Li Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Li Wang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Huiyan Zhang
Beijing Laboratory for Intelligent Environmental Protection, School of Computer and Artificial Intelligence, Beijing Technology & Business University, Beijing 100048, China
6 shared publications - Jiping Xu
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
6 shared publications - Xiaoyi Wang
China Conservatory of Music, Beijing 100101, China
5 shared publications - Zhiyao Zhao
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
5 shared publications - Jiabin Yu
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
4 shared publications - Qian Sun
Beijing Laboratory for Intelligent Environmental Protection, School of Computer and Artificial Intelligence, Beijing Technology & Business University, Beijing 100048, China
4 shared publications
Latest Publications
- Open Access
- 20 June 2026
- Published by IWA Publishing in Water Reuse
- Vol. 16 (3) , 505-526
Method for predicting eutrophication in water bodies based on dual experience pool TDDPG and DDPG-dual 3Q learning mode
A three-layer flow diagram of a deep reinforcement learning framework for water eutrophication prediction. It shows multi-factor water quality data input and preprocessing, three core models (DDPG-Double 3Q fusion, improved Double 3Q learning with LSTM and Transformer, and dual experience pool TDDPG), and output evaluation with prediction curves and metrics (MAE 0.012, RMSE 0.018, MAPE 3.5%, TLI 52.4). Water eutrophication prediction remains challenging due to poor long-term feature retention, susceptibility to local optima, and difficulties in balancing smooth and abrupt time-series patterns. To address these issues, this study develops a two-stage reinforcement-learning forecasting framework in which Transformer-based temporal representation, auxiliary replay learning, and error-aware Q-value selection are jointly organized for multivariate eutrophication prediction. In the first stage, the TDDPG model replaces the conventional actor representation in DDPG with a Transformer-based temporal feature extractor and uses an auxiliary replay buffer to reduce the effect of strongly correlated sequential samples during policy learning. In the second stage, the DDPG-Double 3Q model treats the outputs and errors of several DDPG-based predictors as decision states, allowing the final prediction policy to select and refine candidate predictions under both gradual and abrupt water-quality variations. Experimental validation using multi-factor water quality monitoring data demonstrates that the proposed framework achieves an average improvement of 35% across key evaluation metrics – Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) compared to baseline models such as ADDPG and RDPG. The results indicate that the framework improves prediction accuracy and training stability in the tested dataset, suggesting that reinforcement learning can provide a useful sequential decision-making formulation for multivariate eutrophication forecasting.
- 20 June 2026
- Published by IWA Publishing in Water Reuse
- Vol. 16 (3) , 505-526
Open AccessMethod for predicting eutrophication in water bodies based on dual experience pool TDDPG and DDPG-dual 3Q learning mode
A three-layer flow diagram of a deep reinforcement learning framework for water eutrophication prediction. It shows multi-factor water quality data input and preprocessing, three core models (DDPG-Double 3Q fusion, improved Double 3Q learning with LSTM and Transformer, and dual experience pool TDDPG), and output evaluation with prediction curves and metrics (MAE 0.012, RMSE 0.018, MAPE 3.5%, TLI 52.4). Water eutrophication prediction remains challenging due to poor long-term feature retention, susceptibility to local optima, and difficulties in balancing smooth and abrupt time-series patterns. To address these issues, this study develops a two-stage reinforcement-learning forecasting framework in which Transformer-based temporal representation, auxiliary replay learning, and error-aware Q-value selection are jointly organized for multivariate eutrophication prediction. In the first stage, the TDDPG model replaces the conventional actor representation in DDPG with a Transformer-based temporal feature extractor and uses an auxiliary replay buffer to reduce the effect of strongly correlated sequential samples during policy learning. In the second stage, the DDPG-Double 3Q model treats the outputs and errors of several DDPG-based predictors as decision states, allowing the final prediction policy to select and refine candidate predictions under both gradual and abrupt water-quality variations. Experimental validation using multi-factor water quality monitoring data demonstrates that the proposed framework achieves an average improvement of 35% across key evaluation metrics – Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) compared to baseline models such as ADDPG and RDPG. The results indicate that the framework improves prediction accuracy and training stability in the tested dataset, suggesting that reinforcement learning can provide a useful sequential decision-making formulation for multivariate eutrophication forecasting.
