Advertisement

Rainfall Prediction Using Fuzzy Neural Network with Genetically Enhanced Weight Initialization

  • V. S. Felix EnigoEmail author
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 35)

Abstract

In this paper, a hybrid approach of combining the techniques of artificial neural network along with fuzzy logic and genetic algorithm is used in prediction of rainfall classes. We have used genetic approach for initialization of weights in contrast to fixed weights or random weights for initialization of fuzzy neural networks. Fixed weights tend to get struck at local optimum by biasing the solution to a particular set of weights. Random initialization of weights increases the probability of obtaining global optimum solution in comparison to fixed weight approach. Our proposed genetic approach of weight initialization, rather than providing random weights, finds the optimal weights through genetic evolution for initialization of the fuzzy neural network. The proposed approach has been analyzed for rainfall classification system which predicts the class of one day ahead rainfall based on its intensity. By incorporating genetic evolved weights for fuzzy neural network, we were able to achieve a better accuracy than random weight approach.

Keywords

Neural network Fuzzy logic Genetic algorithm 

Notes

Acknowledgements

The Meteorological data used in this study were obtained from Boundary Layer Meteorological Tower at Kalpakkam site operated and maintained by Radiological Safety Division, Indira Gandhi Centre for Atomic Research (IGCAR), India.

References

  1. 1.
    Bodri, L., Cermak, V.: Prediction of extreme precipitation using a neural network: application to summer flood occurrence in Moravia. Adv. Eng. Softw. 31(5), 311–321 (2000)CrossRefGoogle Scholar
  2. 2.
    Kumarasiri, A.D., Sonnadara, U.J.: Performance of an artificial neural network on forecasting the daily occurrence and annual depth of rainfall at a tropical site. Hydrol. Process. 22(17), 3535–3542 (2008)CrossRefGoogle Scholar
  3. 3.
    Sahai, A.K., Soman, M.K., Satyan, V.: All India summer monsoon rainfall prediction using an artificial neural network. Clim. Dyn. 16(4), 291–302 (2000)CrossRefGoogle Scholar
  4. 4.
    Fonte, P.M., Quadrado, J.C.: ANN approach to WECS power forecast. In: 10th IEEE International Conference on Emerging Technologies and Factory Automation, pp. 19–22 (2005)Google Scholar
  5. 5.
    Rohrig, K., Range, B.: IEEE Power Engineering Society General Meeting, pp. 18–22 (2006)Google Scholar
  6. 6.
    Aisjah, A.S., Arifin, S.: Maritime weather prediction using fuzzy logic. In: 2nd International Conference on Instrumentation Control and Automation, Bandung, Indonesia, pp. 15–17 (2011)Google Scholar
  7. 7.
    Shah, H., Jaafar, J., Rosdiazli, I., Saima, H., Maymunah, H.: A hybrid system using possibilistic fuzzy C-mean and interval type-2 fuzzy logic for forecasting: a review. In: International Conference on Computer & Information Science, pp. 532–537 (2012)Google Scholar
  8. 8.
    Annas, S., Kania, T., Koyama, S.: Neuro-fuzzy approaches for modeling the wet season tropical rainfall. Agric. Inf. Res. 15(3), 331–341 (2006)Google Scholar
  9. 9.
    Fhira, N., Asiwijaya: A rainfall forecasting using fuzzy system based on genetic algorithm. In: International Conference of Information and Communication Technology (2013)Google Scholar
  10. 10.
    Bagavathsingh, A., Baskaran, R., Venkatraman, B.: Installation and Commissioning of 50m Meteorological Tower at Ediyur Site, IGCAR, Kalpakkam, IGC/SG/RSD/RIAS/92617/EP/3013/REV-AGoogle Scholar
  11. 11.
    Srinivas, C., Bagavath Singh, V., Venkatesan, A., Somavaii, R.: Creation of benchmark Meteorological Observations for RRE on Atmospheric Flow Field at Kalpakkam, IGC Report N. 317Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringSSN College of EngineeringChennaiIndia

Personalised recommendations