Earth Process Model Development by Data Driven Analysis based on Sparse Modeling

2017 Fiscal Year Final Research Report

• Project Area: Initiative for High-Dimensional Data-Driven Science through Deepening of Sparse Modeling
• Project/Area Number: 25120005
• Research Category: Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
• Allocation Type: Single-year Grants
• Review Section: Complex systems
• Research Institution: Tohoku University
• Principal Investigator: Komai Takeshi 東北大学, 環境科学研究科, 教授 (30357024)
• Co-Investigator(Kenkyū-buntansha): 岡本 敦 東北大学, 環境科学研究科, 准教授 (40422092) ; 桑谷 立 国立研究開発法人海洋研究開発機構, 地球内部物質循環研究分野, 研究員 (60646785)
• Co-Investigator(Renkei-kenkyūsha): TSUCHIYA Noriyoshi 東北大学, 大学院環境科学研究科, 教授 (40207410)
• Research Collaborator: NAKAMURA Kengo 東北大学, 大学院環境科学研究科, 助教 ; YOSHIDA Kenta 海洋研究開発機構, 掘削科学センター, 研究員
• Project Period (FY): 2013-06-28 – 2018-03-31
• Keywords: 津波堆積物 / データ解析 / 固体地球科学

Outline of Final Research Achievements

The development of comprehensive framework to extract intrinsic physico-chemical processes hidden in multi-dimensional huge data has been conducted, by introducing the original sparse modeling techniques in the field of earth science. The research areas are the discrimination of tsunami deposits faced on the disaster prevention and the application to basic understanding in solid-earth science and geology, in order to bring fusional approach in the field of big data analysis in earth sciences. For the specific research targets, we have conducted the following three topics for the implementation of data driven analysis. 1) The application to tsunami deposits discrimination method by geochemical data analysis, 2) The risk assessment and behaviors of toxic metals in tsunami deposits, and 3) The introduction of developed sparse modeling to the soli-earth scientific problems.

Free Research Field

環境科学