Affordable Access

Access to the full text

Monthly surface runoff prediction using artificial intelligence: A study from a tropical climate river basin

Authors
  • Reddy, Beeram Satya Narayana1
  • Pramada, S K1
  • Roshni, Thendiyath2
  • 1 National Institute of Technology Calicut, Kozhikode, Kerala, India , Kozhikode (India)
  • 2 National Institute of Technology Patna, Patna, Bihar, India , Patna (India)
Type
Published Article
Journal
Journal of Earth System Science
Publisher
Springer-Verlag
Publication Date
Feb 10, 2021
Volume
130
Issue
1
Identifiers
DOI: 10.1007/s12040-020-01508-8
Source
Springer Nature
Keywords
License
Yellow

Abstract

AbstractAccurate surface runoff prediction is vital for water resources engineers for various applications. Advances in the artificial intelligence techniques can act as robust tools for modelling hydrological processes. The present study focuses on testing the reliability of different data sources and choosing the correct source to model the rainfall-runoff process under data scarce situations using AI techniques. In this study, an absolute homogeneity test was performed for TRMM, gridded and observed precipitation data and found that the observed precipitation dataset is homogeneous and best suitable for modelling rainfall-runoff process in Kallada river basin, Kerala. Emotional artificial neural network (EANN) is a novel hybrid neural network and it is suggested in the present study for accurate monthly surface runoff prediction. This study was also conceived to address and investigate the efficiency of EANN for forecasting monthly surface runoff and compare the performances with conventional feed forward neural network (FFNN) and multivariate adaptive regression spline (MARS) models. Suitable goodness-of-fit criteria such as Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE) and coefficient of determination (R2) and graphical indicators are used for assessing the efficacy of the developed models. The results showed that the EANN model performs better with R2 = 0.80 for the training phase and R2 = 0.77 for validation phase compared to other models. The improvement in the performance of EANN model over FFNN model is 12% and 5.8% for coefficient of determination in the training and validation phase, respectively. Further, the Taylor diagram indicates that there is a close match between the observed and EANN model predicted values in terms of statistical parameters. Overall, this study demonstrated the effectiveness of EANN in modelling the rainfall-runoff process and also could be a useful technique in other fields of water resources engineering.HighlightsThe present study focuses on testing the reliability of different data sources such as gridded, observed and TRMM precipitation datasets and choosing the correct source to model the rainfall-runoff process using AI techniques.From the selected homogeneous dataset and the observed runoff data, potential predictors were identified based on correlation analysis and partial autocorrelation function (PACF).The monthly runoff prediction models were developed using three AI techniques namely FFNN, MARS and EANN in a tropical river basin (Kallada) of Kerala with scarce amount of data.The performance of the developed models were assessed using statistical indicators (NSE, RMSE, and R2) and graphical indicators (Taylor diagram, REC plots and Random walk test).

Report this publication

Statistics

Seen <100 times