Shihu Shu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shihu Shu has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Yanping Zhu
College of Environmental Science and Engineering, Donghua University, Shanghai 201620, China
4 shared publications - Bo Dong
School of Architectural Engineering, Chuzhou Vocational and Technical College, Chuzhou, China
3 shared publications - Dengxin Li
College of Environmental Science and Engineering, Donghua University, Shanghai 201620, China
3 shared publications - Dongqi Wang
Department of Municipal and Environmental Engineering, Xi’an University of Technology, Xi’an, China
2 shared publications - Dongqing Cai
College of Environmental Science and Engineering, Donghua University, Shanghai, People’s Republic of China
2 shared publications - Naiyun Gao
State Key Laboratory of Pollution Control Reuse, Tongji University, Shanghai 200092, China
2 shared publications
Latest Publications
- 6 December 2025
- Published by Elsevier in Water Research
- Vol. 290, 125113
Effect of dual-metal particles on disinfection by-product formation in drinking water
- 6 December 2025
- Published by Elsevier in Water Research
- Vol. 290, 125113
Effect of dual-metal particles on disinfection by-product formation in drinking water
- 13 June 2025
- Published by Elsevier in Water Research
- Vol. 284, 124019
Electron beam/persulfate-induced second-scale upcycling of wastewater polyvinyl alcohol with ultra-low chemical input
- 13 June 2025
- Published by Elsevier in Water Research
- Vol. 284, 124019
Electron beam/persulfate-induced second-scale upcycling of wastewater polyvinyl alcohol with ultra-low chemical input
- Open Access
Prediction of Blue-Green Algae Cells in a City Water Source Based on the LSTM Model
China’s freshwater resources are relatively small per capita, and the traditional passive control of hydrographic outbreaks can no longer meet modern water management needs. Data-driven models, such as Long Short-Term Memory Networks (LSTMs), have been gradually applied to water resources management, but most of the research has focused on the enhancement of the prediction effect of hybrid models while neglecting the importance of data structure. In this study, we predicted the number of dominant algae (blue-green algae) in a water source based on LSTM and explored the effects of different feature combinations and time window steps on the prediction performance. It was found that the model prediction was significantly improved by adding multiple features, and the R2 improved by 31.98% compared with single feature prediction. Meanwhile, as the time window (T-value) increased from 7 to 300, the R2 improved by 0.4%, but the iteration time increased by 96%. The results suggested that appropriate input feature selection is beneficial for model prediction, while longer time windows led to reduced model prediction benefits. Lastly, this study offers insights into future research directions from three key dimensions: the input indicator, optimization algorithm, and model combination.
Open AccessPrediction of Blue-Green Algae Cells in a City Water Source Based on the LSTM Model
China’s freshwater resources are relatively small per capita, and the traditional passive control of hydrographic outbreaks can no longer meet modern water management needs. Data-driven models, such as Long Short-Term Memory Networks (LSTMs), have been gradually applied to water resources management, but most of the research has focused on the enhancement of the prediction effect of hybrid models while neglecting the importance of data structure. In this study, we predicted the number of dominant algae (blue-green algae) in a water source based on LSTM and explored the effects of different feature combinations and time window steps on the prediction performance. It was found that the model prediction was significantly improved by adding multiple features, and the R2 improved by 31.98% compared with single feature prediction. Meanwhile, as the time window (T-value) increased from 7 to 300, the R2 improved by 0.4%, but the iteration time increased by 96%. The results suggested that appropriate input feature selection is beneficial for model prediction, while longer time windows led to reduced model prediction benefits. Lastly, this study offers insights into future research directions from three key dimensions: the input indicator, optimization algorithm, and model combination.
