HOME    About this site    mypage    Japanese    library    university    Feedback

University of the Ryukyus Repository >
Faculty of Engineering >
Peer-reviewed Journal Articles (Faculty of Engineering) >

Title :Domain knowledge integration into deep learning for typhoon intensity classifcation
Authors :Higa, Maiki
Tanahara, Shinya
Adachi, Yoshitaka
Ishiki, Natsumi
Nakama, Shin
Yamada, Hiroyuki
Ito, Kosuke
Kitamoto, Asanobu
Miyata, Ryota
Issue Date :21-Jun-2021
Abstract :In this report, we propose a deep learning technique for high-accuracy estimation of the intensity class of a typhoon from a single satellite image, by incorporating meteorological domain knowledge. By using the Visual Geometric Group’s model, VGG-16, with images preprocessed with fisheye distortion, which enhances a typhoon’s eye, eyewall, and cloud distribution, we achieved much higher classification accuracy than that of a previous study, even with sequential-split validation. Through comparison of t-distributed stochastic neighbor embedding (t-SNE) plots for the feature maps of VGG with the original satellite images, we also verified that the fisheye preprocessing facilitated cluster formation, suggesting that our model could successfully extract image features related to the typhoon intensity class. Moreover, gradient-weighted class activation mapping (Grad-CAM) was applied to highlight the eye and the cloud distributions surrounding the eye, which are important regions for intensity classification; the results suggest that our model qualitatively gained a viewpoint similar to that of domain experts. A series of analyses revealed that the data-driven approach using only deep learning has limitations, and the integration of domain knowledge could bring new breakthroughs.
URL :https://doi.org/10.1038/s41598-021-92286-w
Type Local :雑誌掲載論文
ISSN :2045-2322
Publisher :Nature Research
URI :http://hdl.handle.net/20.500.12000/48845
Citation :Scientific Reports Vol.11
Appears in Collections:Peer-reviewed Journal Articles (Faculty of Engineering)

Files in This Item:

File Description SizeFormat
s41598-021-92286-w.pdf1758KbAdobe PDFView/Open