The Application Of Artificial Neural Network In Environment Quality Evaluation In Small Area Of Ziyang City

Environment quality assessment was one of the most important environmental managing institutions in china. It can make a scientific assessment for the environmental quality of a certain region, thus provide scientific foundations for environmental management, environmental engineering, environmental standards, environmental planning, comprehensive prevention and treatment, and ecological environmental construction etc. Scholars both domestic and foreign have done many researches on methods for environmental quality assessment in the past years, but most of the methods are general according a certain environmental element to assessment of multiple environmental quality indices in a big region, without proceeding environment quality assessment of several environmental elements in a concretion region, thus, in this paper, application of assessment method of ANN to assess the environmental quality of small region. The method is no reference to span administrative region and other regions could be divided into small region, and according to the traits of the region to select environmental quality parameters then put them into the model to assess and predict environmental quality. Thus, the method is universal applicability.In this paper, the BP-ANN environmental quality assessment model was improved, the expert samples (training samples) of BP-ANN model were extended to improve model's anti interference capacity and veracity. That is, created 10 training samples randomly between samples based on environmental standards instituted by government. And the improved BP-ANN model is applied in air and ground water environmental quality evaluation of the second bridge area of Tuo river in Ziyang city' s small region. then environmental monitoring results (involves air monitoring results and ground water monitoring results) of Ziyang city's small region was put into model respectively to assess air quality and ground water quality of Ziyang City's small region, the results shown that BP-ANN model is feasible in environmental quality assessment, at the same time, assessed conclusions are objective and assessed model is universal applicability. By comparing the evaluation result of ANN with that of fuzzy synthesis assessment, it can be found that the evaluation result from ANN is much objective and reasonable because the weights and thresholds of ANN can be determined through self-organization, self-adapting and self-studying, which avoid the subjective limitation in determining the weight factor of fuzzy synthesis assessment.