Can Bayesian Networks Improve Ground-Strike Point Classification?

• Published in: Atmosphere Vol. 15; no. 7; p. 776
• Main Authors: Lesejane, Wandile, Hunt, Hugh G. P., Schumann, Carina, Ajoodha, Ritesh
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2024
• Subjects: Accuracy; Algorithms; Bayesian analysis; bayesian network; Bayesian theory; Classification; Cloud-to-ground lightning; Datasets; ground-strike point; IEC62858; Lightning; lightning location systems; Lightning strokes; Locating; Machine learning; Mathematical models; Networks; Probability; Probability distribution; Probability theory; Risk assessment; Structure-function relationships; Variables
• ISSN: 2073-4433; 2073-4433
• DOI: 10.3390/atmos15070776

Studying cloud-to-ground lightning strokes and ground-strike points provides an alternative method of lightning mapping for lightning risk assessment. Various k-means algorithms have been used to verify the ground-strike points from lightning locating systems, producing results with room for improvement. This paper proposes using Bayesian networks (BNs), a model not previously used for this purpose, to classify lightning ground-strike points. A Bayesian network is a probabilistic graphical model that uses Bayes’ theorem to represent the conditional dependencies of variables. The networks created for this research were trained from the data using a score-based structure-learning procedure and the Bayesian information criterion score function. The models were evaluated using confusion matrices and kappa indices and produced accuracy values ranging from 86% to 94% and kappa indices of up to 0.76. While BN models do not outperform k-means algorithms, they offer an alternative by not requiring predetermined distances. However, the easy implementation of the k-means approach means that no significant gain is made by implementing the more complex Bayesian network approach.