- 8 September 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 184
A Transformer-based water quality prediction model with mixed fractional Brownian features and multi-feature bottleneck transformation
- 8 September 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 184
A Transformer-based water quality prediction model with mixed fractional Brownian features and multi-feature bottleneck transformation
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (8) , 13418-13430
Environment Fusion Routing Protocol for Wireless Sensor Networks
Wireless sensor network (WSN) is usually deployed in unattended monitoring environments, with limited energy and large-scale characteristics. Therefore, the performance of WSN is susceptible to the influence of external environment and its own energy. The existing routing protocols try to optimize energy efficiency and routing reliability from the perspective of the network itself. However, they do not take into account the environmental impact from the outside, which makes them unable to properly respond to harsh environment. Therefore, a new Environment Fusion Routing Protocol (EFRP) is proposed. Cluster heads are selected in a probabilistic manner according to the ratio of the energy of each node and environmental factors. Nodes with excellent environment have a higher probability of being selected as cluster heads. Besides, the EFRP optimal path is determined according to the comprehensive potential field superimposed by the distance field, residual energy field and environmental field. The best path can be weighed among delay, energy saving and routing invulnerability. Therefore, the balance of network energy is realized and the invulnerability of the network in harsh environment is improved. The experimental results show that EFRP can significantly improve the data transmission and invulnerability of the network in harsh environments.
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (8) , 13418-13430
Environment Fusion Routing Protocol for Wireless Sensor Networks
Wireless sensor network (WSN) is usually deployed in unattended monitoring environments, with limited energy and large-scale characteristics. Therefore, the performance of WSN is susceptible to the influence of external environment and its own energy. The existing routing protocols try to optimize energy efficiency and routing reliability from the perspective of the network itself. However, they do not take into account the environmental impact from the outside, which makes them unable to properly respond to harsh environment. Therefore, a new Environment Fusion Routing Protocol (EFRP) is proposed. Cluster heads are selected in a probabilistic manner according to the ratio of the energy of each node and environmental factors. Nodes with excellent environment have a higher probability of being selected as cluster heads. Besides, the EFRP optimal path is determined according to the comprehensive potential field superimposed by the distance field, residual energy field and environmental field. The best path can be weighed among delay, energy saving and routing invulnerability. Therefore, the balance of network energy is realized and the invulnerability of the network in harsh environment is improved. The experimental results show that EFRP can significantly improve the data transmission and invulnerability of the network in harsh environments.
- Open Access
- 8 February 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (4) , 2911-2925
Environment adaptive deployment of water quality sensor networks
- 8 February 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (4) , 2911-2925
Open AccessEnvironment adaptive deployment of water quality sensor networks
- Open Access
- 1 January 2021
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 68 (3) , 3967-3977
Energy-Efficient Deployment of Water Quality Sensor Networks
Water quality sensor networks are promising tools for the exploration of oceans. Some key areas need to be monitored effectively. Water quality sensors are deployed randomly or uniformly, however, and understanding how to deploy sensor nodes reasonably and realize effective monitoring of key areas on the basis of monitoring the whole area is an urgent problem to be solved. Additionally, energy is limited in water quality sensor networks. When moving sensor nodes, we should extend the life cycle of the sensor networks as much as possible. In this study, sensor nodes in non-key monitored areas are moved to key areas. First, we used the concentric circle method to determine the mobile sensor nodes and the target locations. Then, we determined the relationship between the mobile sensor nodes and the target locations according to the energy matrix. Finally, we calculated the shortest moving path according to the Floyd algorithm, which realizes the redeployment of the key monitored area. The simulation results showed that, compared with the method of direct movement, the proposed method can effectively reduce the energy consumption and save the network adjustment time based on the effective coverage of key areas.
