Search

At present, for business lightning positioning systems, the classification of lightning discharge types is mostly based on lightning pulse signal features, and there is still a lot of room for improvement. We propose a lightning discharge classification method based on convolutional encoding features. This method utilizes convolutional neural networks to extract encoding features, and uses random forests to classify the extracted encoding features, achieving high accuracy discrimination for various lightning discharge events. Compared with traditional multi-parameter-based methods, the new method proposed in this paper has the ability to identify multiple lightning discharge events and does not require precise detailed feature engineering to extract individual pulse parameters. The accuracy of this method for identifying lightning discharge types in intra-cloud flash (IC), cloud-to-ground flash (CG), and narrow bipolar events (NBEs) is 97%, which is higher than that of multi-parameter methods. Moreover, our method can complete the classification task of lightning signals at a faster speed. Under the same conditions, the new method only requires 28.2 µs to identify one pulse, while deep learning-based methods require 300 µs. This method has faster recognition speed and higher accuracy in identifying multiple discharge types, which can better meet the needs of real-time business positioning. [ABSTRACT FROM AUTHOR]

At present, for business lightning positioning systems, the classification of lightning discharge types is mostly based on lightning pulse signal features, and there is still a lot of room for improvement. We propose a lightning discharge classification method based on convolutional encoding features. This method utilizes convolutional neural networks to extract encoding features, and uses random forests to classify the extracted encoding features, achieving high accuracy discrimination for various lightning discharge events. Compared with traditional multi-parameter-based methods, the new method proposed in this paper has the ability to identify multiple lightning discharge events and does not require precise detailed feature engineering to extract individual pulse parameters. The accuracy of this method for identifying lightning discharge types in intra-cloud flash (IC), cloud-to-ground flash (CG), and narrow bipolar events (NBEs) is 97%, which is higher than that of multi-parameter methods. Moreover, our method can complete the classification task of lightning signals at a faster speed. Under the same conditions, the new method only requires 28.2 µs to identify one pulse, while deep learning-based methods require 300 µs. This method has faster recognition speed and higher accuracy in identifying multiple discharge types, which can better meet the needs of real-time business positioning.

A machine‐learning classifier for radiation waveforms of negative return strokes (RSs) is built and tested based on the Random Forest classifier using a large data set consisting of 14,898 negative RSs and 159,277 intracloud (IC) pulses with 3‐D location information. Eleven simple parameters including three parameters related with pulse characteristics and eight parameters related with the relative strength of pulses are defined to build the classifier. Two parameters for the evaluation of the classifier performance are also defined, including the classification accuracy, which is the percentage of true RSs in all classified RSs, and the identification efficiency, which is the percentage of correctly classified RSs in all true RSs. The tradeoff between the accuracy and the efficiency is examined and simple methods to tune the tradeoff are developed. The classifier achieved the best overall performance with an accuracy of 98.84% and an efficiency of 98.81%. With the same technique, the classifier for positive RSs is also built and tested using a data set consisting of 8,700 positive RSs. The classifier has an accuracy of 99.04% and an efficiency of 98.37%. By examining misclassified waveforms, we show evidence that some RSs and IC discharges produce special radiation waveforms that are almost impossible to correctly classify without 3‐D location information, resulting in a fundamental difficulty to achieve very high accuracy and efficiency in the classification of lightning radiation waveforms. Plain Language Summary: Lightning location systems are required to classify return strokes (RSs) from intracloud (IC) discharges accurately and efficiently because the RS is the main discharge component that poses direct threats to the human society. In this paper, we report a machine‐learning classifier for negative RSs built using a large data set with accurate 3‐D location information. The classifier has an accuracy of 98.84% (98.84% of classified RSs are correct classifications) and an efficiency of 98.81% (98.81% of RSs can be correctly classified). With the same technique, we also built a classifier for positive RSs with similarly high accuracy and efficiency. Our classifiers only require some simple waveform parameters so the same technique can be used by various lightning location systems relatively easily. A sample Python script to use the classifier is provided and readers are encouraged to test the classifier using their own data set. We also demonstrate that some RSs and IC discharges produce abnormal waveforms, so 100% accuracy or efficiency is fundamentally difficult to realize using only waveform information. Key Points: A machine‐learning classifier for negative return strokes (RSs) is built using a large data set with 3‐D location informationBoth an accuracy and an efficiency of about 98.8% are achieved and the accuracy‐efficiency tradeoff can be easily controlledSome RSs and intracloud discharges produce special waveforms that are fundamentally difficult to classify without 3‐D location results [ABSTRACT FROM AUTHOR]

