Artificial Neural Network Based Water Quality Forecasting Model for Ganga River

Water is an important natural resource and an essential material guarantee for human survival and development. With the continuous development and progress of social economy, people's demand for water resources is higher and higher, but the current water environment is not optimistic, so the water quality evaluation and management is very urgent. In practical work, in order to ensure that the water quality reaches the standard, a variety of methods need to be used for testing, the most common of which is water sample analysis. However, due to the immature testing technology, and most of the tasks of water sample determination are completed manually, many samples are difficult to obtain accurately, resulting in large deviation of the test results, which cannot meet the current water quality monitoring requirements. Principal component analysis, particle swarm optimization (PSO) and support vector machine (SVM) models are widely used in the research field of water pollutant content as effective prediction and analysis methods, which can well link various elements in the water environment and realize reasonable judgment and control of the impact laws and change laws of different substance concentration changes. At the same time, it plays a very positive role in protecting the ecological environment. In this paper, the principal component analysis model and PSO algorithm were described in detail. Combining the SVM model and the adaptive learning mechanism of PSO, a set of online water environment quality monitoring system based on PSO was designed and developed, which provided technical support for solving the problems of the lack of representativeness and poor accuracy of traditional water quality monitoring data. Compared with the traditional single neural network, the result showed that the SVM-based evaluation model had a higher prediction effect, and the accuracy was also improved by about 6.5%, which can reflect the water pollution situation more truly and reliably.

Section: Introductionmentioning

confidence: 99%

Water Quality Evaluation Model Based on Principal Component and Particle Swarm Optimization Support Vector Machine

2021

“…In addition, some researchers have explored the monitoring and prediction methods of water resources, hoping to get a perfect monitoring and prediction model. Bisht Anil Kumar mainly explored the water quality prediction model in a certain area and determined the feasibility of artificial intelligence in the water quality prediction model [8]. Yang Huanhai explored the water quality prediction model in multi-scale aquaculture and determined the reliability of this multi-scale water quality prediction model [9].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Water Quality Monitoring Indicators Based on Random Forest

2020

Water resources are not only the material basis to support the current social and economic development, but also an important resource to maintain people's daily life. Therefore, the protection of water resources from being infringed not only requires the cooperation of relevant researchers, but also is closely related to every resident in the society. Everyone needs to pay more attention to it. In the current society, the water environment in different regions is generally protected through multiple processes. Among them, the first line of defense is the monitoring of water quality and the prediction model of indicators. The monitoring and early warning model of water quality indicators is generally based on the real-time monitoring of the content of various substances in the water environment, so as to comprehensively evaluate the water environment and predict the water quality in the future period according to the concentration of different substances. The existing water quality indicator monitoring and prediction model not only is an important technology to control water environmental pollution in the current society, but also can reflect the quality status in the target waters and the future water quality development trend in all aspects. More professional water quality related data can be collected through the existing monitoring models of various indicators of water quality. Based on the in-depth analysis of these data, the main pollutants in the target waters, the current pollution situation and the possible future damage can be fully understood. On the other hand, this water quality indicator monitoring model has also provided assistance for professionals to develop more scientific and reasonable water pollution control plans. In this paper, the existing water quality index monitoring and prediction model was updated by using the stochastic forest algorithm model. The stochastic forest algorithm model generally predicts the indicators and pollution status of the target water area in the future by processing the relevant data of the water quality indicators of the target water area. Finally, the performance of this new water quality monitoring index and prediction model has been improved by about 26% on average.

“…Bisht Anil Kumar can obtain the severity assessment data of local water pollution problems through the assessment of local water quality and the combination of artificial neural network technology. The analysis of the data can determine the feasibility of this technology in water pollution control [10]. Yang Huanhai reflected the severity of local water pollution problems by studying the normal growth of local aquatic products, and combined the prediction model based on long-term and short-term memory neural network.…”

Section: Introductionmentioning

confidence: 99%

Evaluation on the Construction of Water Pollution Control Model Based on Random Forest

2020

With the continuous development of society, water pollution has become an important factor restricting people's survival and development, so it is necessary to establish a system that can effectively control water quality, ensure drinking water safety and reduce water waste. Water pollution control means to reduce water consumption, improve water quality and protect the ecological environment by designing an environmental protection measure that can effectively prevent water eutrophication. However, due to the insufficient attention paid to the assessment of water quality, many water bodies have been seriously affected. In order to solve the problems of traditional water pollution control models that rely too much on the subjective judgment and professional knowledge of experts and scholars, such as high difficulty in predicting water pollution problems and low prediction accuracy, based on reality, a stochastic forest algorithm was proposed to build control models to solve the problem. The divided interval samples were collected by computer, and then the samples were randomly classified by random forest algorithm. The calculated average generalization error was reduced by continuously introducing random variables. The final sample classification can more intuitively see the real-time state of water quality. Finally, according to the experimental data, the water pollution control model based on random forest proposed in this paper has an average increase of 13.1% in the four evaluation indicators compared with the traditional water pollution control model.