Forecasting of runoff and sediment using neural network and multi regression in Aghajari Marls

Vatakhah, Mahadi; Saidian, Hamzeh

doi:10.22059/jrwm.2014.52840

Document Type : Research Paper

Authors

Mahadi Vatakhah ¹
Hamzeh Saidian ²

¹ Associate Professor, Department of Watershed Management, Faculty of Natural Resources, Tarbiat Modares University, Iran

² Former Ph.D. Student, Department of Watershed Management, Faculty of Natural Resources, Tarbiat Modares University, Iran

https://doi.org/10.22059/jrwm.2014.52840

Abstract

Erosion and sediment movement phenomena are one of the most complex issues in management of rivers drainage areas that in water projects are very important. That its measurement wants high time and cost. Issue of surface runoff in river basin is a complex issue that human knowledge and understanding about its physical laws a viewpoint of some mathematical formulas is limited. In this study to investigate modeling runoff and sediment production in different land uses of Aaghajari formation deposits, part of Margha watershed in Izeh city with area 1609 hectares was selected. In this study, some soil physical and chemical characteristics such as percentage of sand very fine, sand, clay, silt, pH, electrical conductivity, moisture, calcium carbonate and soil salinity in different land uses of Aghajari formation were used. Then the rain simulator in 7 point and with three replicated in different intensities 0.75, 1 and 1.25 mm in minute in three land use range, residential areas and agricultural lands, were used the amount of runoff and sediment. And the same of number were sampled in 0-20 cm in soil layer. In totally, 126 times sampling runoff and sediment were done. And 189 soil experiments were done. In order to perform all statistical analysis were used 11.5 SPSS and EXCEL and MATLAB 2008 software. The results showed that multi regression analysis in conditions with high input and little output data shows more favorable results than neural network. And in high intensities owing to data homogeny, neural network operation than to low precipitation intensities is better. But in multi regression in high and low precipitation intensities showed acceptable operation. The average of relative error in three land uses in sediment production in precipitation intensity 0.75 mm in minute were in multi regression 7.2 percent and root mean square error 0.06. And in neural network in same precipitation intensity the average of relative error 146/9 percent and root mean square error 0.41 were. The average of relative error in three land uses in sediment production in precipitation intensity 1 mm in minute were in multi regression 8.5 percent and root mean square error 0.19. And in neural network in same precipitation intensity the average of relative error 96.36 percent and root mean square error 0.85 were. The average of relative error in three land uses in sediment production in precipitation intensity 1.25 mm in minute were in multi regression 1.8 percent and root mean square error 0.38. And in neural network in same precipitation intensity were the average of relative error 37/6 percent and root mean square error 0.73.

Keywords

References

[1] Abrahart, R.J. and White, S.M. (2001). Modelling sediment transfer inMalawe: comparing backpropagation neural network solutionagainst a multiple linear regressionbenchmark using small datasets. Physics and Chemistry of the Earth, 26, 19-24.

[2] Alp, M and Kerem Cigizoglu, H. (2009). Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environmental Modelling and Software, 22, 2-13.

[3] ASCE (2000). Artificial neural networks in hydrology: 1. Preliminaryconcepts. Journal of Hydrologic Engineering, 5, 115-123.

[4] Asghari moghadam, A., Norani, V. and Nadiri, A. (2008): Modeling[p1] of Tabriz plain rainfall using neutral networks. Agriculture Science Journal, 18(1), 1-15. (In Persian).

[5] Barthes, B. and Roose, E. (2002).Aggregate Stability as an Indicator of Soil Susceptibility to Runoff and Erosion; Validation at Several Levels, Catena, 47, 133-149.

[6] Cannon, A.J. and Whitfied, P.H. (2002). Downscaling recent stream - flow conditions in British Columbia, Canada using ensemble neural network. Journal of Hydrology, 259, 136-151.

[7] Das, G. (2000). Hydrology and Soil Conservation Engineering. Asoke K. Ghosh, Prentic- Hall of India, 489P.

[8] Dawson, C.W. and Wilby, R.L. (2001). Hydrological modelling using artificial neural networks. Progress in Physical Geography, 25, 80-108.

[9] Gautam, M.R., Watanabe, K. and Saegusa, H. (2000). Runoff analysis in humid forest catchment with artificial neural network. Journal of Hydrology, 235, 117-136.

[10] Green, I.R.A. and Stephenson, D. (1986). Criteria for comparison of single event models. Hydrological Sciences Journal, 31, 395-411.

