Temporal Weather Prediction using Back Propagation based Genetic Algorithm Technique

Full Text (PDF, 436KB), PP.55-61

Views: 0 Downloads: 0


Shaminder Singh 1,* Jasmeen Gill 1

1. Punjab Technical University/Ph.D. Scholar, Kapurthala, 144601, Indian

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2014.12.08

Received: 17 Jan. 2014 / Revised: 10 May 2014 / Accepted: 24 Aug. 2014 / Published: 8 Nov. 2014

Index Terms

Temporal Weather Forecasting, Time Series Prediction, Artificial Neural Networks, Back Propagation Algorithm, Genetic Algorithms


Hybrid back propagation based genetic algorithm approach is a popular way to train neural networks for weather prediction. The major drawback of this method is that weather parameters were assumed to be independent of each other and their temporal relation with one another was not considered. So in the present research a modified time series based weather prediction model is proposed to eliminate the problems incurred in hybrid BP/GA technique. The results are very encouraging; the proposed temporal weather prediction model outperforms the previous models while performing for dynamic and chaotic weather conditions.

Cite This Paper

Shaminder Singh, Jasmeen Gill, "Temporal Weather Prediction using Back Propagation based Genetic Algorithm Technique", International Journal of Intelligent Systems and Applications(IJISA), vol.6, no.12, pp.55-61, 2014. DOI:10.5815/ijisa.2014.12.08


[1]A. Azadeh, S. F. Ghaderi, S. Tarverdian and F. Saberi “Integration of ANN and GA to predict electrical energy consumption” 32nd IEEE Conf. on Industrial Electron. Paris, France, vol. 7, pp. 2552-2557, 2006.

[2]R. J. Frank, N. Davey and S. P. Hunt, “Time series prediction and neural networks”, J. of Univ. of Hertfordshire, UK, vol. 31, pp. 91-103, 2008.

[3]J. Gill, B. Singh, S. Singh, “Training back propagation neural networks with genetic algorithm for weather forecasting”, 8th IEEE SISY, Serbia, pp. 465-469, 2010.

[4]J. Gill, S. Singh and P. Bhambri, “Artificial intelligent weather forecasting system: a case study”, PIMT J. of Research, vol. 6, pp. 70-77, 2013.

[5]S. Huawang and D. Yong, “Application of an improved genetic algorithms in artificial neural networks”, Int. Sym. on Inform. Process, Huangshan, China, pp. 263-266, 2009.

[6]I. Maqsood, M.R. Khan and A. Abraham, “Neuro-computing based canadian weather analysis”, 2nd Int. Workshop on Intell. Sys. Design and Applications, Atanta, Georgia, pp. 39–44, 2002.

[7]I. Maqsood, M.R. Khan and A. Abraham, “Weather forecasting models using ensembles of neural networks”, 3rd Int. Conf. on Intell. Sys. Design and Applications. Germany, pp. 33-42, 2003.

[8]Paras, S. Mathur, A. Kumar and M. Chandra, “A feature based neural network model for weather forecasting”, Journal of World Academy of Sciences, Engg. and Tech., vol. 34, pp. 66-73, 2007.

[9]E. A. Plummer, “Time series forecasting with feed-forward neural networks: guidelines and limitations”, Univ. of Wyoming, 2000.

[10]S. Rajasekaran and P. Vijayalakshmi, Neural Networks, Fuzzy Logic and Genetic Algorithms, Prentice Hall of India, New Delhi, 2004, pp. 253-265.

[11]P. K. Sarangi, N. Singh, R.K. Chauhan and R. Singh, “Short term load forecasting using artificial neural network: a comparison with genetic algorithm implementation”, J. of ARPN Engg. and App. Sci., vol. 4, pp. 88-93, 2009.

[12]S. Simmy, S. Yang and C. Ho, “Improving the back-propagation algorithm using evolutionary strategy”, IEEE Trans. on Circuits and Sys., vol. 5, 2007.

[13]S. Singh, P. Bhambri and J. Gill, “Time series based temperature prediction using back propagation with genetic algorithm technique”, Int. J. of Comp. Sci. Issues, vol. 8, pp. 28-32, 2011.

[14]M. Srinivas and L. M. Patnaik, “Genetic algorithms: a survey”, IEEE Trans. on Computation, vol. 27, pp. 17-26, 1994.

[15]L. Xiaofeng, “The establishment of forecasting model based on BP neural network of self-adjusted all parameters”, J. of Forecasting, vol. 20, pp. 69-71, 2001.