- Open Access
Optimization of Secondary Chlorination in Water Distribution Systems for Enhanced Disinfection and Reduced Chlorine Odor Using Deep Belief Network and NSGA-II
This research explores the strategic optimization of secondary chlorination in water distribution systems (WDSs), in order to enhance the efficiency of disinfection while mitigating odor and operational costs and promoting sustainability in water quality management. The methodology integrates EPANET simulations for water hydraulic and quality modeling with a deep belief network (DBN) within the deep learning framework for accurate chloric odor prediction. Utilizing the non-dominated sorting genetic algorithm-II (NSGA-II), this methodology systematically balances the objectives of chloride dosage and chloramine formation. It combines a chloric odor intensity assessment, a multi-component kinetic model, and dual-objective optimization to conduct a comparative analysis of case studies on secondary chlorination strategies. The optimal configuration with five secondary chlorination stations reduced chloric odor intensity to 1.20 at a cost of USD 40,020.77 per year in Network A while, with eight stations, chloric odor intensity was reduced to 0.88 at a cost of USD 71,405.38 per year in Network B. The results demonstrate a balanced trade-off between odor intensity and operational cost on one hand and sustainability on the other hand, highlighting the importance of precise chlorine management to improve both the sensory and safety qualities of drinking water while ensuring the sustainable use and management of water resources.
Open AccessOptimization of Secondary Chlorination in Water Distribution Systems for Enhanced Disinfection and Reduced Chlorine Odor Using Deep Belief Network and NSGA-II
This research explores the strategic optimization of secondary chlorination in water distribution systems (WDSs), in order to enhance the efficiency of disinfection while mitigating odor and operational costs and promoting sustainability in water quality management. The methodology integrates EPANET simulations for water hydraulic and quality modeling with a deep belief network (DBN) within the deep learning framework for accurate chloric odor prediction. Utilizing the non-dominated sorting genetic algorithm-II (NSGA-II), this methodology systematically balances the objectives of chloride dosage and chloramine formation. It combines a chloric odor intensity assessment, a multi-component kinetic model, and dual-objective optimization to conduct a comparative analysis of case studies on secondary chlorination strategies. The optimal configuration with five secondary chlorination stations reduced chloric odor intensity to 1.20 at a cost of USD 40,020.77 per year in Network A while, with eight stations, chloric odor intensity was reduced to 0.88 at a cost of USD 71,405.38 per year in Network B. The results demonstrate a balanced trade-off between odor intensity and operational cost on one hand and sustainability on the other hand, highlighting the importance of precise chlorine management to improve both the sensory and safety qualities of drinking water while ensuring the sustainable use and management of water resources.
- Open Access
Identification of Flow Pressure-Driven Leakage Zones Using Improved EDNN-PP-LCNetV2 with Deep Learning Framework in Water Distribution System
This study introduces a novel deep learning framework for detecting leakage in water distribution systems (WDSs). The key innovation lies in a two-step process: First, the WDS is partitioned using a K-means clustering algorithm based on pressure sensitivity analysis. Then, an encoder–decoder neural network (EDNN) model is employed to extract and process the pressure and flow sensitivities. The core of the framework is the PP-LCNetV2 architecture that ensures the model’s lightweight, which is optimized for CPU devices. This combination ensures rapid, accurate leakage detection. Three cases are employed to evaluate the method. By applying data augmentation techniques, including the demand and measurement noises, the framework demonstrates robustness across different noise levels. Compared with other methods, the results show this method can efficiently detect over 90% of leakage across different operating conditions while maintaining a higher recognition of the magnitude of leakages. This research offers a significant improvement in computational efficiency and detection accuracy over existing approaches.
Open AccessIdentification of Flow Pressure-Driven Leakage Zones Using Improved EDNN-PP-LCNetV2 with Deep Learning Framework in Water Distribution System
This study introduces a novel deep learning framework for detecting leakage in water distribution systems (WDSs). The key innovation lies in a two-step process: First, the WDS is partitioned using a K-means clustering algorithm based on pressure sensitivity analysis. Then, an encoder–decoder neural network (EDNN) model is employed to extract and process the pressure and flow sensitivities. The core of the framework is the PP-LCNetV2 architecture that ensures the model’s lightweight, which is optimized for CPU devices. This combination ensures rapid, accurate leakage detection. Three cases are employed to evaluate the method. By applying data augmentation techniques, including the demand and measurement noises, the framework demonstrates robustness across different noise levels. Compared with other methods, the results show this method can efficiently detect over 90% of leakage across different operating conditions while maintaining a higher recognition of the magnitude of leakages. This research offers a significant improvement in computational efficiency and detection accuracy over existing approaches.
