 152 .

CHENG Wanqing , YUAN Dingbo , XIONG Peng , et al . Construction and evaluation of city water quality index prediction model based on multiple machine learning algorithms [J ] . Acta Scientiae Circumstantiae , 2023 , 43 ( 11 ): 144 - 152 .

王梓璇 . 山地城市供水管网水质预警系统研究 [D ] . 重庆 : 重庆大学 , 2022 .

王亦琳 , 陶涛 , 赵平伟 , 等 . 基于Elman神经网络的供水管网浊度预测研究 [J ] . 中国市政工程 , 2022 ( 1 ): 64 - 68 .

WANG Yilin , TAO Tao , ZHAO Pingwei , et al . Research on turbidity prediction of water supply pipe network based on Elman neural network [J ] . China Municipal Engineering , 2022 ( 1 ): 64 - 68 .

YING F . Analysis of quality control for water environment monitoring [EB/OL ] . [ 2024-11-12 ] . http://en.cnki.com.cn/Article_en/CJFDTotal-SXJL201801038.htm http://en.cnki.com.cn/Article_en/CJFDTotal-SXJL201801038.htm .

THOMANN R V . The future “golden age” of predictive models for surface water quality and ecosystem management [J ] . Journal of Environmental Engineering , 1998 , 124 ( 2 ): 94 - 103 .

NAJAH A A , EL-SHAFIE A , KARIM O A , et al . Water quality prediction model utilizing integrated wavelet-ANFIS model with cross-validation [J ] . Neural Computing and Applications , 2012 , 21 ( 5 ): 833 - 841 .

刘杰 , 陈前 , 许妍 , 等 . 长江流域洞庭湖区出入湖磷通量模拟及水质预测：机器学习与传统水文模型耦合方法 [J ] . 地球科学 , 2024 , 49 ( 11 ): 3995 - 4007 .

LIU Jie , CHEN Qian , XU Yan , et al . Simulation of phosphorus inflow and outflow fluxes and water quality prediction in Dongting Lake area of the Yangtze River basin: a coupled approach of machine learning and traditional hydrological modeling [J ] . Earth Science , 2024 , 49 ( 11 ): 3995 - 4007 .

TU Jichang , YANG Xueqin , CHEN Chaobo , et al . Water quality prediction model based on GRU hybrid network [C ] // 2019 Chinese Automation Congress . Piscataway, NJ, USA : IEEE , 2019 : 1893 - 1898 .

芮栋妮 , 马燕燕 , 叶林 . 机器学习方法在污水处理系统中的应用 [J ] . 环境工程 , 2022 , 40 ( 6 ): 145 - 153 .

RUI Dongni , MA Yanyan , YE Lin . Application of machine learning methods in wastewater treatment systems [J ] . Environmental Engineering , 2022 , 40 ( 6 ): 145 - 153 .

LIU Gang , GUO Jiabao . Bidirectional LSTM with attention mechanism and convolutional layer for text classification [J ] . Neurocomputing , 2019 , 337 : 325 - 338 .

PALANGI H , WARD R , DENG Li . Distributed compressive sensing: a deep learning approach [J ] . IEEE Transactions on Signal Processing , 2016 , 64 ( 17 ): 4504 - 4518 .

SHENG Liming , JIAN Zhou , XIN Li , et al . Water quality prediction method based on preferred classification [J ] . IET Cyber-Physical Systems: Theory & Applications , 2020 , 5 ( 2 ): 176 - 180 .

HARI K N , JAGRAT J . Adaptability of smart water systems in urban belt: a case study at Sastra University, Thanjavur [J ] . Asian Journal of Management , 2020 , 11 ( 1 ): 21 - 25 .

LI Jiada , YANG Xiafei , SITZENFREI R . Rethinking the framework of smart water system: a review [J ] . Water , 2020 , 12 ( 2 ): 412 .

MARCHESE D , JIN A , FOX-LENT C , et al . Resilience for smart water systems [J ] . Journal of Water Resources Planning and Management , 2020 , 146 ( 1 ): 02519002 .

CUI Bo , MENG Qinghong . Smart water monitoring and management system based on the architecture of internet of things [J ] . Applied Mechanics and Materials , 2013 , 278-280 : 1822 - 1825 .

BHARATH SINGH J , NIRMITHA S , KAVIYA S S . Smart urban water quality prediction system using machine learning [C ] // Journal of Physics: Conference Series . Bristol, UK : IOP Publishing , 2021 : 012057 .

YAO Fengchun . Study on the application of smart water system in urban water supply [J ] . Science Innovation , 2021 , 9 ( 4 ): 176 - 178 .

NTULI N , ABU-MAHFOUZ A . A simple security architecture for smart water management system [J ] . Procedia Computer Science , 2016 , 83 : 1164 - 1169 .

李如忠 . 水质预测理论模式研究进展与趋势分析 [J ] . 合肥工业大学学报(自然科学版) , 2006 , 29 ( 1 ): 26 - 30 .

LI Ruzhong . Advance and trend analysis of theoretical methodology for water quality forecast [J ] . Journal of Hefei University of Technology (Natural Science) , 2006 , 29 ( 1 ): 26 - 30 .

CHEN Kangyang , CHEN Hexia , ZHOU Chuanlong , et al . Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data [J ] . Water Research , 2020 , 171 : 115454 .

PUROHIT S K , PANIGRAHI S , SETHY P K , et al . Time series forecasting of price of agricultural products using hybrid methods [J ] . Applied Artificial Intelligence , 2021 , 35 ( 15 ): 1388 - 1406 .

CHEN M Y , CHIANG H S , SANGAIAH A K , et al . Recurrent neural network with attention mechanism for language model [J ] . Neural Computing and Applications , 2020 , 32 ( 12 ): 7915 - 7923 .

YAYAN U , ARSLAN A T , YUCEL H . A novel method for SoH prediction of batteries based on stacked LSTM with quick charge data [J ] . Applied Artificial Intelligence , 2021 , 35 ( 6 ): 421 - 439 .

DAHL G E , YU Dong , DENG Li , et al . Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition [J ] . IEEE Transactions on Audio Speech and Language Processing , 2012 , 20 ( 1 ): 30 - 42 .

BALI N , SINGLA A . Deep learning based wheat crop yield prediction model in Punjab region of North India [J ] . Applied Artificial Intelligence , 2021 , 35 ( 15 ): 1304 - 1328 .

FARABET C , COUPRIE C , NAJMAN L , et al . Learning hierarchical features for scene labeling [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 35 ( 8 ): 1915 - 1929 .

PLANK B , SØGAARD A , GOLDBERG Y . Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss [C ] // Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics . Stroudsburg, PA, USA : ACL , 2016 : 412 - 418 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

Effects of Expansion Angle Crater Film Hole on the Film Cooling Characteristics of a Double-Wall Structure

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Study on the Thermodynamic Properties in the Anomalous Region of Supercritical Water

Electrothermal Coupling Research on the Evolutionary Law of Anti-Corona Performance for High-Altitude Air-Cooled Generators

Related Author

No data

Related Institution

No data

⁰