With the development of social economy, the Water Pollution (WP) caused by people’s improper lifestyle is becoming more and more serious. Especially in recent years, WP has occurred frequently, and the protection of water environment health has become an urgent problem to be solved. WP prediction is the basis of water resources management and WP control, and ensuring the accuracy of WP prediction is extremely important for WP prevention and planning. In this article, the prediction of WP was studied; the detection method of WP based on spectral method and the prediction method of WP based on spectral method and improved Back Propagation (BP) Neural Network (NN) were proposed; the effect and application of the prediction method were studied. The research showed that the sum of square error and mean square error generated by the improved BP WP prediction method were 9.4 and 1.88 respectively, while the sum of square error and mean square error generated by the traditional BP WP prediction method were 299.49 and 59.9 respectively. Compared with the traditional BP WP prediction method, the improved BP WP prediction method had a more accurate prediction effect. At the same time, this article used the improved BP WP prediction method to evaluate the pollution risk level of the two water environments in Z City. The conclusion was that the water environment W belongs to the water environment with low pollution risk level; water environment R belongs to water environment with medium pollution risk level.

Saleme Estevao. Evaluation on Water Pollution Prediction and Evaluation Method Based on Spectral Method. Water Pollution Prevention and Control Project (2020), Vol. 1, Issue 1: 40-50. https://doi.org/10.38007/WPPCP.2020.010105.

[1] Yan Yan. Ecological risk assessment from the viewpoint of surface water pollution in Xiamen City, China.International Journal of Sustainable Development & World Ecology 25.5 (2018): 403-410. https://doi.org/10.1080/13504509.2017.1422567

[2] Kumar Vinod. Assessment of heavy-metal pollution in three different Indian water bodies by combination of multivariate analysis and water pollution indices. Human and ecological risk assessment: an international journal (2018) 26(1): 1-16. https://doi.org/10.1080/10807039.2018.1497946

[3] Xinyan Li, Hao Wu, Hui Qian. Groundwater contamination risk assessment using intrinsic vulnerability, pollution loading and groundwater value: a case study in Yinchuan plain, China. Environmental Science and Pollution Research. (2020) 27(36): 45591-45604. https://doi.org/10.1007/s11356-020-10221-4

[4] Yankui Tang. Emerging pollutants in water environment: Occurrence, monitoring, fate, and risk assessment. Water Environment Research. (2019) 91(10): 984-991. https://doi.org/10.1002/wer.1163

[5] Chen Sophia Shuang. Assessment of urban river water pollution with urbanization in East Africa. Environmental Science and Pollution Research. (2020) 29(27): 40812-40825. 

[6] Solangi Ghulam Shabir. Groundwater quality evaluation using the water quality index (WQI), the synthetic pollution index (SPI), and geospatial tools: a case study of Sujawal district, Pakistan. Human and Ecological Risk Assessment: An International Journal. (2020) 26(6): 1529-1549. https://doi.org/10.1080/10807039.2019.1588099

[7] Huanhai Yang, Shue Liu. A prediction model of aquaculture water quality based on multiscale decomposition. Mathematical Biosciences and Engineering. (2020) 18(6): 7561-7579. https://doi.org/10.3934/mbe.2021374

[8] Bisht Anil Kumar. Artificial neural network based water quality forecasting model for ganga river. International Journal of Engineering and Advanced Technology. (2019) 8(6): 2778-2785. https://doi.org/10.35940/ijeat.F8841.088619

[9] Haghiabi Amir Hamzeh, Ali Heidar Nasrolahi, Abbas Parsaie. Water quality prediction using machine learning methods. Water Quality Research Journal. (2018) 53(1): 3-13. https://doi.org/10.2166/wqrj.2018.025

[10] Barzegar Rahim, Mohammad Taghi Aalami, Jan Adamowski. Short-term water quality variable prediction using a hybrid CNN-LSTM deep learning model. Stochastic Environmental Research and Risk Assessment. (2020) 34(2): 415-433. https://doi.org/10.1007/s00477-020-01776-2

[11] Ayaz Muhammad, Nasir-Uddin Khan. Forecasting of heavy metal contamination in coastal sea surface waters of the karachi harbour area by neural network approach. Nature Environment and Pollution Technology. (2019) 18(3): 719-733.

[12] Leong, Wei Cong. Prediction of water quality index (WQI) using support vector machine (SVM) and least square-support vector machine (LS-SVM). International Journal of River Basin Management. (2019) 19(2): 149-156. https://doi.org/10.1080/15715124.2019.1628030

[13] Hassan MdMehedi. Efficient prediction of water quality index (WQI) using machine learning algorithms. Human-Centric Intelligent Systems. (2020) 1(3-4): 86-97. https://doi.org/10.2991/hcis.k.211203.001

[14] Simin Ge. Microcystin in source water: pollution characteristics and human health risk assessment. RSC advances. (2020) 11(11): 6415-6422. https://doi.org/10.1039/D0RA08983D

[15] Feng Liu. A prediction method of urban water pollution based on improved BP neural network. International Journal of Environmental Technology and Management. (2020) 24(3-4): 294-306.