Dataset Information

Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits.

ABSTRACT: Geochemical discrimination has recently been recognised as a potentially useful proxy for identifying tsunami deposits in addition to classical proxies such as sedimentological and micropalaeontological evidence. However, difficulties remain because it is unclear which elements best discriminate between tsunami and non-tsunami deposits. Herein, we propose a mathematical methodology for the geochemical discrimination of tsunami deposits using machine-learning techniques. The proposed method can determine the appropriate combinations of elements and the precise discrimination plane that best discerns tsunami deposits from non-tsunami deposits in high-dimensional compositional space through the use of data sets of bulk composition that have been categorised as tsunami or non-tsunami sediments. We applied this method to the 2011 Tohoku tsunami and to background marine sedimentary rocks. After an exhaustive search of all 262,144 (= 2(18)) combinations of the 18 analysed elements, we observed several tens of combinations with discrimination rates higher than 99.0%. The analytical results show that elements such as Ca and several heavy-metal elements are important for discriminating tsunami deposits from marine sedimentary rocks. These elements are considered to reflect the formation mechanism and origin of the tsunami deposits. The proposed methodology has the potential to aid in the identification of past tsunamis by using other tsunami proxies.

SUBMITTER: Kuwatani T

PROVIDER: S-EPMC4233330 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits.

Kuwatani Tatsu T Nagata Kenji K Okada Masato M Watanabe Takahiro T Ogawa Yasumasa Y Komai Takeshi T Tsuchiya Noriyoshi N

Scientific reports 20141117

Geochemical discrimination has recently been recognised as a potentially useful proxy for identifying tsunami deposits in addition to classical proxies such as sedimentological and micropalaeontological evidence. However, difficulties remain because it is unclear which elements best discriminate between tsunami and non-tsunami deposits. Herein, we propose a mathematical methodology for the geochemical discrimination of tsunami deposits using machine-learning techniques. The proposed method can d ...[more]

PMID: 25399750

Similar Datasets

Project description:BackgroundThe largest earthquake on record in Japan (magnitude 9.0) occurred on March 11, 2011, and the subsequent tsunami devastated the Pacific coast of Northern Japan. These further triggered the Fukushima I nuclear power plant accidents. Such a hugely complex disaster inevitably has negative psychological effects on general populations as well as on the direct victims. While previous disaster studies enrolled descriptive approaches focusing on direct victims, the structure of the psychological adjustment process of people from the general population has remained uncertain. The current study attempted to establish a path model that sufficiently reflects the early psychological adaptation process of the general population to large-scale natural disasters.Methods and findingsParticipants from the primary disaster area (n = 1083) and other areas (n = 2372) voluntarily participated in an online questionnaire study. By constructing path models using a structural equation model procedure (SEM), we examined the structural relationship among psychological constructs known related to disasters. As post-traumatic stress symptoms (PTS) were significantly more present in people in the primarily affected area than in those in secondary- or non-affected areas, the path models were constructed for the primary victims. The parsimoniously depicted model with the best fit was achieved for the psychological-adjustment centered model with quality of life (QoL) as a final outcome.ConclusionThe paths to QoL via negative routes (from negative cognitive appraisal, PTS, and general stress) were dominant, suggesting the importance of clinical intervention for reducing negative cognitive appraisal, and for caring for general stress and PTS to maintain QoL at an early stage of psychological adaptation to a disaster. The model also depicted the presence of a positive route where positive cognitive appraisal facilitates post-traumatic growth (PTG) to achieve a higher QoL, suggesting the potential importance of positive psychological preventive care for unexpected natural disasters.

Dataset Information

Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits.

Publications

Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets