Vol. 1 No. 6 (2019): Volume 1, Issue 6, year 2019

Forecasting Monthly Discharge Using Machine Learning Techniques

Bharthavarapu Srikanth
Research Scholar Civil Department Vel Tech Rangarajan Dr. sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, 600062, India.
Geetha Selvarani A.
Professor, Civil Department Vel Tech Rangarajan Dr.sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, 600062, India.
Bibhuti Bhusan Sahoo
Associate Professor Department of Civil Engineering MVR college of engineering & Technology, Paritala (V), Kanchikacherla (M), Krishna District, Andhra Pradesh, 521180, India.
Published November 2, 2019
  • MLP,
  • SVR,
  • Forecasting,
  • Time series
How to Cite
Srikanth, B., A., G. S., & Sahoo, B. B. (2019). Forecasting Monthly Discharge Using Machine Learning Techniques. International Research Journal of Multidisciplinary Technovation, 1(6), 1-6. Retrieved from https://mapletreejournals.com/index.php/irjmt/article/view/255


Discharge prediction methods play crucial role in providing early warnings and helping local people and government agencies to prepare well before flood or managing available water for various purposes. The ability to predict future river flows helps people anticipate and plan for upcoming flooding, preventing deaths and decreasing property destruction. Different hydrological models supporting these predictions have different characteristics, driven by available data and the research area. This study applied two different types of Machine learning techniques to the Tikarpara station present in the lower end of the Mahanadi river basin India. The two Machine learning techniques include Multi-layer perception (MLP) and support vector regression (SVR) MLP has shown great deal of accuracy as compared to SVR across the cases used in the study; based on available data and the study area, MLP showed the best applicability, compared to SVR techniques. MLP out performed SVR model with r2 = 0.75 and lowest RMSE = 0.58.MLP can be used as a promising tool for forecasting monthly discharge at the selected station.


Download data is not yet available.


[1] Marques C, Ferreira J, Rocha A, Castanheira J, 1. Marques C, Ferreira J, Rocha A, Castanheira J, Melo-Gonçalves P, Vaz N, Dias J (2006) Singular spectrum analysis and forecasting of hydrological time series. Physics and Chemistry of the Earth, Parts A/B/C 31 (18):1172-1179
[2] Carlson RF, MacCormick A, Watts DG (1970) Application of linear random models to four annual streamflow series. Water Resources Research 6 (4):1070-1078
[3] Box G, Jenkins G (1970) Time series analysis; forecasting and control. Holden-Day, San Francisco(CA).
[4] Vapnik V (1998) Statistical learning theory. 1998. Wiley, New York,
[5] Osuna E, Freund R, Girosi F (1997) Support vector machines: Training and applications.
[6] Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery 2 (2):121-167
[7] Deka PC (2014) Support vector machine applications in the field of hydrology: a review. Applied soft computing 19:372-386
[8] Pai P-F, Lin K-P, Lin C-S, Chang P-T (2010) Time series forecasting by a seasonal support vector regression model. Expert Systems with Applications 37 (6):4261-4265
[9] Sang Y-F, Wang D, Wu J-C, Zhu Q-P, Wang L (2009) The relation between periods’ identification and noises in hydrologic series data. Journal of Hydrology 368 (1):165-177
[10] Nayak PC, Sudheer K, Rangan D, Ramasastri K (2004) A neuro-fuzzy computing technique for modeling hydrological time series. Journal of Hydrology 291 (1):52-66
[11] Sudheer K, Gosain A, Ramasastri K (2002) A data‐driven algorithm for constructing artificial neural network rainfall‐runoff models. Hydrological processes 16 (6):1325-1330
[12] Cheng C-T, Lin J-Y, Sun Y-G, Chau K (2005) Long-term prediction of discharges in Manwan Hydropower using adaptive-network-based fuzzy inference systems models. Advances in natural computation:434-434