- 27 June 2024
- Published by Springer Nature
- p. 1577-1586
Research on Safety Evaluation of Water Supply Network Based on Urban Physical Examination
- 27 June 2024
- Published by Springer Nature
- p. 1577-1586
Research on Safety Evaluation of Water Supply Network Based on Urban Physical Examination
- 1 May 2024
- Published by Springer Nature
- p. 123-133
The Effectiveness of Urban Water Loss Control and Their Implications for Rural Revitalization
- 1 May 2024
- Published by Springer Nature
- p. 123-133
The Effectiveness of Urban Water Loss Control and Their Implications for Rural Revitalization
- Open Access
A Unified Spatial-Pressure Sensitivity Partitioning and Leakage Detection Method within a Deep Learning Framework
This study introduces an innovative approach for leak detection in water distribution systems (WDSs), integrating three-order embedding, k-means clustering, and long short-term memory (LSTM) networks, with pressure-sensitive analysis techniques. This comprehensive methodology segments the network into distinct partitions, utilizes simulated leak events to train the deep learning networks, and establishes a sophisticated model for accurately identifying leak partitions. This approach generates a leak dataset by adjusting water demands, which could effectively pinpoint the leaks in a specific partition by leveraging both the pressure sensitivity and spatial coordinates of nodes, allowing for the elimination of the need for manual work and precise identification of leaks in targeted areas. Through the analysis of two case studies, the model demonstrates its ability to effectively pinpoint potential leak partitions, significantly enhancing operational efficiency and reliability in managing the complex problems of urban water resource management. This approach not only optimizes leak detection but also paves the way for advanced, data-driven strategies in WDSs, ensuring sustainable and secure water distribution in urban settings.
Open AccessA Unified Spatial-Pressure Sensitivity Partitioning and Leakage Detection Method within a Deep Learning Framework
This study introduces an innovative approach for leak detection in water distribution systems (WDSs), integrating three-order embedding, k-means clustering, and long short-term memory (LSTM) networks, with pressure-sensitive analysis techniques. This comprehensive methodology segments the network into distinct partitions, utilizes simulated leak events to train the deep learning networks, and establishes a sophisticated model for accurately identifying leak partitions. This approach generates a leak dataset by adjusting water demands, which could effectively pinpoint the leaks in a specific partition by leveraging both the pressure sensitivity and spatial coordinates of nodes, allowing for the elimination of the need for manual work and precise identification of leaks in targeted areas. Through the analysis of two case studies, the model demonstrates its ability to effectively pinpoint potential leak partitions, significantly enhancing operational efficiency and reliability in managing the complex problems of urban water resource management. This approach not only optimizes leak detection but also paves the way for advanced, data-driven strategies in WDSs, ensuring sustainable and secure water distribution in urban settings.
- Open Access
Comparison of Medium-Pressure UV/Peracetic Acid to Remove Three Typical Refractory Contaminants of Textile Wastewater
In this work, the performance of medium-pressure UV/peracetic acid (MPUV/PAA/H2O2) was explored on removing reactive black 5 (RB5), aniline (ANL), and polyvinyl alcohol (PVA), three typical refractory contaminants in printing and dyeing wastewater, compared with MPUV/H2O2. MPUV/PAA/H2O2 showed 75.0, 44.9, and 57.7% removals of RB5, ANL, and PVA, respectively, within 5 min. The removal of RB5 increased from 68.98 to 91.2%, with pH increasing from 6 to 9, while the removals of ANL and PVA were much less pH-dependent. Quenching experiment results indicated that UV photolysis and radical (i.e., •OH and R-C•) oxidation contributed to RB5 removal, while PAA showed high activity in the oxidation of ANL. For PVA, •OH oxidation and UV photolysis were likely the main mechanisms. The coexisting natural organic matter had a negative effect on the degradation of RB5 and PVA. In addition, MPUV/PAA/H2O2 could effectively degrade those pollutants without increasing the toxicity. This work provides a theoretical reference for the utilization of MPUV/PAA/H2O2 in removing structurally diverse refractory contaminants from printing and dyeing wastewater.
