Noise injection – denoising techniques to improve artificial intelligence -based rainfall – runoff modeling

Document Type : Research Paper

Authors

• Afshin Partovyan ¹
• Vahid Nourani ²
• Mohammad taghi ALAMI ³

¹ Ph.D.Student Department of Civil Engineering , Faculty of Civil Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Isfahan, Iran.

² Professor, Faculty of Civil Engineering, University of Tabriz- گروه عمران آّب، دانشکده عمران، واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران

³ Professor, Department of Water Resources Engineering, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran.

Abstract

Accurate modeling of hydrological processes such as rainfall-runoff can provide important information for water resources management of a watershed. Consequently, various black box models have been used recently to simulate such a complex phenomenon. Efficiency of any data driven model largely depends on quantity and quality of available data and noisy data may create negative impact on the performance of the model. In this way, noise reduction of data using an appropriate denoising scheme may lead to a better performance in the use of the data-driven model. Therefore in this paper, first wavelet-denoising method was applied to denoise daily time series and then by adding noises to this denoised data and forming different training sets with the denoised- jittered input data, simulation of rainfall – runoff process for Pole Anyan station in Zarrineh River drainage basin in upstream of Bookan dam, was done by both ANN and ANFIS models. To evaluate the model accuracy, the proposed model was compared with MLR and ARIMA models.
Comparison of the obtained results via the trained ANN and ANFIS using denoised-jittered data revealed that the outcome of the this model for runoff forecasting is improved when the proposed approach, as a pre-processing method, is applied to the used data. The results show that the proposed data processing which serves both denoising and jittering approaches could improve performance of the ANN and ANFIS-based rainfall-runoff modeling of the case study respectively up to 23% and 14% in verification phase.

Keywords

• Rainfall-Runoff modeling
• Black box models
• Wavelet Denoising
• Noise injection
• Zarrineh river watershed

20.1001.1.20086377.1397.11.36.8.9

---

References

حقی زاده، ع؛ محمدلو، م؛ نوری، ف. 1394 . شبیه
سازی فرایند بارش رواناب با استفاده از شبکۀ عصبی
مصنوعی و سیستم فازی عصبی تطبیقی و رگرسیون
چندمتغیره(مطالعه موردی: حوضۀ آبخیز خرم آباد).
.233-243 : اکوهیدرولوژی 2
. 2) قربان زاده، م؛ ملای نیا، م.ر؛ قره سوفلو، ج. 1394
ارزیابی شبکه عصبی مصنوعی در برآورد بارش رواناب
(مطالعه موردی رودخانه کرج). کنفرانس ملی مهندسی
معماری. عمران و توسعه شهری. 10 صفحه.
3) لیبرمن ،ج و باوکر، آ.ه. 1388 .آمار مهندسی. مرکز
نشر دانشگاهی. 608 صفحه.
4) نورانی، و؛ و صالحی، ک. 1387 . مدل سازی بارش-
رواناب با استفاده از روش شبکه عصبی فازی تطبیقی و
مقایسه آن با روش های شبکه عصبی و استنتاج فازی.
چهارمین کنگره ملی مهندسی عمران . دانشگاه تهران. 8
صفحه.
5) نورا نی، و؛کی نژاد، م.ع؛ ملکا نی، ل. 1388 . استفاده
از سیستم فازی - عصبی تطبیقی در مدل سازی بارش -
رواناب. نشریه مهندسی عمران و محیط زیست دانشگاه
6 صفحه. . تبریز.شماره 4
6) Abrahart, R.J., F. Anctil, P. Coulibaly, C.W.
Dawson, N.J. Mount, L.M. See, A.Y. Shamseldin,
D.P. Solomatine, E. Toth, and R.L. Wilby.2012.
Two decades of anarchy? Emerging themes and
outstanding challenges for neural network river
forecasting. Progress in Physical Geography 36:
480-513.
7) An, G. 1996. The effect of adding noise during
back propagation training on a generalization
performance. Neural Computation 8: 643–674.
8) Antar, M.A., I. Elassiouti and M.N. Alam.
2006. Rainfall–runoff modeling using artificial
neural networks technique: a Blue Nile catchment
case study. Hydrological Process 20 (5): 1201–
1216.
9) Aqil, M., I. Kita, A. Yano, and S. Nishiyama.
2007. A comparative study of artificial neural
networks and neuro-fuzzy in continuous modeling
of the daily and hourly behaviour of runoff. Journal
of Hydrology 337:22–34.
10) ASCE Task Committee on Application of
Artificial Neural Networks in Hydrology. 2000.
Artificial Neural Networks in hydrology ΙΙ:
Hydrologic Applications. Journal of Hydrologic
Engineering. 386:27-37.
11) Box, G.E.P., and G. Jenkins. 1976. Time
Series Analysis: Forecasting and control, seconded.
Holden-Day, San Francisco.
12) Donoho, D.H.1995.De-noising by softthresholding.
IEEE Transactions on Information
Theory 41(3):613-617.
13) Elshorbagy, A., S.P. Simonovic, and U.S.
Panu. 2002. Noise reduction in chaotic hydrologic
time series: facts and doubts. Journal of Hydrolog
256:147-165.
14) Firat, M., and M. Gungor. 2006. River flow
estimation using Adaptive Neuro Fuzzy Inference
System. Mathematics and Computers in Simulation
11:52-62.
15) Nejad, F., and V. Nourani.2012. Elevation of
wavelet denoising performance via an ANNBased
streamflow forecasting model. International
Journal of Computer Science and Management
Research 1:764-770.
16) Nourani, V., O. Kisi and M. Komasi. 2011.
Two hybrid artificial intelligence approaches for
modeling rainfall-runoff process. Journal of
Hydrology 402:41-59.
17) Rajurkar, M.P., U.C. Kothyari, and U.C.
Chaube.2002.Artificial neural networks for daily
rainfall-runoff modeling. Hydrological Sciences
Journal 47(6): 865-877.
18) Reed, R., R.J. Marks II, and S.Oh.1995
.Similarities of error regularization, sigmoid gain
scaling, target smoothing, and training with jitter.
94 بهبود عملکرد نرم افزارهای هوش مصنوعی در شبیه سازی بارش- رواناب با استفاده از روش حذف - تزریق نوفه
IEEE Transaction on Neural Networks 6 (3): 529–
538.
19) Salas, J.D., J.W. Delleur, V. Yevjevich, and
W.L. Lane. 1980. Applied modeling of
hydrological time series. Water Resources
Publications. Denever.
20) Sang, Y.F. 2012. A practical guide to discrete
wavelet decomposition of hydrologic time series.
Water Resources Management 26: 3345-3365.
21) Zhang, G.P. 2007.A neural network ensemble
method with jittered training data for time series
forecasting. Information Sciences 177:5329–5346