A Machine‐Learning Approach to Classify Cloud‐to‐Ground and Intracloud Lightning.

To know if a lightning discharge reaches the ground or remains within the thundercloud is critical for lightning safety as cloud‐to‐ground lightning poses the greatest threat to life and property. The current classification methods for most lightning detection networks, which are based on the classification of electromagnetic pulses produced by lightning, still have plenty of room to improve, including some known issues to be addressed. We present a machine‐learning approach to classify lightning discharges. The classification model used in this study is based on Support Vector Machines (SVMs). Compared with traditional multiparameter methods, our algorithm does not require extraction of individual pulse parameters and additionally provides a probability for each prediction. Using a representative lightning pulse data collected by the Cordoba Marx Meter Array in Argentina, we found the classification accuracy of our machine‐learning algorithm to be 97%, which is higher than that for the existing lightning detection networks. Plain Language Summary: Electromagnetic signals emitted by lightning can be detected by sensors that are hundreds of kilometers away. Those signals are used to distinguish if the lightning discharge reaches the ground or remains inside the cloud. Higher accuracy of lightning type classification can lead to a better assessment of lightning risk and is also beneficial to lightning climatology studies. We present a machine‐learning–based algorithm to classify lightning pulses. The accuracy of the algorithm is 97%, which is better than those for classification algorithms used by lightning detection networks. Key Points: The classification accuracy of the machine‐learning–based algorithm using a representative lightning pulse data set is 97%Unlike multiparameter classification algorithms, the extraction of pulse parameters is not needed for this machine‐learning algorithmThis algorithm provides a probability for each prediction, which is a valuable metric for prediction uncertainty [ABSTRACT FROM AUTHOR]