Sato, T., and H. Kusaka, 2021: Statistical intercomparison of similarity metrics in sea level pressure pattern classification. J. Meteor. Soc. Japan, 99,
Early Online Release Graphical Abstract NEW GA
Plain Language Summary:
We compare the accuracy of five representative similarity metrics in extracting sea level pressure (SLP) patterns for accurate weather chart classification. We use a large amount of teacher data to statistically evaluate the accuracy of each metric. The evaluation results reveal that S1 and SSIM have the highest accuracy in terms of both average and maximum scores. Their accuracy does not change even when non-ideal data are used as the teacher data.
- The accuracy of five representative similarity metrics is compared in extracting sea level pressure (SLP) patterns using a large amount of teacher data.
- S1-score and SSIM have the highest accuracy and their accuracy does not change even when non- ideal teacher data are used.
- This study can serve as a reference for identifying the most useful similarity metric for the classification of SLP patterns, especially when using non-ideal teacher data.