The BP Neural Network Model of Soil Water-Salt Dynamic State Analysis

Abstract:

With the survey data of Luohui Canal Irrigation District, Shaanxi, China as the example, we employed the three-layer feed forward BP network modeling method to study the soil water-salt dynamic state under the comprehensive conditions of the irrigation district, and adopted the Additional Momentum Method and Self-adaptive Learning-rate Adjustment Strategy to modify the back propagation algorithm; on this basis, we employed the default-factor testing method to analyze the sensitivity degrees of soil salt content and soil alkalinity to every factor in the input layer. The results show this model has a high accuracy and can characterize effectively the internal relationships between the change of farmland soil water-salt dynamic state at a shallow water table during crop growth period and its influential factors. Soil moisture content, groundwater salt content and groundwater evaporating capacity are main sensitive factors of soil water-salt dynamic state; the factors interact and affect each other, giving rise to a coupling relationship under complex conditions. Combining the above methods can provide a feasible and effective approach to study the law of soil water-salt dynamic state under a shallow water table during crop growth period, which is a supplement to and improvement in conventional research methods for soil water-salt dynamic state.

• Periodical: Advanced Materials Research (Volume 668)
• Pages: 928-932
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.668.928
• Online since: March 2013
• Authors: Yu Guo Qiang, Mao Sheng Zhang, Zhan Bin Li
• Keywords: Artificial Neural Network (ANN), Salt Dynamic, Sensitiveness Factors, Soils Salinity, Water Dynamic

References

[1] Pitman, M., Läuchli, A. Global impacts` of salinity and agricultural ecosystems. In: Läuchli, A., Lüttge, U. (Eds. ), Salinity: Environment–Plants–Molecules. Kluwer Academic Publishers, New York, p.3–20. (2002).

DOI: 10.1007/0-306-48155-3_1

[2] Qadir, M., Ghafoor, A., Murtaza, G. Amelioration strategies for saline soils. Land Degradation and Development Vol. 11 (2000), p.501–521.

DOI: 10.1002/1099-145x(200011/12)11:6<501::aid-ldr405>3.0.co;2-s

[3] Khan, S., Xevi, E., Meyer, W.S. Salt, water, and groundwater management models to determine sustainable cropping patterns in shallow saline groundwater regions of Australia. Journal of Crop ProductionVol. 7 (2003), 325–340.

DOI: 10.1300/j144v07n01_12

[4] Pang, X.P., Letey, J. Development and evaluation of ENVIRO-GRO, an integrated water, salinity, and nitrogen model. Soil Science Society of America Journal Vol. 62 (1998), p.1418–1427.

DOI: 10.2136/sssaj1998.03615995006200050039x

[5] Ragab, R., Malash, N., Abdel Gawad, G., Arslan, A., Ghaibeh, A. A holistic generic integrated approach for irrigation, crop and field management: 1. The SALTMED model and its calibration using field data from Egypt and Syria. Agricultural Water Management Vol. 78 (2005).

DOI: 10.1016/j.agwat.2005.04.022

[6] Erzin, Y., Rao, B.H., Singh, D.N. Artificial neural network models for predicting soil thermal resisitivity. International Journal of Thermal SciencesVol. 47 (2007), 1347–1358.

DOI: 10.1016/j.ijthermalsci.2007.11.001

[7] Jahangir, M., Jagath, J.K., Application of artificial neural network and genetic algorithm in flow and transport simulations. Advances in Water Resources Vol. 22 (1998), p.145–158.

DOI: 10.1016/s0309-1708(98)00002-5

[8] Baker, L., Ellison, D. Optimisation of pedotransfer functions using an artificialneural network ensemble method. Geoderma Vol. 144 (2008), p.212–224.

DOI: 10.1016/j.geoderma.2007.11.016

[9] Co, H.C., Boosarawongse, R. Forecasting Thailand's rice export: statistical tech-niques vs. artificial neural networks. Computers & Industrial Engineering Vol. 53 (2007), p.610–627.

DOI: 10.1016/j.cie.2007.06.005

[10] Wang W, Pieter H A J M Van Gelder, Vrijling J K, Jun Ma. Forecasting daily stream flow using hybrid ANN models. Journal of Hydrology Vol. 324 (2006), p.383–399.

DOI: 10.1016/j.jhydrol.2005.09.032

[11] Anctil F, Perrin C, Andreassian V. Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall–runoff forecasting models. Environment Modeling SoftwareVol. 19 (2004), p.357–368.

DOI: 10.1016/s1364-8152(03)00135-x