- 1 January 2021
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 68 (3) , 3967-3977
Open AccessEnergy-Efficient Deployment of Water Quality Sensor Networks
Water quality sensor networks are promising tools for the exploration of oceans. Some key areas need to be monitored effectively. Water quality sensors are deployed randomly or uniformly, however, and understanding how to deploy sensor nodes reasonably and realize effective monitoring of key areas on the basis of monitoring the whole area is an urgent problem to be solved. Additionally, energy is limited in water quality sensor networks. When moving sensor nodes, we should extend the life cycle of the sensor networks as much as possible. In this study, sensor nodes in non-key monitored areas are moved to key areas. First, we used the concentric circle method to determine the mobile sensor nodes and the target locations. Then, we determined the relationship between the mobile sensor nodes and the target locations according to the energy matrix. Finally, we calculated the shortest moving path according to the Floyd algorithm, which realizes the redeployment of the key monitored area. The simulation results showed that, compared with the method of direct movement, the proposed method can effectively reduce the energy consumption and save the network adjustment time based on the effective coverage of key areas.
- Open Access
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 216762-216771
Event-Triggered State Estimation for Wireless Sensor Network Systems With Packet Losses and Correlated Noises
In this article, an event-triggered state estimation problem for wireless sensor network systems affected by random packet losses and correlated noises is considered. A set of independent Bernoulli variables are used to describe the random packet losses in the measurement transmission. An event-triggered transmission strategy is introduced to decrease limited network bandwidth consumption, and the measurement noise is correlated with the process noises of the same moment and the previous moment. Event-triggered estimator of process noises under the linear minimum variance criterion is derived. Then, an event-triggered state estimation algorithm related to the packet loss rate, noise correlation coefficient and triggering threshold is designed. Sufficient conditions are provided to guarantee convergence of the estimation error covariances of the proposed estimator. Finally, comparative simulation verifies the effectiveness of our algorithm.
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 216762-216771
Open AccessEvent-Triggered State Estimation for Wireless Sensor Network Systems With Packet Losses and Correlated Noises
In this article, an event-triggered state estimation problem for wireless sensor network systems affected by random packet losses and correlated noises is considered. A set of independent Bernoulli variables are used to describe the random packet losses in the measurement transmission. An event-triggered transmission strategy is introduced to decrease limited network bandwidth consumption, and the measurement noise is correlated with the process noises of the same moment and the previous moment. Event-triggered estimator of process noises under the linear minimum variance criterion is derived. Then, an event-triggered state estimation algorithm related to the packet loss rate, noise correlation coefficient and triggering threshold is designed. Sufficient conditions are provided to guarantee convergence of the estimation error covariances of the proposed estimator. Finally, comparative simulation verifies the effectiveness of our algorithm.
- Open Access
- 3 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 26235-26246
An Action Dependent Heuristic Dynamic Programming Approach for Algal Bloom Prediction With Time-Varying Parameters
- 3 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 26235-26246
Open AccessAn Action Dependent Heuristic Dynamic Programming Approach for Algal Bloom Prediction With Time-Varying Parameters
- Open Access
- 6 March 2018
- Published by Wiley in Journal of Chemistry
- Vol. 2018, 1-14
A Fusion Water Quality Soft-Sensing Method Based on WASP Model and Its Application in Water Eutrophication Evaluation
Water environment protection is of great significance for both economic development and improvement of people’s livelihood, where modeling of water environment evolution is indispensable in water quality analysis. However, many water quality indexes related to water quality model cannot be measured online, and some model parameters always vary among different water areas. Thus, this paper proposes a water quality soft-sensing method based on the water quality mechanism model to simulate evolution of water quality indexes online, where unscented Kalman filter is utilized to estimate model parameters. Furthermore, a modified fuzzy comprehensive evaluation method is presented to evaluate the level of water eutrophication condition. Finally, the water quality data collected from Taihu Lake and Beihai Lake are used to validate the effectiveness and generality of the proposed method. The results show that the proposed soft-sensing method is able to describe the variation of related water quality indexes, with better accuracy compared to nonlinear least squares based method and traditional trial-and-error based method. On this basis, the water eutrophication condition can be also accurately evaluated.
