Artificial neural network application in an implemented lightning locating system

Abstract Time difference of arrival (TDOA) technique is one of many bases to determine lightning strike location employed in a lightning locating system (LLS). In this technique, at least four measurement sensors are required to correctly locate a lightning strike. Usage of fewer number of sensors will result in non-unique solutions to the generated hyperbolas, and hence wrong lightning strike point. This research aims to correctly determine the strike point even if only three measuring sensors are utilized. An artificial neural network (ANN) based algorithm was developed for a 400 km2 coverage area in Southern Malaysia using time of arrival data collected at the three measuring stations over a certain period. The Levenberg–Marquardt algorithm is demonstrated to correctly identify the lightning strike coordinates with an average error of 350 m. The algorithm has helped the three-station TDOA-based LLS to successfully locate the lightning strike point with a remarkable accuracy comparable to that of commercial systems.

[1]  W. Lyu,et al.  Simulation of cloud-to-ground lightning strikes to structures based on an improved stochastic lightning model , 2020, Journal of Atmospheric and Solar-Terrestrial Physics.

[2]  R. Sathya,et al.  Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification , 2013 .

[3]  S. Jeffrey Underwood,et al.  Cloud-to-Ground Lightning Flash Parameters Associated with Heavy Rainfall Alarms in the Denver, Colorado, Urban Drainage and Flood Control District ALERT Network , 2006 .

[4]  X. Qie,et al.  Characteristics of upward lightning from a 325-m-tall meteorology tower , 2014 .

[5]  R. Orville.  Cloud‐to‐ground lightning flash characteristics in the contiguous United States: 1989–1991 , 1994 .

[6]  Guo H. Huang,et al.  Application of soft computing models to hourly weather analysis in southern Saskatchewan, Canada , 2005, Eng. Appl. Artif. Intell..

[7]  C. Senabre,et al.  Comparative analysis of self organizing maps vs. multilayer perceptron neural networks for short-term load forecasting , 2010, 2010 Modern Electric Power Systems.

[8]  Lambros Ekonomou,et al.  Artificial neural network-based software tool for calculating the lightning performance of high-voltage transmission lines , 2006 .

[9]  André Nunes De Souza,et al.  Evaluation and identification of lightning models by artificial neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[10]  B. Lynn,et al.  Ground-based measurements of the vertical E-field in mountainous regions and the “Austausch” effect , 2017 .

[11]  Mohd Zainal Abidin Ab Kadir,et al.  Recent statistics on lightning fatalities in Malaysia , 2012, 2012 International Conference on Lightning Protection (ICLP).

[12]  Zulkurnain Abdul-Malek,et al.  Localised Single-Station Lightning Detection by Using TOA Method , 2013 .

[13]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .

[14]  C. Price,et al.  Why is lightning more intense over the oceans? , 2020 .

[15]  K.L. Cummins,et al.  An Overview of Lightning Locating Systems: History, Techniques, and Data Uses, With an In-Depth Look at the U.S. NLDN , 2009, IEEE Transactions on Electromagnetic Compatibility.

[16]  Yaping Du,et al.  An improved wave impedance approach for locating close lightning stroke from single station observation and its validation , 2015 .

[17]  Ashutosh Kumar Singh,et al.  Impact of galactic cosmic rays on Earth’s atmosphere and human health , 2011 .

[18]  Zulkurnain Abdul-Malek,et al.  Discriminating cloud to ground lightning flashes based on wavelet analysis of electric field signals , 2018, Journal of Atmospheric and Solar-Terrestrial Physics.

[19]  Ashutosh Kumar Singh,et al.  Lightning and middle atmospheric discharges in the atmosphere , 2015 .

[20]  B. Bates,et al.  Lightning prediction for Australia using multivariate analyses of large-scale atmospheric variables , 2017 .

[21]  S. Choudhury,et al.  A connectionist approach to thunderstorm forecasting , 2004, IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04..

[22]  W. J. Koshak,et al.  TOA Lightning Location Retrieval on Spherical and Oblate Spheroidal Earth Geometries , 2001 .

[23]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[24]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[25]  D. McCann.  A Neural Network Short-Term Forecast of Significant Thunderstorms , 1992 .

[26]  Attila Gulyás.  Application of preventive measures in lightning protection , 2011 .

[27]  Ismail Musirin,et al.  Application of meta-evolutionary programming in ANN-based lightning prediction system , 2010 .

[28]  Daohong Wang,et al.  Charge Structure of Winter Thunderstorm in Japan: a Review and an Update , 2018 .

[29]  Zulkurnain Abdul-Malek,et al.  Modeling of Time of Arrival Method for Lightning Locating Systems , 2015 .

[30]  Dongfang Wang,et al.  Lightning VHF radiation location system based on short-baseline TDOA technique — Validation in rocket-triggered lightning , 2013 .

[31]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[32]  Kenneth L. Cummins,et al.  A Combined TOA/MDF Technology Upgrade of the U.S. National Lightning Detection Network , 1998 .

[33]  Samuel Lukas,et al.  Backpropagation and Levenberg-Marquardt Algorithm for Training Finite Element Neural Network , 2012, 2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation.

[34]  Lambros Ekonomou,et al.  Application of artificial neural network methods for the lightning performance evaluation of Hellenic high voltage transmission lines , 2007 .