Nguyễn Hiền Thân * , Chế Đình Lý Phạm Văn Tất

* Tác giả liên hệ (nhthan@nomail.com)

Abstract

Water pollution has been increasing quickly and complexly for recent years. Water quality forecast to provide prompt and timely information on water pollution is very necessary. In this study, the aim of the study was to compare capability of water quality forecast by the multilayer perceptron neural network method and the grey theory method that emphasized rapid predictability and accuracy, contributing to improving the efficiency of water quality forecast. The data were collected from 23 monitoring stations of Dong Nai river from 2010 to 2014 in Dong Nai and Binh Duong Department of Natural Resources and Environment for forecasting the water quality index. The results showed that both methods had good performance of water quality forecast. The water quality index forecasted by the multilayer perceptron neural network model showed higher accuracy (RMSE = 2.88, R2 = 0.987 and P = 0) than that forecasted by the grey theory model (RMSE = 7.84, R2 = 0.879 and P = 0).
Keywords: Artificial neural network, comparing, forecast, grey theory, water quality

Tóm tắt

Ô nhiễm môi trường nước đang gia tăng nhanh chóng và phức tạp trong những năm gần đây. Dự đoán chất lượng nước nhằm cung cấp thông tin nhanh chóng và kịp thời về tình trạng ô nhiễm nguồn nước là rất cần thiết. Trong nghiên cứu này, khả năng dự đoán chất lượng nước được so sánh bằng phương pháp mạng nơ ron perceptron nhiều lớp và phương pháp lý thuyết xám tập trung khả năng dự đoán nhanh và độ chính xác góp phần nâng cao hiệu quả công tác dự đoán chất lượng nước. Dữ liệu nghiên cứu được thu thập tại 23 điểm quan trắc chất lượng nước Sông Đồng Nai từ 2010 – 2014 tại Sở Tài nguyên và Môi trường tỉnh Đồng Nai và Bình Dương dùng để dự đoán chỉ số chất lượng nước (WQI). Kết quả nghiên cứu cho thấy cả hai phương pháp cho kết quả dự đoán tốt chất lượng nước. Chỉ số chất lượng nước được dự đoán bằng mạng nơ ron có độ chính xác cao hơn (RMSE =2,88, R2 = 0,987 và P = 0) so với phương pháp dự đoán bằng lý thuyết xám (RMSE =7,84, R2 = 0,879 và P = 0).
Từ khóa: Chất lượng nước, dự đoán, lý thuyết xám, mạng nơ ron nhân tạo, so sánh

Article Details

Tài liệu tham khảo

Ali Mohammadi, & Zade, S. Z., 2011. Appling grey forecasting method to forecast the portfolio’s rate of return in stock market of Iran. Australian Journal of Business and Management Research. 1: 1-16.

Alireza Shakeri Abdolmaleki, A. G. A., Jaber Soltani, 2013. Artificial neural network (ann) approach for predicting Cu concentration in drinking water of Chahnimeh1 reservoir in Sistan-Balochistan, Iran. Health Scope. 2: 31-38.

Alkarkhi, A. F. M., Ahmad, A., & Easa, A. M., 2009. Assessment of surface water quality of selected estuariesof Malaysia: multivariate statistical techniques. The Environmentalist. 29: 255–262.

Vishnu B and P, Syamala, 2012. Grey model for stream flow prediction, Aceh International Journal of Science and Technology. 1:14-19.

Banejad, H., & Olyaie, E., 2011. Application of an artificial neural network model to rivers water quality indexes prediction – a case study. Journal of American Science. 7: 60-65.

Barzegar, R., Adamowski, J., & Moghaddam, A. A., 2016. Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran. Stochastic Environmental Research and Risk Assessment. 1-23.

Diamantopoulou, M. J., Antonopoulos, V. Z., & Papamichail, D. M., 2005. The use of a neural network technique for the prediction of water quality parameters of Axios River in Northern Greece. European Water. 11(12): 55-62.

Dounis, A. I., Tiropanis, P., Tseles, D., Nikolaou, G., & Syrcos, G. P., 2006. A comparison of grey model and fuzzy predictive model for time series. International Journal of Information and Mathematical Sciences. 2: 176-181.

Haiyan, W., 2002. Assessment and prediction of overall environmental quality of Zhuzhou City, Hunan Province, China. Environmental Management. 66: 329-340.

Hsu, C.-C., & Chen, C.-Y., 2003. Applications of improved grey prediction model for power demand forecasting. Energy Conversion and Management. 44: 2241–2249.

Kazemi, A., Modarres, M., & al, e., 2011. A markov chain grey forecasting model: a case study of energy demand of industry sector in Iran. 2011 3rd International Conference on Information and Financial Engineering. 12: 13-18.

Lin, Y.-H., Chiu, C.-C., Lin, Y.-J., & Lee, P.-C., 2013. Rainfall prediction using innovative grey model with the dynamic index. Journal of Marine Science and Technology. 21: 63-75.

Lobbrecht, A. H., Dibike, Y. B., & Solomatine, D. P., 2002. Applications of neural networks and fuzzy logic to integrated water management. 5: 50-58

Mekanik, F., Lee, T. S., & Imteaz, M. A., 2011. Rainfall modeling using artificial neural network for a mountainous region in West Iran. Paper presented at the Proceedings of the 19th International Congress on Modelling and Simulation, Perth, Australia.

Pai, T.-Y., Ho, C.-L., & et al., 2011. Using seven types of GM (1, 1) model to forecast hourly particulate matter concentration in Banciao City of Taiwan. Water, Air, & Soil Pollution. 217: 25-33.

Palani, S., Liong, S.-Y., & Tkalich, P., 2008. An ANN application for water quality forecasting. Marine Pollution Bulletin. 56: 1586 - 1597.

Patki, V. K., Shrihari, S., & Manu, B., 2013. Water quality prediction in distribution system using cascade feed forward neural network. International Journal of Advanced Technology in Civil Engineering. 2(1): 84-91.

Sarani, N., Soltani, J., Sarani, S., & Moasheri, A., 2012. Comparison of artificial neural network and multivariate linear regression model to predict sodium adsorption ratio (SAR) (case study: Sistan River, Iran). International Journal of Biological, Ecological and Environmental Sciences. 1: 2277 – 4394.

Sayadi, M., Rezaei, A., Rezaei, M., & Nourozi, K., 2014. Multivariate statistical analysis of surface water chemistry: A case study of Gharasoo River, Iran Paper presented at the Proceedings of the International Academy of Ecology and Environmental Sciences.

Slavek, N., & Jovi´c, A., 2012. Application of grey system theory to software projects ranking. 53:284-293.

Thair S.K, Abdul Hameed M. J, & Ayad S. M., 2014. Prediction of water quality of Euphrates River by using artificial neural network model (spatial and temporal study). International Research Journal of Natural Sciences. 2(3): 25-38.

Tổng cục Môi trường, 2011. Quyết định số 879/QĐ-TCMT về việc ban hành sổ tay hướng dẫn tính toán chỉ số chất lượng nước. Hà Nội.

Xuepeng, J., Zhisheng, X., Jianming, W., & Xiangbing1, L., 2006. Fire prediction based on reverse sequence grey model. Paper presented at the 2006 International Symposium on Safety Science and Technology, Beijing.

Zulin, H., & Benlin, D., 2012. Water quality health assessment of offshore area in North Branch of the Yangtze River Estuary. Dyna. 79: 50-58.