Estimation of Prediction Intervals for ANN- Based Rainfall- Runoff Modeling

Authors

Faculty of Civil Engineering, University of Tabriz, Iran

Abstract

     In this study, Lower Upper Bound Estimation (LUBE) method, which was firstly introduced by Khosravi et al. (2010) and is a novel PIs construction method in hydrologic issues, is applied to construct PIs for ANN-based rainfall-runoff modeling. This technique is independent of any knowledge about the bounds of PIs or data distribution. The ANN-based LUBE method includes two outputs showing upper and lower bounds of prediction in contrast to the classic ANNs, which consider one output as point prediction. In this way, dominant input data combination is selected by the mutual information (MI) to the model rainfall-runoff process in both monthly and daily scales for two different watersheds in Iran and USA. Finally, the obtained PIs by the proposed LUBE method are compared with those obtained by the classic Bootstrap method.
.

Keywords

Main Subjects

References

رجایی ط، زینی­وند ا، "مدل‌سازی تراز آب زیرزمینی با بهره‌گیری از مدل هیبرید موجک- شبکه عصبی مصنوعی (مطالعه موردی: دشت شریف‌آباد)"، نشریه مهندسی عمران و محیط زیست دانشگاه تبریز، 1393، 44 (4)، 51-63.
ندیری ع، واحدی ف، اصغری ­مقدم ا، کدخدایی ع، "استفاده از مدل هوش مصنوعی مرکب نظارت شده برای پیش‌بینی سطح آب زیرزمینی"، نشریه مهندسی عمران و محیط زیست دانشگاه تبریز، 1395، 46 (3)، 101-112.
Chryssolouris G, Lee M, Ramsey A, “Confidence interval prediction for neural network models”, IEEE Transactions on Neural Networks, 1996, 7 (1), 229-232.
Dhanesh Y, Sudheer KP, “Predictions in ungauged basins: can we use artificial neural networks”, American Geophysical Union Joint Assembly, Foz Doiguassu, Brazil, 2010, August 8-13.
Efron B, Tibshirani RJ, “An introduction to the bootstrap”, CRC press, 1994.
Gao Z, Gu B, Lin J, “Monomodal image registration using mutual information based methods”, Image and Vision Computing”, 2008, 26 (2), 164-173.
Grant El, Leavenworth RS, “Statistical quality and control New York”, McGraw-Hill, 1972, 643.
Hagan MT, Menhaj MB, “Training feedforward networks with the Marquardt algorithm”, IEEE Transactions on Neural Networks, 1994, 5 (6), 989-993.
Imrie CE, Durucan S, Korre A, “River flow prediction using artificial neural networks: generalisation beyond the calibration range”, Journal of Hydrology, 2000, 233 (1-4), 138-153.
Kasiviswanathan KS, Sudheer KP, “Quantification of the predictive uncertainty of artificial neural network based river flow forecast models”, Stochastic Environmental Research and Risk Assessment, 2013, 27 (1), 137-146.
Kasiviswanathan KS, Sudheer KP, “Comparison of methods used for quantifying prediction interval in artificial neural network hydrologic models”, Modeling Earth Systems and Environment, 2016, 2 (1), 2-22.
Kumar S, Tiwari MK, Chatterjee C, Mishra A, “Reservoir inflow forecasting using ensemble models based on neural networks, wavelet analysis and bootstrap method”, Water Resources Management, 2015, 29 (13), 4863-4883.
Khosravi A, Nahavandi S, Creighton D, “A prediction interval-based approach to determine optimal structures of neural network metamodels”, Expert Systems with Applications, 2010, 37 (3), 2377-2387.
Khosravi A, Nahavandi S, Creighton D, Atiya AF, “Lower upper bound estimation method for construction of neural network-based prediction intervals”, IEEE Transactions on Neural Networks, 2011 ,22 (3), 337-46.
MacKay DJC, “A practical Bayesian framework for backpropagation networks”, Neural Computation, 1992, 4 (3), 448-472.
Nourani V, Kisi Ö, Komasi M, “Two hybrid artificial intelligence approaches for modeling rainfall-runoff process”, Journal of Hydrology, 2011, 402 (1-2), 41-59.
Nourani V, Khanghah TR, Baghanam AH, “Application of Entropy Concept for Input Selection of Wavelet-ANN Based Rainfall-Runoff Modeling”, Journal of Environmental Informatics, 2015, 26 (1).
Nourani V, Paknezhad NJ, Sharghi E, Khosravi A, “Estimation of prediction interval in ANN-based multi-GCMs downscaling of hydro- climatologic parameters”, Journal of Hydrology, 2019, 579, 124226.
Quan H, Srinivasan D, Khosravi A, “Particle swarm optimization for construction of neural network-based prediction intervals”, Neurocomputing, 2014, 127, 172-180.
Riad S, Mania J, Bouchaou L, Najjar Y, “Predicting catchment flow in a semiarid region via an artificial neural network technique”, Hydrological Processes,  2004, 18 (13), 2387-2393.
Shannon CE, “A mathematical theory of communication”, Bell System Technical Journal, 1948, 27 (3), 379-423.
Sharghi E, Nourani V, Najafi H, Gokcekus H, “Conjunction of a newly proposed emotional ANN (EANN) and wavelet transform for suspended sediment load modeling”, Water Supply, 2019, 19 (6), 1726-34.
Srivastav RK, Sudheer KP and Chaubey I, “A simplified approach to quantifying predictive and parametric uncertainty in artificial neural network hydrologic models”, Water Resources Research, 2007, 43 (10).
Sudheer KP, Gosain AK, Ramasastri KS, “A data‐driven algorithm for constructing artificial neural network rainfall‐runoff models”, Hydrological Processes, 2002, 16 (6), 1325-1330.
Tiwari MK, Chatterjee C, “Uncertainty assessment and ensemble flood forecasting using bootstrap based artificial neural networks (BANNs)”, Journal of Hydrology, 2010, 382 (1-4), 20-33.
Taormina R, Chau KW, “ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS”, Engineering Applications of Artificial Intelligence, 2015, 45, 429-40.
Yang HH, Van Vuuren S, Sharma S, Hermansky H, “Relevance of time- frequency features for phonetic and speaker-channel classification. Speech communication”, 2000, 31 (1), 35-50.
Zio E, “A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes”, IEEE Transactions on Nuclear Science, 2006, 53 (3),1460-1478
Journal of Civil and Environmental Engineering
Volume 51.4, Issue 105 - Serial Number 105
Winter 2022
January 2022
Pages 57-67

Files

Share

How to cite

Statistics