Machine Learning-Based Lightning Localization Algorithm Using Lightning-Induced Voltages on Transmission Lines

Abstract

In this study, we present a Machine Learning based method to locate lightning flashes using calculations of lightning-induced voltages on a transmission line. The proposed approach takes advantage of the preinstalled voltage measurement systems on power transmission lines to get the data. Hence, it does not require the installation of additional sensors such as ELF, VLF, or VHF. The proposed model is shown to yield reasonable accuracy in estimating 2D geolocations for lightning strike points in a grid of 10x10 km 2 . The median location error obtained is less than 90 m when the sensors are 2 km away from each other. The algorithm is shown to be flexible when it comes to choosing the distance between the two voltage sensors. Furthermore, the changes in the risetime of the return stroke currents had negligible effect on the geolocation accuracies.

Lightning Strike Location Identification Based on 3D Weather Radar Data

“…Mostajabi et al (2019) used machine learning techniques to successfully hindcast nearby and distant lightning hazards by looking at single-site observations of meteorological parameters. Karami et al (2020) presented a machine learning-based method to locate lightning flashes using calculations of lightning-induced voltages on a transmission line. Zhu et al (2021) presented a machinelearning approach (support vector machines) to classify cloudto-ground and intracloud lightning.…”

An Efficient Compression Method for Lightning Electromagnetic Pulse Signal Based on Convolutional Neural Network and Autoencoder

“…Zhu et al [10] used the SVM algorithm to classify representative cloud-to-ground and intracloud lightning, and its accuracy could reach 97%. In locating lightning events, Karami et al [11] proposed using a machine learning method to locate the lightning strike point based on the lightning-induced voltage value measured by sensors on the transmission line. Recently, Wang et al [12] also combined the lightning positioning method with artificial intelligence, and used the deep-learning encoding feature matching method to improve the speed, accuracy and anti-interference ability of the original positioning algorithm.…”

Lightning Location and Peak Current Estimation From Lightning-Induced Voltages on Transmission Lines With a Machine Learning Approach

“…The first attempt to implement this method can be found in [22], whose authors presented an ML-based lightning location algorithm relying on data from preinstalled voltage measurement systems on power transmission lines. In spite of obtaining promising results in terms of location error, the main drawback of [22] is that the model of the physical system (lightning+power network) is really simplified.…”

“…The first attempt to implement this method can be found in [22], whose authors presented an ML-based lightning location algorithm relying on data from preinstalled voltage measurement systems on power transmission lines. In spite of obtaining promising results in terms of location error, the main drawback of [22] is that the model of the physical system (lightning+power network) is really simplified. Indeed, the lightning-induced voltage database required for the ML model training and testing is generated with the Rusck's formula [23] (which is valid for a lossless single-wire transmission line above a perfectly conducting ground), and the excitation source is a step current propagating upward along the lightning channel.…”

“…Furthermore, in [22], the voltage signals are normalized, thus losing information about the peak current. On the contrary, in this work, the peak current is inserted in the target of the ML model, allowing a peak current estimate from voltage measurements.…”