Classification of VLF/LF Lightning Signals Using Sensors and Deep Learning Methods

Lightning waveform plays an important role in lightning observation, location, and lightning disaster investigation. Based on a large amount of lightning waveform data provided by existing real-time very low frequency/low frequency (VLF/LF) lightning waveform acquisition equipment, an automatic and accurate lightning waveform classification method becomes extremely important. With the widespread application of deep learning in image and speech recognition, it becomes possible to use deep learning to classify lightning waveforms. In this study, 50,000 lightning waveform samples were collected. The data was divided into the following categories: positive cloud ground flash, negative cloud ground flash, cloud ground flash with ionosphere reflection signal, positive narrow bipolar event, negative narrow bipolar event, positive pre-breakdown process, negative pre-breakdown process, continuous multi-pulse cloud flash, bipolar pulse, skywave. A multi-layer one-dimensional convolutional neural network (1D-CNN) was designed to automatically extract VLF/LF lightning waveform features and distinguish lightning waveforms. The model achieved an overall accuracy of 99.11% in the lightning dataset and overall accuracy of 97.55% in a thunderstorm process. Considering its excellent performance, this model could be used in lightning sensors to assist in lightning monitoring and positioning.

[1]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[2]  Steven J. Goodman,et al.  Comparison of ground‐based 3‐dimensional lightning mapping observations with satellite‐based LIS observations in Oklahoma , 2000 .

[3]  Robert B. Fisher,et al.  Hierarchical Classification of Kelps utilizing Deep Residual Features , 2019, ArXiv.

[4]  O. OlawoleF..  Lightning a Fundamental of Atmospheric Electricity , 2014 .

[5]  D. M. Levine,et al.  Sources of the strongest RF radiation from lightning , 1979 .

[6]  Fredrik Gustafsson,et al.  Determining the initial states in forward-backward filtering , 1996, IEEE Trans. Signal Process..

[7]  C. Gomes,et al.  The fine structure of positive lightning return-stroke radiation fields , 2004, IEEE Transactions on Electromagnetic Compatibility.

[8]  Xuan-Min Shao,et al.  The Los Alamos Sferic Array: A research tool for lightning investigations , 2002 .

[9]  V. Rakov,et al.  Lightning: Physics and Effects , 2007 .

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Jeffrey C. Bailey,et al.  A class of unusual lightning electric field waveforms with very strong high‐frequency radiation , 1989 .

[12]  Vladimir A. Rakov,et al.  LIGHTNING PHENOMENOLOGY AND PARAMETERS IMPORTANT FOR LIGHTNING PROTECTION , 2007 .

[13]  Petros Daras,et al.  Deep Learning on Multi Sensor Data for Counter UAV Applications—A Systematic Review , 2019, Sensors.

[14]  Xiaojiang Du,et al.  A Novel Deep Learning Strategy for Classifying Different Attack Patterns for Deep Brain Implants , 2019, IEEE Access.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Thar Baker,et al.  A Deep Learning Approach for Energy Efficient Computational Offloading in Mobile Edge Computing , 2019, IEEE Access.

[17]  Paul Krehbiel,et al.  A GPS‐based three‐dimensional lightning mapping system: Initial observations in central New Mexico , 1999 .

[18]  C. Rodger,et al.  The world wide lightning location network (WWLLN): Update of status and applications , 2014, 2014 XXXIth URSI General Assembly and Scientific Symposium (URSI GASS).

[19]  Honglin Wu,et al.  A Shallow Network with Combined Pooling for Fast Traffic Sign Recognition , 2017, Inf..

[20]  Yang Zhang,et al.  Observations of narrow bipolar events reveal how lightning is initiated in thunderstorms , 2016, Nature Communications.

[21]  Sang Min Yoon,et al.  Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening † , 2018, Sensors.

[22]  Y. Raǐzer.  Lightning: Physics and Effects , 2004 .

[23]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[24]  J. Lowke.  On the physics of lightning , 2004, IEEE Transactions on Plasma Science.

[25]  Fangyuan Wang,et al.  A Recognition Method for Rice Plant Diseases and Pests Video Detection Based on Deep Convolutional Neural Network , 2020, Sensors.

[26]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[27]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[28]  Fei Wang,et al.  MFB-CBRNN: A Hybrid Network for MI Detection Using 12-Lead ECGs , 2020, IEEE Journal of Biomedical and Health Informatics.

[29]  James B. Brundell,et al.  VLF lightning location by time of group arrival (TOGA) at multiple sites , 2002 .

[30]  Thar Baker,et al.  Prospects of Machine and Deep Learning in Analysis of Vital Signs for the Improvement of Healthcare Services , 2020, Nature-Inspired Computation in Data Mining and Machine Learning.

[31]  Jin He,et al.  Real-Time Multilead Convolutional Neural Network for Myocardial Infarction Detection , 2018, IEEE Journal of Biomedical and Health Informatics.

[32]  John P. Barrett,et al.  A low‐frequency near‐field interferometric‐TOA 3‐D Lightning Mapping Array , 2014 .

[33]  Ting Wu,et al.  Lightning Mapping With an Array of Fast Antennas , 2018 .