Constructing Urban Building Water Environment Governance through Digital Art-Enhanced Big Data Visualization

Abstract

This paper studies the visualization of urban water environment governance based on big data analysis. The nonlinear compensation model based on neural network aims at the error in the process of water quality prediction, and describes the migration and transformation of pollutants in the river water environment by analyzing the causes of river pollution. Establish a visual management system for urban water environment governance. After pretreatment, take it as input data, input it in the training model, and make a prediction. The visual simulation results of the case show that the relationship between runoff and rainfall can be described by runoff coefficient, and the calculated runoff coefficient is 0.326. The improvement rate of ammonia nitrogen in the same water period changes slightly, while the improvement rate of different rivers and different river sections varies greatly, with the change range of more than 25%-93%. It is necessary to strengthen the comprehensive analysis and application ability of big data, continuously improve the systematization, scientification, refinement and visualization level of water environment monitoring, and provide strong support for scientific management of ecological environment.