Application of a Hybrid Optimized BP Network Model to Estimate Water Quality Parameters of Beihai Lake in Beijing

Yan, Jianzhuo; Xu, Zongbao; Yu, Yongchuan; Xu, Hongxia; Gao, Kaili

doi:10.3390/app9091863

Cited by 59 publications

(39 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 12, the APE max of the MAGA-BP prediction model is only about 4%, while the APE of other prediction points is less than 2%, and the MAPE is 2.23%, which is also less than 3%. According to existing studies [29,40,[51][52][53][54], this prediction error is acceptable. Therefore, the MAGA-BP prediction model is reliable.…”

Section: Resultsmentioning

confidence: 94%

Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

Chen

Zhang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In order to accurately predict the erosion effect of underwater cleaning with an angle nozzle under different working conditions, this paper uses refractory bricks to simulate marine fouling as the erosion target, and studies the optimized erosion prediction model by erosion test based on the submerged low-pressure water jet. The erosion test is conducted by orthogonal experimental design, and experimental data are used for the prediction model. By combining with statistical range and variance analysis methods, the jet pressure, impact time and jet angle are determined as three inputs of the prediction model, and erosion depth is the output index of the prediction model. A virtual data generation method is used to increase the amount of input data for the prediction model. This paper also proposes a Mind-evolved Advanced Genetic Algorithm (MAGA), which has a reliable optimization effect in the verification of four stand test functions. Then, the improved back-propagating (BP) neural network prediction models are established by respectively using Genetic Algorithm (GA) and MAGA optimization algorithms to optimize the initial thresholds and weights of the BP neural network. Compared to the prediction results of the BP and GA-BP models, the R2 of the MAGA-BP model is the highest, reaching 0.9954; the total error is reduced by 47.31% and 35.01%; the root mean square error decreases by 51.05% and 31.80%; and the maximum absolute percentage error decreases by 65.79% and 64.01%, respectively. The average prediction accuracy of the MAGA-BP model is controlled within 3%, which has been significantly improved. The results show that the prediction accuracy of the MAGA-BP prediction model is higher and more reliable, and the MAGA algorithm has a good optimization effect. This optimized erosion prediction method is feasible.

show abstract

Section: Resultsmentioning

confidence: 94%

Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

Chen

Zhang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…As indicated in Table 8, the PSO-LSTM model used in this paper generally has a smaller MAPE value, which indicates a good performance at predicting water quality time series. To further illustrate that the PSO-LSTM model used in this paper has higher accuracy in predicting water quality time series, this paper compares it with the prediction results of literature [24], who used a hybrid optimized BP network model to predict dissolved oxygen time series. The results are reported in Table 8.…”

Section: Resultsmentioning

confidence: 99%

“…The mean absolute percentage error (MAPE) is used in this paper to compare the prediction performance of water time series prediction models when different datasets are used. The MAPE is defined and calculated as follows [24]:…”

Section: Model Evaluation Criteriamentioning

confidence: 99%

Application of a Parallel Particle Swarm Optimization-Long Short Term Memory Model to Improve Water Quality Data

Yan

Chen

et al. 2019

Water

Self Cite

View full text Add to dashboard Cite

Water quality data cleaning is important for the management of water environments. A framework for water quality time series cleaning is proposed in this paper. Considering the nonlinear relationships among water quality indicators, support vector regression (SVR) is used to forecast water quality indicators when some indicators are missing or when they show abnormal values at a certain point in time. Considering the time series of water quality information, long short-term memory (LSTM) networks are used to forecast water quality indicators when all indicators are missing at a certain point in time. A parallel model based on particle swarm optimization (PSO) and LSTM is realized based on a microservices architecture to improve the efficiency of model execution and the predictive accuracy of the LSTM networks. The performance of the model is evaluated in terms of the mean absolute error (MAE) and root-mean-square error (RMSE). Inlet water quality data from a wastewater treatment plant in Gaobeidian, Beijing, China is considered as a case study to examine the effectiveness of this approach. The experimental results reveal that this model has better predictive accuracy than other data-driven models because of smaller MAE and RMSE and has an advantage in terms of time consumption compared with standalone serial algorithms.

show abstract

“…Consequently, the former was found to perform marginally better for majority of the results. Yan et al (2019) [32] proposed a hybrid optimized algorithm involving particle swarm optimization (PSO) and genetic algorithm (GA) combined with a BP neural network that can predict the water quality in time series and exhibited a good performance in the Beihai Lake in Beijing. Their study results denoted that the model based on PSO and GA that optimized the BP neural network can predict the water quality parameters with a reasonable accuracy, suggesting that this model is valuable for estimating the quality of lake water.…”

Section: Introductionmentioning

confidence: 99%

“…Both the model performances were subsequently compared to evaluate their robustness. The highest correlation function kernel and selection of the most optimal input design were executed in different prediction horizons (i.e., 1, 5, 10, 20, and 40 years) [31][32][33] using the two proposed methods.…”

Section: Introductionmentioning

confidence: 99%

Modeling the Nonlinearity of Sea Level Oscillations in the Malaysian Coastal Areas Using Machine Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

The estimation of an increase in sea level with sufficient warning time is important in low-lying regions, especially in the east coast of Peninsular Malaysia (ECPM). This study primarily aims to investigate the validity and effectiveness of the support vector machine (SVM) and genetic programming (GP) models for predicting the monthly mean sea level variations and comparing their prediction accuracies in terms of the model performances. The input dataset was obtained from Kerteh, Tioman Island, and Tanjung Sedili in Malaysia from January 2007 to December 2017 to predict the sea levels for five different time periods (1, 5, 10, 20, and 40 years). Further, the SVM and GP models are subjected to preprocessing to obtain optimal performance. The tuning parameters are generalized for the optimal input designs (SVM2 and GP2), and the results denote that SVM2 outperforms GP with R of 0.81 and 0.86 during the training and testing periods, respectively, at the study locations. However, GP can provide values of 0.71 and 0.79 for training and testing, respectively, at the study locations. The results show precise predictions of the monthly mean sea level, denoting the promising potential of the used models for performing sea level data analysis.

show abstract

Application of a Hybrid Optimized BP Network Model to Estimate Water Quality Parameters of Beihai Lake in Beijing

Cited by 59 publications

References 25 publications

Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

Application of a Parallel Particle Swarm Optimization-Long Short Term Memory Model to Improve Water Quality Data

Modeling the Nonlinearity of Sea Level Oscillations in the Malaysian Coastal Areas Using Machine Learning Algorithms

Contact Info

Product

Resources

About