ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "4a9782c0-ea87-4b64-bbb6-c6bc2bab4919"}, "_deposit": {"id": "2011633", "owners": [1], "pid": {"revision_id": 0, "type": "depid", "value": "2011633"}, "status": "published"}, "_oai": {"id": "oai:u-ryukyu.repo.nii.ac.jp:02011633", "sets": ["1642838338003", "1642838406845"]}, "author_link": [], "item_1617186331708": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Domain knowledge integration into deep learning for typhoon intensity classifcation", "subitem_1551255648112": "en"}]}, "item_1617186419668": {"attribute_name": "Creator", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Higa, Maiki", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Tanahara, Shinya", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Adachi, Yoshitaka", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Ishiki, Natsumi", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Nakama, Shin", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Yamada, Hiroyuki", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Ito, Kosuke", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Kitamoto, Asanobu", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Miyata, Ryota", "creatorNameLang": "en"}]}]}, "item_1617186476635": {"attribute_name": "Access Rights", "attribute_value_mlt": [{"subitem_1522299639480": "open access", "subitem_1600958577026": "http://purl.org/coar/access_right/c_abf2"}]}, "item_1617186499011": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_1522650717957": "ja", "subitem_1522651041219": "© The Author(s) 2021"}, {"subitem_1522650717957": "en", "subitem_1522650727486": "http://creativecommons.org/licenses/by/4.0/", "subitem_1522651041219": "http://creativecommons.org/licenses/by/4.0/"}]}, "item_1617186626617": {"attribute_name": "Description", "attribute_value_mlt": [{"subitem_description": "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.", "subitem_description_type": "Other"}, {"subitem_description": "論文", "subitem_description_type": "Other"}]}, "item_1617186643794": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_1522300295150": "en", "subitem_1522300316516": "Nature Research"}]}, "item_1617186702042": {"attribute_name": "Language", "attribute_value_mlt": [{"subitem_1551255818386": "eng"}]}, "item_1617186783814": {"attribute_name": "Identifier", "attribute_value_mlt": [{"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/20.500.12000/48845"}]}, "item_1617186920753": {"attribute_name": "Source Identifier", "attribute_value_mlt": [{"subitem_1522646500366": "ISSN", "subitem_1522646572813": "2045-2322"}]}, "item_1617186941041": {"attribute_name": "Source Title", "attribute_value_mlt": [{"subitem_1522650068558": "en", "subitem_1522650091861": "Scientific Reports"}]}, "item_1617187056579": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2021-06-21", "bibliographicIssueDateType": "Issued"}, "bibliographicVolumeNumber": "11"}]}, "item_1617258105262": {"attribute_name": "Resource Type", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_1617265215918": {"attribute_name": "Version Type", "attribute_value_mlt": [{"subitem_1522305645492": "VoR", "subitem_1600292170262": "http://purl.org/coar/version/c_970fb48d4fbd8a85"}]}, "item_1617353299429": {"attribute_name": "Relation", "attribute_value_mlt": [{"subitem_1522306287251": {"subitem_1522306382014": "DOI", "subitem_1522306436033": "https://doi.org/10.1038/s41598-021-92286-w"}}, {"subitem_1522306287251": {"subitem_1522306382014": "DOI", "subitem_1522306436033": "https://doi.org/10.1038/s41598-021-92286-w"}}]}, "item_1617605131499": {"attribute_name": "File", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "download_preview_message": "", "file_order": 0, "filename": "s41598-021-92286-w.pdf", "future_date_message": "", "is_thumbnail": false, "mimetype": "", "size": 0, "url": {"objectType": "fulltext", "url": "https://u-ryukyu.repo.nii.ac.jp/record/2011633/files/s41598-021-92286-w.pdf"}, "version_id": "d4f203cc-7a80-4aca-a7b7-895715880963"}]}, "item_title": "Domain knowledge integration into deep learning for typhoon intensity classifcation", "item_type_id": "15", "owner": "1", "path": ["1642838338003", "1642838406845"], "permalink_uri": "http://hdl.handle.net/20.500.12000/48845", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2021-09-02"}, "publish_date": "2021-09-02", "publish_status": "0", "recid": "2011633", "relation": {}, "relation_version_is_last": true, "title": ["Domain knowledge integration into deep learning for typhoon intensity classifcation"], "weko_shared_id": -1}
  1. 学術雑誌論文
  2. その他
  1. 部局別インデックス
  2. 工学部

Domain knowledge integration into deep learning for typhoon intensity classifcation

http://hdl.handle.net/20.500.12000/48845
http://hdl.handle.net/20.500.12000/48845
9829133f-6915-4f36-b211-f737f3023dce
名前 / ファイル ライセンス アクション
s41598-021-92286-w.pdf s41598-021-92286-w.pdf
Item type デフォルトアイテムタイプ(フル)(1)
公開日 2021-09-02
タイトル
タイトル Domain knowledge integration into deep learning for typhoon intensity classifcation
言語 en
作成者 Higa, Maiki

× Higa, Maiki

en Higa, Maiki

Search repository
Tanahara, Shinya

× Tanahara, Shinya

en Tanahara, Shinya

Search repository
Adachi, Yoshitaka

× Adachi, Yoshitaka

en Adachi, Yoshitaka

Search repository
Ishiki, Natsumi

× Ishiki, Natsumi

en Ishiki, Natsumi

Search repository
Nakama, Shin

× Nakama, Shin

en Nakama, Shin

Search repository
Yamada, Hiroyuki

× Yamada, Hiroyuki

en Yamada, Hiroyuki

Search repository
Ito, Kosuke

× Ito, Kosuke

en Ito, Kosuke

Search repository
Kitamoto, Asanobu

× Kitamoto, Asanobu

en Kitamoto, Asanobu

Search repository
Miyata, Ryota

× Miyata, Ryota

en Miyata, Ryota

Search repository
アクセス権
アクセス権 open access
アクセス権URI http://purl.org/coar/access_right/c_abf2
権利情報
言語 ja
権利情報 © The Author(s) 2021
権利情報
言語 en
権利情報Resource http://creativecommons.org/licenses/by/4.0/
権利情報 http://creativecommons.org/licenses/by/4.0/
内容記述
内容記述タイプ Other
内容記述 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.
内容記述
内容記述タイプ Other
内容記述 論文
出版者
言語 en
出版者 Nature Research
言語
言語 eng
資源タイプ
資源タイプ journal article
資源タイプ識別子 http://purl.org/coar/resource_type/c_6501
出版タイプ
出版タイプ VoR
出版タイプResource http://purl.org/coar/version/c_970fb48d4fbd8a85
識別子
識別子 http://hdl.handle.net/20.500.12000/48845
識別子タイプ HDL
関連情報
識別子タイプ DOI
関連識別子 https://doi.org/10.1038/s41598-021-92286-w
関連情報
識別子タイプ DOI
関連識別子 https://doi.org/10.1038/s41598-021-92286-w
収録物識別子
収録物識別子タイプ ISSN
収録物識別子 2045-2322
収録物名
言語 en
収録物名 Scientific Reports
書誌情報
巻 11, 発行日 2021-06-21
戻る
0
views
See details
Views

Versions

Ver.1 2022-02-01 06:52:12.001508
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3