Application of Artificial Neural Network (ANN) Model for Estimation of Runoff Yield at Kalidevi Watershed of Dhar District in Madhya Pradesh
51 / 31
Keywords:
Artificial neural network(ANN), Antecedent precipitation index(API), Levenverg- Marquardt (LM) algorithm, Minmax, Standard deviation,Back propagation (BP)Abstract
The runoff at any point is a complex function of watershed characteristics and hydrological parameters in space and time. Accurate estimation of runoff yield is required for proper watershed management and other developmental work in the watershed area. The study was conducted in Kalidevi watershed of Dhar District in Madhya Pradesh. Artificial neural network (ANN) model was used and most preferred which is developed for the estimation of runoff with input parameters. The Daily rainfall, average temperature, API (Antecedent precipitation index) and the days were taken as input variables for the study period (year 2003 to 2005) during the rainy seasons and the same were used for the analysis and application of ANN model for estimation of runoff yield for the watershed area. The ANN model for runoff had correlation coefficient of 0.973 and found superior over other tested.
Downloads
References
AICRP (2006). Land Use Planning and Management of Natural Resources of Dhar District
through Remote Sensing. An Annual Report of AICRP project College of Agriculture Indore
MP-submitted to ISRO Bangalore.
Coulibaly P, Anctil F and Bobee B (2000) Previous hydrologique par researc de neurones artifacts:
et at de l'art. Reveue Canadienne de genie Civil 26(3): 293-304.
Das G (2000) Hydrology and Soil Conservation Engineering. Prentice Hall of India
Pvt ltd New Delhi , p 265
Harun S, Nor NIH and Kassim AHM (2002) Artificial neural network models for rainfall-runoff
relationship. Jurnal Teknologi 37(B):1-12.
Haykin S (1994) Neural Networks A Comprehensive Foundation. IEEE Press.
Haykin S (1999) Neural Networks Prentice Hall, NJ, 2nd edn.
Hsu K, Gupta HV and Sooroochian S (1997) Application of recurrent neural network to rainfall
runoff modeling . Proc. Aesthetics in the Constructed Envirenment, ASCE, New York ,
pp 68-73.
Leonard JA, Kramer MA and Ungar LH (1990) Using radial basis functions to approximate a
function and its error bounds. IEEE Transactions on Neural Networks 3(4): 624-627.
Sarangi A, Madramootoo CA, Enright P, Prasher SO and Patel RM (2005) Performance evaluation
of ANN and geomorphology based models for runoff and sediment yield prediction for a
Canadian watershed. Current Science 89: 2022-2033.
Sarkar A, Agarwal A and Singh RD (2006). Artificial neural network models for rainfall -runoff
forecasting in hilly catchment. J. of Ind. Water Resources Society 26(3-4):5-12.
Singh A (1987) Studies on some aspect of soil and water in relation to resources management in
northeastern hill region. PhD thesis , Deptt of Agricultural Engineering , Faculty of
Agriculture BCKVV, W.B.
Sudheer KP, Gosain AK and Ramasastri KS (2000) A data -driven algorithm for constructing
artificial neural network rainfall -runoff models. Hydrol. Processes 16: 1325-1330.
Verma SK, Singh J, Tiwari SC and Ranade DH (2006) Runoff estimation by using remote sensing
and GIS from watershed. J. Soil Water Conservation 5(3):49-53.
Zong L, She W, Guo ZL and Shen W (2000) Runoff analysis in humid forest catchments with
artificial neural network: Journal of Zhejiang University of Agriculture and Life Sciences
(4): 361-364.
Downloads
Submitted
Published
Issue
Section
License
Journal of Soil Salinity and Water Quality serves as an official organ of the Indian Society of Soil Salinity and Water Quality (ISSSWQ) for the publication of research papers, reviews, and short communications as per the constitution and by-laws of the society. Soft and hard copy of the journal are sent free to all its members. All disputes are subject to the exclusive jurisdiction of competent court and forums in Kamal only. The society does not assume any responsibility for opinion by the authors in the articles and no-material in any form can be reproduced without the prior permission of the society. The society is not responsible for any delay, whatsoever, in publication/ delivery of the periodicals to the subscribers due to unforeseen circumstances or postal delay. The society does not vouch for any claims made by the advertisers of products and services. The publisher and the editors shall not be held liable for any consequences in the event of such claim not being honoured by the advertisers.