Open AccessComparison of Medium-Pressure UV/Peracetic Acid to Remove Three Typical Refractory Contaminants of Textile Wastewater
In this work, the performance of medium-pressure UV/peracetic acid (MPUV/PAA/H2O2) was explored on removing reactive black 5 (RB5), aniline (ANL), and polyvinyl alcohol (PVA), three typical refractory contaminants in printing and dyeing wastewater, compared with MPUV/H2O2. MPUV/PAA/H2O2 showed 75.0, 44.9, and 57.7% removals of RB5, ANL, and PVA, respectively, within 5 min. The removal of RB5 increased from 68.98 to 91.2%, with pH increasing from 6 to 9, while the removals of ANL and PVA were much less pH-dependent. Quenching experiment results indicated that UV photolysis and radical (i.e., •OH and R-C•) oxidation contributed to RB5 removal, while PAA showed high activity in the oxidation of ANL. For PVA, •OH oxidation and UV photolysis were likely the main mechanisms. The coexisting natural organic matter had a negative effect on the degradation of RB5 and PVA. In addition, MPUV/PAA/H2O2 could effectively degrade those pollutants without increasing the toxicity. This work provides a theoretical reference for the utilization of MPUV/PAA/H2O2 in removing structurally diverse refractory contaminants from printing and dyeing wastewater.
- Open Access
Effect of Medium Pressure Ultraviolet/Chlorine Advanced Oxidation on the Production of Disinfection by-Products from Seven Model Benzene Precursors
UV/chlorine advanced oxidation process (AOP), as a potential alternative to UV/H2O2 in water treatment, may pose a potential risk of increased disinfection by-product (DBP) formation and is of great concern. In this paper, seven benzene derivatives, containing two chlorine-inert and five chlorine-active compounds, were selected as typical model DBP precursors, and the effects of medium pressure UV/chlorine (MPUV/chlorine) on their chlorine demand and DBP formation potential (DBPFP) were evaluated. The results showed that MPUV/chlorine could significantly increase the chlorine demand and DBPFP of the two inert precursors. For the four slow but active DBP precursors, MPUV/chlorine may accelerate their short-term DBP formation, whereas it showed an insignificant effect or even reduced their chlorine demand and DBPFP. For the only fast and active DBP precursor, MPUV/chlorine showed an insignificant effect on its short-term DBP formation or DBPFP. The overall effect of MPUV/chlorine was more significant at pH 6 than at pH 8. In the presence of Br−, MPUV/chlorine significantly increased the bromine substitution factors of THMs. In addition, linear fitting results indicated that the UV/chlorine-induced change in overall chlorine demand may be considered as a potential indicator for the prediction of DBPFP alteration.
Open AccessEffect of Medium Pressure Ultraviolet/Chlorine Advanced Oxidation on the Production of Disinfection by-Products from Seven Model Benzene Precursors
UV/chlorine advanced oxidation process (AOP), as a potential alternative to UV/H2O2 in water treatment, may pose a potential risk of increased disinfection by-product (DBP) formation and is of great concern. In this paper, seven benzene derivatives, containing two chlorine-inert and five chlorine-active compounds, were selected as typical model DBP precursors, and the effects of medium pressure UV/chlorine (MPUV/chlorine) on their chlorine demand and DBP formation potential (DBPFP) were evaluated. The results showed that MPUV/chlorine could significantly increase the chlorine demand and DBPFP of the two inert precursors. For the four slow but active DBP precursors, MPUV/chlorine may accelerate their short-term DBP formation, whereas it showed an insignificant effect or even reduced their chlorine demand and DBPFP. For the only fast and active DBP precursor, MPUV/chlorine showed an insignificant effect on its short-term DBP formation or DBPFP. The overall effect of MPUV/chlorine was more significant at pH 6 than at pH 8. In the presence of Br−, MPUV/chlorine significantly increased the bromine substitution factors of THMs. In addition, linear fitting results indicated that the UV/chlorine-induced change in overall chlorine demand may be considered as a potential indicator for the prediction of DBPFP alteration.