Analysis of Water Pollution Causes and Control Countermeasures in Liaohe Estuary via Support Vector Machine Particle Swarm Optimization under Deep Learning

Abstract

This study explores the loss or degradation of the ecosystem and its service function in the Liaohe estuary coastal zone due to the deterioration of water quality. A prediction system based on support vector machine (SVM)-particle swarm optimization (PSO) (SVM-PSO) algorithm is proposed under the background of deep learning. SVM-PSO algorithm is employed to analyze the pollution status of the Liaohe estuary, so is the difference in water pollution of different sea consuming types. Based on the analysis results for causes of pollution, the control countermeasures of water pollution in Liaohe estuary are put forward. The results suggest that the water pollution index prediction model based on SVM-PSO algorithm shows the maximum error of 2.41%, the average error of 1.24% in predicting the samples, the root mean square error (RMSE) of 5.36 × 10 −4 , and the square of correlation coefficient of 0.91. Therefore, the prediction system in this study is feasible. At present, the water pollution status of Liaohe estuary is of moderate and severe levels of eutrophication, and the water pollution status basically remains at the level of mild pollution. The general trend is from phosphorus moderate restricted eutrophication to phosphorus restricted potential eutrophication. To sum up, the SVM-PSO algorithm shows good sewage prediction ability, which can be applied and promoted in water pollution control and has reliable reference significance.

A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years

“…All three models have shown good performance in predicting WQI, effectively shortening the calculation time and reducing errors in the derivation process of sub-indicators. Guize Liu et al [149] proposed a prediction system based on the Support Vector Machine and Particle Swarm Optimization algorithm. The results show that the maximum error of the water pollution index prediction model for sample prediction is 2.41%, the average error is 1.24%, and the root mean square error is 5.36 × 10 −4 , with a correlation coefficient of 0.91 squared.…”

Predicting Groundwater Indicator Concentration Based on Long Short-Term Memory Neural Network: A Case Study

“…Human activities affect groundwater quality [ 14 ]. Due to the imperfect sewage treatment facilities, wastewater would pollute the surrounding surface water systems and soil [ 15 , 16 ]. The discharge of domestic wastewater and the excessive use of chemical fertilizers aggravate the pollution of groundwater.…”

Evaluation of total dissolved solids in rivers by improved neuro fuzzy approaches using metaheuristic algorithms

“…The results showed that, for predicting electrical conductivity (EC) and total hardness (TH) in the test stage, ANFIS-DE was the most appropriate model. Liu et al (2022) used support vector machine particle swarm optimization with deep learning to investigate the causes of water pollution and control countermeasures in the Liaohe estuary. The results showed that the SVM-PSO approach has excellent predictive performance.…”