Multidisciplinary and Interdisciplinary(M)
Session Sub-categoryGeneral Geosciences, Information Geosciences & Simulations
Session IDM-GI27
Related FieldsS, P, H, A, B
TitleData-driven geosciences
Short TitleData-driven geosciences
Main ConvenerNameTatsu Kuwatani
AffiliationJapan Agency for Marine-Earth Science and Technology
Co-Convener 1NameHiromichi Nagao
AffiliationEarthquake Research Institute, The University of Tokyo
Co-Convener 2NameTakane Hori
AffiliationR&D Center for Earthquake and Tsunami, Japan Agency for Marine-Earth Science and Technology
Session LanguageJJ
ScopeIt is important to extract essential processes and structures from observed data sets in order to understand and predict the dynamic behavior of the earth and planetary systems. Recently, many powerful methodologies have been proposed to extract useful information from high-dimensional data sets in information sciences. This session aims to provide an opportunity to gather various geoscientists to have a productive discussion for interdisciplinary collaborations.
Presentation FormatOral and Poster presentation
Invited Authors
  • Shigeru Obayashi (Tohoku University)
  • Hideitsu Hino (University of Tsukuba)
  • Kei Hirose (Kyushu University, RIKEN AIP)
  • Koji Hukushima (University of Tokyo)
  • Masato Okada (Graduate School of Frontier Sciences, The University of Tokyo)
  • Hikaru Iwamori (Department of Solid Earth Geochemistry, Japan Agency for Marine-Earth Science and Technology, Department of Earth and Planetary Sciences, Tokyo Institute of Technology)
  • Yoshinobu Kawahara (Osaka University)
  • Tomoyuki Higuchi (The Institute of Statistical Mathematics)
Time Presentation No Title Presenter Abstract
Oral Presentation May 22 PM1
13:45 - 14:00 MGI27-01A New Direction of Engineering Simulation Driven by Data AssimilationShigeru Obayashi Abstract
14:00 - 14:15 MGI27-02Semiparametric Adaptive Estimation With Nonignorable NonresponseKosuke Morikawa Abstract
14:15 - 14:30 MGI27-03Grain Growth Prediction Based on Data Assimilation by Implementing 4DVar on Phase-Field ModelsShin-ichi Ito Abstract
14:30 - 14:45 MGI27-04Statistical methods for outlier detectionHideitsu Hino Abstract
14:45 - 15:00 MGI27-05Machine learning-based geochemical discrimination of magmatictectonic settingsKenta Ueki Abstract
15:00 - 15:15 MGI27-06Simple structure estimation via prenet regularizationKei Hirose Abstract
Oral Presentation May 22 PM2
15:30 - 15:45 MGI27-07Data-driven scientific approach through Monte Carlo methodsKoji Hukushima Abstract
15:45 - 16:00 MGI27-08Hydrothermal experiments and data-driven approaches for water-rock reactionsAtsushi Okamoto Abstract
16:00 - 16:15 MGI27-09Unraveling the controls on the silica metasomatic reactions during serpentinization using the exchange Monte Carlo method.Ryosuke Oyanagi Abstract
16:15 - 16:30 MGI27-10Seismic Wavefield Imaging of Long-Period Ground Motion in the Tokyo Metropolitan Area, JapanMasayuki Kano Abstract
16:30 - 16:45 MGI27-11Beyond Receiver Functions: Direct Estimation of Green’s Functions Using Reversible-Jump MCMC MethodTakeshi Akuhara Abstract
16:45 - 17:00 MGI27-12Data-driven approach in geosciencesMasato Okada Abstract
Oral Presentation May 23 AM2
10:45 - 11:00 MGI27-13Chemical geodynamics based on statistical analyses and forward simulationHikaru Iwamori Abstract
11:00 - 11:15 MGI27-14Analysis of Rock Fracture Patterns by Persistent HomologyAnna Suzuki Abstract
11:15 - 11:30 MGI27-15Graph theoretic network mapping of rock fracture networks for mechanism classification using machine learning techniquesKyle Steven Bahr Abstract
11:30 - 11:45 MGI27-16Spatiotemporal data analysis with dynamic mode decompositionYoshinobu Kawahara Abstract
11:45 - 12:00 MGI27-17Prediction of ground-motion index using a deep neural networkHisahiko Kubo Abstract
12:00 - 12:15 MGI27-18Automatic Construction of Generative Model by Deep Learning for Earth and Space SciencesTomoyuki Higuchi Abstract
Presentation No Title Presenter Abstract
Poster Presentation May 23 Core Time
MGI27-P01 Geochemical database of Japanese islands based on published domestic data: standardization of metadata and chemical data Satoru Haraguchi Abstract
MGI27-P02 A new clustering method for geochemical data using spatial contextual information: GEOFCM Kenta Yoshida Abstract
MGI27-P03 Effectiveness of use of geological information for geostatistical modeling of metal concentration in deposit Takuya Kiriyama Abstract
MGI27-P04 Identifications of shallow slow earthquakes based on deep learning in the Nankai trough Masaru Nakano Abstract
MGI27-P05 Application of the Earth Mover's distance (EMD) for a quantitative comparison of SPO data from the rigid particle rotation model and the columnar mineral grain in metamorphic rock Taroujirou Matumura Abstract
MGI27-P06 Data-driven approach for understanding and prediction of seismic activity Takane Hori Abstract
MGI27-P07 Data assimilation for massive autonomous systems based on a second-order adjoint method Hiromichi Nagao Abstract
MGI27-P08 Bayesian estimation with replica exchange Monte Carlo method and application to geochemical problems Nagata Kenji Abstract
MGI27-P09 Progress and future prospects of data-driven analysis in solid-earth science Tatsu Kuwatani Abstract