File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An unsupervised learning approach to study synchroneity of past events in the South China Sea

TitleAn unsupervised learning approach to study synchroneity of past events in the South China Sea
Authors
Keywordsmachine learning
ocean sediment
sunsupervised classification
Issue Date2019
PublisherSpringer Verlag. The Journal's web site is located at http://www.springer.com/earth+sciences/journal/11707
Citation
Frontiers of Earth Science in China, 2019, v. 13, p. 628-640 How to Cite?
AbstractUnsupervised machine learning methods were applied on multivariate geophysical and geochemical datasets of ocean floor sediment cores collected from the South China Sea. The well-preserved and continuous core samples comprising high resolution Cenozoic sediment records enable scientists to carry out paleoenvironment studies in detail. Bayesian age-depth chronological models constructed from biostratigraphic control points for the drilling sites are applied on cluster boundaries generated from two popular unsupervised learning methods: K-means and random forest. The unsupervised learning methods experimented have produced compact and unambiguous clusters from the datasets, indicating that previously unknown data patterns can be revealed when all variables from the datasets are taken into account simultaneously. A study of synchroneity of past events represented by the cluster boundaries across geographically separated ocean drilling sites is achieved through converting the fixed depths of cluster boundaries into chronological ranges represented by Gaussian density plots which are then compared with known past events in the region. A Gaussian density peak at around 7.2 Ma has been identified from results of all three sites and it is suggested to coincide with the initiation of the East Asian monsoon. Contrary to traditional statistical approach, a priori assumptions are not required for unsupervised learning, and the clustering results serve as a novel data-driven proxy for studying the complex and dynamic processes of the paleoenvironment surrounding the ocean sediment. This work serves as a pioneering approach to extract valuable information of regional events and opens up a systematic and objective way to study the vast global ocean sediment datasets.
Persistent Identifierhttp://hdl.handle.net/10722/287936
ISSN
2015 SCImago Journal Rankings: 0.424
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorTSE, KC-
dc.contributor.authorChiu, HC-
dc.contributor.authorTsang, MY-
dc.contributor.authorLi, Y-
dc.contributor.authorLam, EY-
dc.date.accessioned2020-10-05T12:05:25Z-
dc.date.available2020-10-05T12:05:25Z-
dc.date.issued2019-
dc.identifier.citationFrontiers of Earth Science in China, 2019, v. 13, p. 628-640-
dc.identifier.issn1673-7385-
dc.identifier.urihttp://hdl.handle.net/10722/287936-
dc.description.abstractUnsupervised machine learning methods were applied on multivariate geophysical and geochemical datasets of ocean floor sediment cores collected from the South China Sea. The well-preserved and continuous core samples comprising high resolution Cenozoic sediment records enable scientists to carry out paleoenvironment studies in detail. Bayesian age-depth chronological models constructed from biostratigraphic control points for the drilling sites are applied on cluster boundaries generated from two popular unsupervised learning methods: K-means and random forest. The unsupervised learning methods experimented have produced compact and unambiguous clusters from the datasets, indicating that previously unknown data patterns can be revealed when all variables from the datasets are taken into account simultaneously. A study of synchroneity of past events represented by the cluster boundaries across geographically separated ocean drilling sites is achieved through converting the fixed depths of cluster boundaries into chronological ranges represented by Gaussian density plots which are then compared with known past events in the region. A Gaussian density peak at around 7.2 Ma has been identified from results of all three sites and it is suggested to coincide with the initiation of the East Asian monsoon. Contrary to traditional statistical approach, a priori assumptions are not required for unsupervised learning, and the clustering results serve as a novel data-driven proxy for studying the complex and dynamic processes of the paleoenvironment surrounding the ocean sediment. This work serves as a pioneering approach to extract valuable information of regional events and opens up a systematic and objective way to study the vast global ocean sediment datasets.-
dc.languageeng-
dc.publisherSpringer Verlag. The Journal's web site is located at http://www.springer.com/earth+sciences/journal/11707-
dc.relation.ispartofFrontiers of Earth Science in China-
dc.rightsThis is a post-peer-review, pre-copyedit version of an article published in [insert journal title]. The final authenticated version is available online at: https://doi.org/[insert DOI]-
dc.subjectmachine learning-
dc.subjectocean sediment-
dc.subjectsunsupervised classification-
dc.titleAn unsupervised learning approach to study synchroneity of past events in the South China Sea-
dc.typeArticle-
dc.identifier.emailLi, Y: yiliang@hku.hk-
dc.identifier.emailLam, EY: elam@eee.hku.hk-
dc.identifier.authorityLi, Y=rp01354-
dc.identifier.authorityLam, EY=rp00131-
dc.identifier.doi10.1007/s11707-019-0748-x-
dc.identifier.scopuseid_2-s2.0-85070299224-
dc.identifier.hkuros314908-
dc.identifier.volume13-
dc.identifier.spage628-
dc.identifier.epage640-
dc.identifier.isiWOS:000490321200014-
dc.publisher.placeChina-
dc.identifier.issnl1673-7385-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats