Presentation 2018-08-27
Learning ARGO Profiles by using the Signature Method
Nozomi Sugiura, Shigeki Hosoda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A profile in the ARGO ocean observing array can be viewed as a sequence of three-dimensional vectors composed of pressure, salinity, and temperature. Since it appears as a continuous curve in three-dimensional space, the collection of all the iterated integrals, the signature, is able to represent its shape, and the set of signatures fits into an algebraic structure. Moreover, a nonlinear function of the profile shape can be represented by a linear combination of the iterated integrals. Such a mathematical structure allows us to perform machine learning for nonlinear functions with respect to the shape of profiles. This method is applicable to the automatic quality control of the ARGO profile data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Ocean observation / Machine learning / Quality control / Signature
Paper # AI2018-18
Date of Issue 2018-08-20 (AI)

Conference Information
Committee AI
Conference Date 2018/8/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning ARGO Profiles by using the Signature Method
Sub Title (in English)
Keyword(1) Ocean observation
Keyword(2) Machine learning
Keyword(3) Quality control
Keyword(4) Signature
1st Author's Name Nozomi Sugiura
1st Author's Affiliation Japan Agency for Marine-Earth Science and Technology(JAMSTEC)
2nd Author's Name Shigeki Hosoda
2nd Author's Affiliation Japan Agency for Marine-Earth Science and Technology(JAMSTEC)
Date 2018-08-27
Paper # AI2018-18
Volume (vol) vol.118
Number (no) AI-197
Page pp.pp.27-32(AI),
#Pages 6
Date of Issue 2018-08-20 (AI)