Application of RBF Networks in Mercury Pollution Spatial Prediction of a Gold Mine Area

Abstract:

This paper adopts the Radial Basis Function (RBF) Neural Networks to conduct a spatial prediction on the mercury pollution situation of the Jiapigou gold mine area, locate the primary pollution sources, delineate the pollution area according to the mercury concentration data of 27 soil samples from this area, and draws the mercury concentration isoline with the gridded data. Compared with the methods in the past such as classical statistics and BP Neural Networks to analyse the soil pollution, this method presents advantages such as the quantification of the result, the explicitness of the pollution area, and the ability to explain the blind area of the samples.

• Periodical: Advanced Materials Research (Volumes 926-930)
• Pages: 2771-2776
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.926-930.2771
• Online since: May 2014
• Authors: Hao Chen Wang, Jing Yang, He Ping Lin*
• Keywords: Artificial Neural Network (ANN), Environment Monitoring, Radial Basis Function (RBF), Spatial Prediction, Statistical Learning

References

[1] Lu Weiping. Geology of Gold Ore In Jiapigou Valley And Brief History of Its Mining Technology[J]. Journal of Anshan University of Science and Technology, 2004, 04: 298-305.

[2] Liu Xuejiao. The Spatial Distribution of Mercury And Methymercury And Mercury's ERA In Soil of The Region of Jiapigou Gold Mine[D]. Northeast Normal University, (2011).

[3] Zhou Lei, Qi Yanbing, Chang Qingrui, Yang Fengqun. Comparison of Spatial Interpolation Methods of Available Potassium In Hantai County[J]. Journal of Northwest A & F University(Natural Science Edition), 2012, 08: 193-199.

[4] Li Yafen, Wang Jing, Wang Ning. Distribution Characteristics And Risk Assessment of Mercury Poluution In The River Water And Sediment of The Songhua River Upstream Gold Mining Area[J]. Journal of Agro-Environment Science, 2013, 03: 622-628.

[5] Yang Jing, Wang Ning. Assessment of Potential Ecological Risk of Heavy Metals in Soils From Jia-Pi-Gou Gold Mine Area, China[J]. Journal of Agro-Environment Science, 2013, 03: 595-600.

[6] Zou Tingting. Huadian City, Gold Mining Areas of The Temporal And Spatial Distribution of Mercury And Ecological Risk Assessment[D]. Northeast Normal University, (2009).

[7] Guo Qingchun, He Zhenfang, Li Li, Li Haining. Application of BP Neural Network Model For Prediction of Water Pollutants Concentration In Taihu Lake[J]. Journal of Southern Agriculture, 2011, 10: 1303-1306.

[8] Wang Linlin. Application of Back-propagation Artificial Neural Network In Speciation of Plumbum And Cadmium In City Soil[D]. Jilin University, (2009).

[9] Yang Juan, Wang Changjin, Li Bing, Li Huanxiu, He Xin. Prediction of Soil Heavy Metal Pollution of Peri-urban Zone Based On BP Artificial Neural Network- A Case Study Of The Chengdu Plain[J]. Acta Pedologica Sinica, 2007, 03: 430-436.

[10] Zhou Mei, Li Zheng, Ling Haibo, Wang Kan, Cai Junxiong. Research On Water Quality Evaluation In Yishui River Based On BP Neutral Networks[J]. Environmental Science & Technology, 2012, S1: 385-388+435.

[11] Ai Na, Wu Zuowei, Ren Jianghua. Support Vector Machine And Artificial Neural Network[J]. Journal of Shandong University of Technology(Natural Science Edition), 2005, 05: 48-52.

[12] Lowe D, Broomhead D. Multivariable functional interpolation and adaptive networks[J]. Complex systems, 1988, 2: 321-355.

[13] Karayiannis N B, Mi G W. Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques[J]. Neural Networks, IEEE Transactions on, 1997, 8(6): 1492-1506.

DOI: 10.1109/72.641471

[14] Chen Tingyong, Yin Shuyou, Lin Heping. RBF Artificial Neural Network Topology Definition And Proof of Uniqueness of Solution[J]. Journal of Northeast Normal University(Natural Science Edition), 2009, 03: 30-35.