- 6 March 2018
- Published by Wiley in Journal of Chemistry
- Vol. 2018, 1-14
Open AccessA Fusion Water Quality Soft-Sensing Method Based on WASP Model and Its Application in Water Eutrophication Evaluation
Water environment protection is of great significance for both economic development and improvement of people’s livelihood, where modeling of water environment evolution is indispensable in water quality analysis. However, many water quality indexes related to water quality model cannot be measured online, and some model parameters always vary among different water areas. Thus, this paper proposes a water quality soft-sensing method based on the water quality mechanism model to simulate evolution of water quality indexes online, where unscented Kalman filter is utilized to estimate model parameters. Furthermore, a modified fuzzy comprehensive evaluation method is presented to evaluate the level of water eutrophication condition. Finally, the water quality data collected from Taihu Lake and Beihai Lake are used to validate the effectiveness and generality of the proposed method. The results show that the proposed soft-sensing method is able to describe the variation of related water quality indexes, with better accuracy compared to nonlinear least squares based method and traditional trial-and-error based method. On this basis, the water eutrophication condition can be also accurately evaluated.
- Open Access
- 1 January 2017
- Published by Wiley in Advances in Mathematical Physics
- Vol. 2017, 1-7
The Adaptive-Clustering and Error-Correction Method for Forecasting Cyanobacteria Blooms in Lakes and Reservoirs
Globally, cyanobacteria blooms frequently occur, and effective prediction of cyanobacteria blooms in lakes and reservoirs could constitute an essential proactive strategy for water-resource protection. However, cyanobacteria blooms are very complicated because of the internal stochastic nature of the system evolution and the external uncertainty of the observation data. In this study, an adaptive-clustering algorithm is introduced to obtain some typical operating intervals. In addition, the number of nearest neighbors used for modeling was optimized by particle swarm optimization. Finally, a fuzzy linear regression method based on error-correction was used to revise the model dynamically near the operating point. We found that the combined method can characterize the evolutionary track of cyanobacteria blooms in lakes and reservoirs. The model constructed in this paper is compared to other cyanobacteria-bloom forecasting methods (e.g., phase space reconstruction and traditional-clustering linear regression), and, then, the average relative error and average absolute error are used to compare the accuracies of these models. The results suggest that the proposed model is superior. As such, the newly developed approach achieves more precise predictions, which can be used to prevent the further deterioration of the water environment.
- 1 January 2017
- Published by Wiley in Advances in Mathematical Physics
- Vol. 2017, 1-7
Open AccessThe Adaptive-Clustering and Error-Correction Method for Forecasting Cyanobacteria Blooms in Lakes and Reservoirs
Globally, cyanobacteria blooms frequently occur, and effective prediction of cyanobacteria blooms in lakes and reservoirs could constitute an essential proactive strategy for water-resource protection. However, cyanobacteria blooms are very complicated because of the internal stochastic nature of the system evolution and the external uncertainty of the observation data. In this study, an adaptive-clustering algorithm is introduced to obtain some typical operating intervals. In addition, the number of nearest neighbors used for modeling was optimized by particle swarm optimization. Finally, a fuzzy linear regression method based on error-correction was used to revise the model dynamically near the operating point. We found that the combined method can characterize the evolutionary track of cyanobacteria blooms in lakes and reservoirs. The model constructed in this paper is compared to other cyanobacteria-bloom forecasting methods (e.g., phase space reconstruction and traditional-clustering linear regression), and, then, the average relative error and average absolute error are used to compare the accuracies of these models. The results suggest that the proposed model is superior. As such, the newly developed approach achieves more precise predictions, which can be used to prevent the further deterioration of the water environment.