Abstract
Thunderstorms are an unpredictable natural hazard. They affect daily human life especially for space launcher development program in the near future. The variations in meteorological parameters were used to capture thunderstorm activity. In this study, six parameters, namely pressure, temperature, relative humidity, cloud, rainfall and precipitable water vapor were analyzed in order to develop a thunderstorm prediction system. To realize the development of this thunderstorm prediction system, we developed a thunderstorm prediction model based on the Adaptive Neuro-fuzzy Inference System (ANFIS) family (ANFIS FCM, ANFIS FSC, and ANFIS Human Expert). Three models from the ANFIS family were assessed to ascertain their capability for thunderstorm prediction. Input and output variables were taken from the Tawau meteorology station. The results showed that the thunderstorm prediction model based on ANFIS Human Expert showed a good efficiency with an estimated error prediction of <2% with root mean square error (RMSE) and percentage error (PE) values of 3.028% and 23.545% respectively compared to RMSE and PE of ANFIS FCM and ANFIS FSC.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Suparta W, Putro WS, Singh MSJ, Asillam MF (2015) Characterization of GPS and meteorological parameters for mesoscale convective systems model over Tawau, Malaysia. Adv Sci Lett 21:203–206
Suparta W, Putro WS, Singh MSJ, Asillam MF (2015) The estimation of rainfall and precipitation variation during 2011 convective system using an artificial neural network over Tawau, Sabah. Paper presented at the 2015 IEEE international conference on space science and communication, space science centre (ANGKASA), Universiti Kebangsaan Malaysia, Langkawi, 10–12 August 2015
Chen TC, Wang SY, Yen MC (2007) Enhancement of afternoon thunderstorm activity by urbanization in a valley: Taipei. J Appl Meteorol Climatol 46:1324–1340
Loo YY, Billa L, Singh A (2015) Effect of climate change on seasonal monsoon in Asia and its impact on the variability of monsoon rainfall in Southeast Asia. Geosci Front 6:817–823
Heistermann M, Crisologo I, Abon CC, Racoma BA, Jacobi S, Servando NT, David CPC, Bronstert A (2013) Using the new Philippine radar network to reconstruct the Habagat of August 2012 monsoon event around Metropolitan Manila. Nat Hazards Earth Syst Sci 13:653–657
Albar AMH, AL-Khalaf AK, Mohamed HAB (2015) Radar rainfall estimation of a severe thunderstorm over Jeddah. Atmos Clim Sci 5:302
Velden C, Harper B, Wells F, Beven JL II (2006) The Dvorak tropical cyclone intensity estimation technique. Bull Am Meteorol Soc 87:1195
Spiridonov V, Curic M (2015) A storm modeling system as an advanced tool in prediction of well organized slowly moving convective cloud system and early warning of severe weather risk. Asia Pac J Atmos Sci 51:61–75
Litta AJ, Mary Idicula S, Mohanty UC (2013) Artificial neural network model in prediction of meteorological parameters during premonsoon thunderstorms. Int J Atmos Sci 1:1–14
Suykens JAK (2001) Nonlinear modeling and support vector machine. Paper presented at the 2001 IEEE instrumentation and measurement technology conference, Budapest convention centre, Budapest, Hungary, 21–23 May 2001
Rajasekaran S, Pai GV (2004) Neural networks. Fuzzy Logic and Genetic Algorithms. PEU Learning Pvt. Ltd, New Delhi, pp 17–456
Suparta W, Alhasa KM (2015) Modeling of zenith path delay over Antarctica using an adaptive neuro fuzzy inference system technique. Expert Syst Appl 42:1050–1064
Cao Z, Kandel A, Li L (1990) A new model of fuzzy reasoning. Fuzzy Sets Syst 36:311–325
Stohlgren TJ, Chase TN, Pielke RA, Kittel TG, Baron J (1998) Evidence that local land use practices influence regional climate, vegetation, and stream flow patterns in adjacent natural areas. Glob Change Biol 4:495–504
Xu X, Tang Q, Xia H, Zhang Y, Li W, Huo X (2016) Chaotic time series prediction for prenatal exposure to polychlorinated biphenyls in umbilical cord blood using the least squares SEATR model. Sci Rep 6:25005
Acknowledgements
This research is supported by Ministry of Science, Technology and Innovation Malaysia (MOSTI) under Science Fund 01-01-02-SF1100 grant and partly funded by Flagship Program: ZF-2014-016 grant. The authors would like thank MetMalaysia, weather underground, NASA and Wyoming University for providing the meteorological data used in this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Suparta, W., Putro, W.S. (2018). Parametric Studies of ANFIS Family Capability for Thunderstorm Prediction. In: Suparta, W., Abdullah, M., Ismail, M. (eds) Space Science and Communication for Sustainability. Springer, Singapore. https://doi.org/10.1007/978-981-10-6574-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-10-6574-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6573-6
Online ISBN: 978-981-10-6574-3
eBook Packages: EngineeringEngineering (R0)