We developed a framework merging unsupervised and supervised machine learning to classify lightning radio signals, and applied it to the possible detection of terrestrial gamma‐ray flashes (TGFs). Recent studies have established a tight connection between energetic in‐cloud pulses (EIPs, >150 kA) and a subset of TGFs, enabling continuous and large‐scale ground‐based TGF detection. However, even with a high peak current threshold, it is time‐consuming to manually search for EIPs in a background of many non‐EIP events, and it becomes even more difficult when a lower peak current threshold is used. Machine learning classifiers are an effective tool. Beginning with unsupervised learning, spectral clustering is performed on the low‐dimensional features extracted by an autoencoder from raw radio waveforms, showing that +EIPs naturally constitute a distinct class of waveform and 6%–7% of the total population. The clustering results are used to form a labeled data set (∼10,000 events) to further train supervised convolutional neural network (CNN) that targets for +EIPs. Our CNN models identify on average 95.2% of true +EIPs with accuracy up to 98.7%, representing a powerful tool for +EIP classification. The pretrained CNN classifier is further applied to identify lower peak current EIPs (LEIPs, >50 kA) from a larger data set (∼30,000 events). Among 10 LEIPs coincident with Fermi TGF observations, 2 previously reported TGFs and 2 unreported but suspected TGFs are found, while the majority are not associated with detectable TGFs. In addition, unsupervised clustering is found to reflect characteristics of the ionosphere reflection height and its effect on radio wave propagation. Plain Language Summary: In this study, we developed a machine learning‐based method to classify lightning radio signals. The method uses unsupervised and supervised machine learning to distinguish different types of signals with high accuracy. The focus of the study is to identify energetic in‐cloud pulses (EIPs) that are associated with a subset of lightning‐related terrestrial gamma‐ray flashes (TGFs). The method successfully identified 95.2% of true EIPs with up to 98.7% accuracy, and discovered new TGF events that were not previously reported. Additionally, the method revealed insights into the ionosphere and radio wave propagation. This method can be useful for studying lightning and other related phenomena. Key Points: A framework merging unsupervised clustering and supervised convolutional neural network (CNN) for lightning classification is developedClustering of positive polarity energetic lightning radio pulses (>150 kA) identifies three processes: +EIPs (6%–7%), +NBEs, and +CGsCNNs detect 95.2% of manually identified +EIPs with up to 98.7% accuracy, enabling studying EIP‐TGF link with lower peak current (>50 kA) [ABSTRACT FROM AUTHOR]

The Earth Networks Total Lightning Network (ENTLN) launched a new processor (P2021) in December 2021. Some major upgrades were made in the new processor, including a new classification algorithm, a new propagation model, and regional data processing architecture. Ground-truth datasets of natural and rocket-triggered lightning acquired in Florida were used to evaluate the performance characteristics of the new processor. Compared to the last processor launched in 2015 (P2015), the stroke classification accuracy increased from 91% to 94% for natural lightning and from 86% to 88% for rocket-triggered lightning. The location accuracy improved significantly with the median location error decreasing from 215 m to 92 m. On a global scale, we found the number of pulses detected by the ENLTN increased in all regions with an overall detection gain of 149%. One can see modest gains in detection in regions with a fairly dense network of sensors and significant gains in regions where sensor density is much lower. Each of the major upgrades as well as their influences on the performance characteristics of the ENLTN are discussed. [ABSTRACT FROM AUTHOR]

