Application of Neural Network and Particle Swarm Optimization Algorithm in Slope Runoff and Sediment Yield Calculation

Abstract:

Neural network black box model for predicting the slope runoff and sediment yield and two empirical equations for calculating the slope runoff and sediment yield were established with the basis of practical field data of slope runoff and sediment amount by artificial simulated rainfall experiments. In additional, particle swarm optimization algorithm is used to inquire the empirical equation’s unknown parameters based on least square method. And results show that, neural network model might represent the nonlinear relationship between runoff, sediment amount and each impact factor excellently. Furthermore, predicted results are satisfactory and its relative error mean is around 10%. Empirical equations are reasonably and reliable, its relative error mean is less than 20%. These two methods provide an operable means for such intricate research of slope runoff and sediment yield predication and calculation.

• Periodical: Advanced Materials Research (Volumes 201-203)
• Pages: 2496-2503
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.201-203.2496
• Online since: February 2011
• Authors: Jun Huang, Pu Te Wu, Xi Ning Zhao, Juan Wang
• Keywords: Artificial Simulated Rainfall, Least-Square Method (LSM), Neural Network (NN), Runoff Amount, Sediment Amount

References

[1] Shumei Ren, Zhongyuan Zhu: Engineering Hydrology. China Agricultural University Press, Beijing 2000(In Chinese).

[2] Jiafu Liu, Zhanguo Jing, Wenfeng Zhan, et al. Research of Soil and Water Conservation. Vol. 17(2010), p.120～124(In Chinese).

[3] Renard K G, Fost G R, Weesies G A, et al. RUSLE-A Guide to Conservation Planning with the Revised Universal Soil Loss Equation. USDA Agricultural Handbook, No. 703, (1997).

[4] Misra R K, Rose C W. European Journal Soil Science. Vol. 10(1996), p.593～604.

[5] Flanagan D C, Nearing M S, Laflen J M. USDA-Water Erosion Prediction Project: Hillslope Profile and Watershed Model Documentation. USDA-ARS National Soil Erosion Research Laboratory, West Lafayette. NSER Report No. 10. (1995).

[6] Faqi Wu, Xiaoguang Zhao, Bingzheng Liu. Journal of Soil Erosion and Soil Water Conservation. Vol. 4(1998), p.72～76(In Chinese).

[7] Wude Yang, Zhaoqian Wang, Guoping Sui, et al. Journal of Soil Erosion and Soil Water Conservation. Vol. 5(1999), p.52～58(In Chinese).

[8] Zisheng Yang. Bulletin of water and soil loss. Vol, 9(1999), p.1～9(In Chinese).

[9] Zhongshan Jiang, Zhiqiang Wang, Zhi Liu. Journal of soil Erosion and Soil Conservation. Vol. 2(1996), p.1～9(In Chinese).

[10] Jinze Mou, Qingmei Meng. The research on Soil Loss Conservation Practice on Loess Plateau. Shannxi: Institute of Soil and Water Conservation, Chinese Academy of Science & MWR. 1981, p.251～255(In Chinese).

[11] Shouyu Chen. Implementation and Application of Artificial Neural Network Simulation. Wuhan: China University of Geosciences Press (2000), p.1～6(In Chinese).

[12] Liqun Han. Artificial Neural Network Tutorial. Beijing: Beijing University of Posts and Telecommunications Press (2006), p.49～50(In Chinese).

[13] Guodong Liu, Jing Ding. Journal of hydraulic engineering. (1999), p.65～70 (In Chinese).

[14] Xiaodong Duan, Cunrui Wang, Xiangdong Liu. 2007. Particle swarm optimization algorithm and its application. Shenyang: Liaoning University Press p.11(In Chinese).

[15] Xingqiong Wei, Yongquan Zhou. Computer Engineering Vol. 36(2010), p.189～191 (In Chinese).

[16] Feng Xu, Qiangguo Cai, Shu-an Wu. Geographical research Vol. 19(2000), p.303～310 (In Chinese).

[17] Shi Y, Eberhart R. International Conference on Evolutionary Computatiorr. Washington, USA: IEEE (1999), p.1945～(1950).