[11] Hossaini, S., Ci., Dehmardeh, A., Fathi, P.Ci. and Ceh Mardeh, M. (2007). Application of neutral networks and multi regression in estimation wheat operating in Kurdistan province Ghahve region. Agriculture Research Journal: Water, Soil, Vegetation in Agriculture, 1, 41-54.

[12] Jordan, A. and Martinez-Zavala, L. (2008). Soil Loss and Runoff Rates on Unpaved Forest Roads in Southern Spain after Simulated Rainfall, Journal of Forest Ecology and Management, 255, 913-919.

[13] Kamphorst, A. (1987). A small rainfall simulator for the determination of soil erodibility, Netherlands, Journal of Agricultural Science, 35, 407-415.

[14] Kinnell, P.I.A. (2005). Sediment Transport by Medium to Large Drops Impacting Flows at Subterminal Velocity, Soil Science Society of America Journal, 69(3), 902-905.

[15] Marcel, G.S., Feike, J.L., Martinus, T. and van Genuchten, H. (1998). Neural network analysis for hierarchical prediction of soil hydraulic properties, Soil Science Society, 62, 847-855.

[16] Menhaj, L.P. (1998). Bases of Neural Networks (Calculative Intelligence). First Volume. Amirkabir Univerity of Technology Press. 642P (In Persian).

[17] Navvabian, M., Liaghat, E.M. and Homaei, M. (2004). Rapid estimation of hydraulic conductivity using neural networks. In: Proceedings of the Second National Student Conference on Water and Soil Resource. Shiraz University Press, pp. 203 -211 (In Persian).

[18] Raisain, R. (2005). Investigation of erosion and sediment rates in Gargak catchment by using rain simulator, Soil Conservation and Watershed Management Research Institute, Project Research Plan Report, 156 P (In Persian).

[19] Rajurkar, M.P., Kothyarib, U.C. and Chaube, U.C. (2004). Modeling of the daily rainfall-runoff relationship with artificial neural network. Journal of Hydrology, 285, 96-113.

[20] Ramani, A. and Sedhi, M. (2004). Forecasting of water level changes of Bahar-Hamedan plain using times series. Water and Wastwater Journal, 15, 2-49. (In Persian).

[21] Reddy, S.B. (2003). Estimation of watershed runoff using artificial neural networks. Ph.D Thesis in Agriculture (unpubl.). Post Graduate School, IARI, New Dehli.

[22] Sarangi, A. and Bhattacharya, A.K. (2005). Comparison of artificial neural network and regression models for sediment loss prediction from Banha watershed in India. Agricultural Water Management, 78(3), 195-208.

[23] Sudheer, K.P., Gosain, A.K. and Ramasatri, K.S. (2002). A data-driven algorithm for constructing artificial neural network rainfall-runoff models. Hydrological Processes, 16, 1325-1330.

[24] Tamari, S., Wösten, J. H.M. and Ruiz-Suarez, J.C. (1996). Testing an artificial neural network for predicting soil hydraulic conductivity. Soil Science Society of America Journal, 60(6), 1732-1741.

[25] Vaezi, A.R., Sadeghi, S.H.R., Bahrami, H.A. and Mahdian, M.H. (2008). Modeling the USLE K-factor for calcareous soils in northwestern Iran. Geomorphology, 97(3), 414-423.

[26] Zarinkafsh, M. (1994). Application Pedology. University of Tehran Press, 236 P (In Persian).

[27] Zehtabian, Gh. (1999). Comparison of runoff and sediment rate in Lehbari marl formation using rain simulator in Gelalmoort subwatershes. University of Tehran Research Plan Report, 107P (In Persian).

[28] Zhang, B. and Govindaraju, R. (2003). Geomorphology-based artificial neural networks for estimation of direct runoff over watershed. Journal of Hydrology, 273, 18-34.

[29] Zhu, X.X. and Zhou, L.Y. (2007). Suspended sediment flux modeling with artificial neural network: Anexample of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology, 84, 111-125.

Journal of Range and Watershed Managment

Forecasting of runoff and sediment using neural network and multi regression in Aghajari Marls

References

References

Volume 67, Issue 3 - Serial Number 3
December 2014
Pages 487-499

Forecasting of runoff and sediment using neural network and multi regression in Aghajari Marls

References

References

Volume 67, Issue 3 - Serial Number 3December 2014Pages 487-499

Volume 67, Issue 3 - Serial Number 3
December 2014
Pages 487-499