A particular strength of lightning remote sensing is the variety of lightning types observed, each with a unique occurrence context and characteristically different emission. Distinct energetic intracloud (EIC) lightning discharges—compact intracloud lightning discharges (CIDs) and energetic intracloud pulses (EIPs)—produce intense RF radiation, suggesting large currents inside the cloud, and they also have different production mechanisms and occurrence contexts. A Low‐Frequency (LF) lightning remote sensing instrument array was deployed during the RELAMPAGO field campaign in west central Argentina, designed to investigate convective storms that produce high‐impact weather. LF data from the campaign can provide a valuable data set for researching the lightning context of EICs in a variety of subtropical convective storms. This paper describes the production of an LF‐CID data set in RELAMPAGO and includes a preliminary analysis of CID prevalence. Geolocated lightning events and their corresponding observed waveforms from the RELAMPAGO LF data set are used in the classification of EICs. Height estimates based on skywave reflections are computed, where prefit residual data editing is used to improve robustness against outliers. Even if EIPs occurred within the network, given the low number of very high‐peak current events and receiver saturation, automatic classification of EIPs may not be feasible using this data. The classification of CIDs, on the other hand, is straightforward and their properties, for both positive and negative polarity, are investigated. A few RELAMPAGO case studies are also presented, where high variability of CID prevalence in ordinary storms and high‐altitude positive CIDs, possibly in overshooting tops, are observed. Key Points: Classification and height estimation of energetic intracloud lightning are investigated using RELAMPAGO Low‐Frequency (LF) lightning waveformsA small number of high‐peak current events and saturation of LF receivers hinder the observation of Energetic In‐Cloud Pulses in RELAMPAGOA catalog of RELAMPAGO Compact Intracloud Discharges is produced to be used in future study of their occurrence in different storm types [ABSTRACT FROM AUTHOR]

Abstract A particular strength of lightning remote sensing is the variety of lightning types observed, each with a unique occurrence context and characteristically different emission. Distinct energetic intracloud (EIC) lightning discharges—compact intracloud lightning discharges (CIDs) and energetic intracloud pulses (EIPs)—produce intense RF radiation, suggesting large currents inside the cloud, and they also have different production mechanisms and occurrence contexts. A Low‐Frequency (LF) lightning remote sensing instrument array was deployed during the RELAMPAGO field campaign in west central Argentina, designed to investigate convective storms that produce high‐impact weather. LF data from the campaign can provide a valuable data set for researching the lightning context of EICs in a variety of subtropical convective storms. This paper describes the production of an LF‐CID data set in RELAMPAGO and includes a preliminary analysis of CID prevalence. Geolocated lightning events and their corresponding observed waveforms from the RELAMPAGO LF data set are used in the classification of EICs. Height estimates based on skywave reflections are computed, where prefit residual data editing is used to improve robustness against outliers. Even if EIPs occurred within the network, given the low number of very high‐peak current events and receiver saturation, automatic classification of EIPs may not be feasible using this data. The classification of CIDs, on the other hand, is straightforward and their properties, for both positive and negative polarity, are investigated. A few RELAMPAGO case studies are also presented, where high variability of CID prevalence in ordinary storms and high‐altitude positive CIDs, possibly in overshooting tops, are observed.

The Earth Networks Total Lightning Network (ENTLN) launched a new processor (P2021) in December 2021. Some major upgrades were made in the new processor, including a new classification algorithm, a new propagation model, and regional data processing architecture. Ground-truth datasets of natural and rocket-triggered lightning acquired in Florida were used to evaluate the performance characteristics of the new processor. Compared to the last processor launched in 2015 (P2015), the stroke classification accuracy increased from 91% to 94% for natural lightning and from 86% to 88% for rocket-triggered lightning. The location accuracy improved significantly with the median location error decreasing from 215 m to 92 m. On a global scale, we found the number of pulses detected by the ENLTN increased in all regions with an overall detection gain of 149%. One can see modest gains in detection in regions with a fairly dense network of sensors and significant gains in regions where sensor density is much lower. Each of the major upgrades as well as their influences on the performance characteristics of the ENLTN are discussed.