Rainfall Prediction Using Time Series Nonlinear Autoregressive Neural Network

International Journal of Computer Science and Engineering

© 2021 by SSRG - IJCSE Journal

Volume 8 Issue 1

Year of Publication : 2021

Authors : Urooj Kaimkhani, Bushra Naz, Sanam Narejo

10.14445/23488387/IJCSE-V8I1P106

How to Cite?

Urooj Kaimkhani, Bushra Naz, Sanam Narejo, "Rainfall Prediction Using Time Series Nonlinear Autoregressive Neural Network," SSRG International Journal of Computer Science and Engineering , vol. 8,  no. 1, pp. 30-38, 2021. Crossref, https://doi.org/10.14445/23488387/IJCSE-V8I1P106

Abstract:

Weather forecasting is important for the daily life plan of the person, but the agriculture sector is also dependent on the weather condition and several industries. This research work reflects the prediction of the metrological parameter in the time series, i.e., prediction of Rainfall by using ANN (Artificial Neural Network) based model NARX (Nonlinear Autoregressive with exogenous input). In this research paper, more than a few ANN models that rely on real-time sequence recurring NARX-based ANN techniques are initiated, trained, and tested with different parameter settings to find the network model's best possible output to its most-wanted prediction function. The model network's performance is evaluated on the basis of the Mean Squared Error (MSE) performance of the model when the data sets are trained, validated, and tested. Although one step ahead of prediction, multi-phase ahead prediction is more complicated and difficult to carry out because of its underlying added complication. Therefore, the findings found in this work provide useful and helpful suggestions for the NARX-ANN model parameters, particularly the choice of hidden layer size and self-regressive leg terms for an efficient predictor of multi-step time series. This study aims to build and train a network that can predict and predict the weather portion of precipitation by optimizing the parameters of the neural network.

Keywords:

Artificial Neural network (ANN), NARX model, Outlier recognition, Time Series forecasting, Rainfall prediction.

References:

[1] G.E. Box, G.M. Jenkins, G.C. Reinsel, and G.M. Ljung, " Time series analysis: forecasting and control. "Holden-Day, 1976.
[2] G.P. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model.", Neuro-computing, vol. 50, pp. 159175, 2003.
[3] C. Brooks, "Univariatetime series modelling and forecasting.", Introductory Econometrics for Finance. 2nd Ed. Cambridge University Press. Cambridge, Massachusetts, 2008.
[4] J.H. Cochrane, Time series for macroeconomics and finance. Manuscript, University of Chicago, 2005.
[5] K.W. Hipel, and A.I. McLeod, Time series modelling of water resources and environmental systems, Elsevier. vol. 45, 1994.
[6] Taieb, Souhaib Ben, Gianluca Bontempi, Amir F. Atiya, and Antti Sorjamaa. "A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition." Expert systems with applications 39, no. 8 (2012): 7067-7083.
[7] De Gooijer, Jan G., and Rob J. Hyndman. "25 years of time series forecasting." International journal of forecasting 22, no. 3 (2006): 443-473.
[8] Xiu, Yan, and Wei Zhang. "Multivariate Chaotic Time Series Prediction Based on NARX Neural Networks." In 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017). Atlantis Press, 2017.
[9] Holmstrom, Mark, Dylan Liu, and Christopher Vo. "Machine learning applied to weather forecasting." (2016).
[10] Liu, James NK, Bavy NL Li, and Tharam S. Dillon. "An improved naive Bayesian classifier technique coupled with a novel input solution method [rainfall prediction]." IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 31, no. 2 (2001): 249-256.
[11] Cao, Qing, Bradley T. Ewing, and Mark A. Thompson. "Forecasting wind speed with recurrent neural networks." European Journal of Operational Research 221, no. 1 (2012): 148-154.
[12] Ahmed Tealab a,*, Hesham Hefny a, Amr Badr b a Computer Science Department, Institute of Statistical Studies and Research, Cairo University, Giza, Egypt b Computer Science Department, Faculty of Computers and Information, Cairo University, Giza, Egypt Received 19 March 2017; accepted 14 May 2017 Available online 3 July 2017
[13] Taksande, Amruta A., and P. S. Mohod. "Applications of data mining in weather forecasting using frequent pattern growth algorithm." International Journal of Science and Research (2015).
[14] Narejo, Sanam, and Eros Pasero. "Meteonowcasting using deep learning architecture." (IJACSA) International Journal of Advanced Computer Science and Applications 8, no. 8 (2017).
[15] Math Works. Matlab R2016a Neural Network Toolbox user Guide. 2016
[16] Narasayya.Kamuju,Rainfall-Runoff Estimation and Comparative Analysis Using Advanced Geospatial Digital Hydrological Modelling Tools, ArcCN-Runoff & ArcSWAT., SSRG International Journal of Geoinformatics and Geological Science 2(3)(2015) 5-10.
[17] Bishwajit Roy, Maheshwari Prasad Singh. An Empirical-based rainfall-runoff modeling using optimization Technique. International Journal of River Basin Management 0:0, pages 1-19, 2019.
[18] Yaseen, Z.M.; Ebtehaj, I.; Kim, S.; Sanikhani, H.; Asadi, H.; Ghareb, M.I.; Bonakdari, H.; Wan Mohtar, W.H.M.; AlAnsari, N.; Shahid, S. Novel Hybrid Data Intelligence Model for Forecasting Monthly Rainfall with Uncertainty Analysis. Water 2019, 11, 502.
[19] Le TT., Pham B.T., Ly HB., Shirzadi A., Le L.M. (2020) Development of 48-hour Precipitation Forecasting Model using Nonlinear Autoregressive Neural Network. In: Ha-Minh C., Dao D., Benboudjema F., Derrible S., Huynh D., Tang A. (eds) CIGOS 2019, Innovation for Sustainable Infrastructure. Lecture Notes in Civil Engineering, vol 54. Springer, Singapore
[20] Esteves, João Trevizoli, Glauco de Souza Rolim, and Antonio Sergio Ferraudo. "Rainfall prediction methodology with binary multilayer perceptron neural networks." Climate Dynamics 52.3-4 (2019): 2319-2331.
[21] Arabeyyat, Omar, Nawras Shatnawi, and Mohammed Matouq. "Nonlinear Multivariate Rainfall Prediction in Jordan Using NARX-ANN Model with GIS Techniques." Jordan Journal of Civil Engineering 12.3 (2018).
[22] Geetali Saha Narendra Chauhan , C. "Analysis methods for numerical weather prediction." Quarterly Journal of the Royal Meteorological Society 112.474 (1986): “ (2017)
[23] Cao, Qing, Bradley T. Ewing, and Mark A. Thompson. "Forecasting wind speed with recurrent neural networks." European Journal of Operational Research 221.1 (2012): 148-154.“Forecasting wind speed with recurrent neural networks”, Qing Cao a , Bradley T. Ewing a,b , Mark A. Thompson a,b, 2012.
[24] Mark Holmstrom, Dylan Liu, Christopher Vo, internal report from Stanford University, “Weather forecasting”, (December 15, 2016),
[25] James N.K.Liu, Bavy N.L.Li, and Tharam S.Dillon, “Weather forecasting and prediction”, ( May 2001)
[26] Amruta A. Taksande, P. S. Mohod. An internal Report, “Rainfall prediction”, 2003.
[27] Darji, M. P., V. K. Dabhi, and H. B. Prajapati. &quot, “Rainfall forecasting using neural network” A survey." In Computer Engineering and Applications (ICACEA), , pp. 706-713, 2015.
[28] Hossain, Moinul, et al. "Forecasting the weather of Nevada: A deep learning approach." 2015 international joint conference on neural networks (IJCNN). IEEE, 2015
[29] Hernández, Emilcy, et al. "Rainfall prediction: A deep learning approach, "International Conference on Hybrid Artificial Intelligence Systems. Springer, Cham, 2016.