Early Prediction of Margalefidinium polykrikoides Bloom Using a LSTM Neural Network Model in the South Sea of Korea SCIE SCOPUS

DC Field Value Language
dc.contributor.author Shin, Jisun -
dc.contributor.author Kim, Soo Mee -
dc.contributor.author Son, Young Baek -
dc.contributor.author Kim, Keunyong -
dc.contributor.author Ryu, Joo-Hyung -
dc.date.accessioned 2020-04-16T08:25:17Z -
dc.date.available 2020-04-16T08:25:17Z -
dc.date.created 2020-02-04 -
dc.date.issued 2019-09 -
dc.identifier.issn 0749-0208 -
dc.identifier.uri https://sciwatch.kiost.ac.kr/handle/2020.kiost/741 -
dc.description.abstract Harmful algal blooms (HABs) have been occurring within the South Sea of Korea (SSK) for decades, causing significant ecological impacts and economic problems for many fish farms concentrated in coastal areas. The occurrence of HABs is related to various factors, including meteorological and physical factors, making it difficult to predict the timing of their occurrence. However, it is essential to make a preliminary forecast of HAB occurrence through analysis of such factors to minimize the damage. In this study, a deep neural network model of long short-term memory (LSTM) that can predict the occurrence time of Margalefidinium polykrikoides blooms is presented and evaluated. Satellite data were used to extract sea surface temperature (SST) and photosynthetically available radiation (PAR), which are environmental factors known to be related to HABs occurrence. M. polykrikoides blooms that have occurred in the past 21 years (1998-2018) have been shown to be initiated when SST reaches around 25 degrees C within the summer season. The prediction performance of LSTM-based neural network was evaluated using test data from 2017 and 2018, and the root-mean-squared-error (RMSE) and prediction accuracy were determined. Prediction for 2017 matched well with the test data; however, for 2018, the network predicted that a HAB would occur between July 19 and Sep. 03, with an RMSE of 0.233 and accuracy of 94.8 %, but the actual occurrence of HAB was between July 24 and Aug. 20. This study shows that the trained LSTM-based network would be useful for early prediction of the future red tide blooms in SSK. -
dc.description.uri 1 -
dc.language English -
dc.publisher COASTAL EDUCATION & RESEARCH FOUNDATION -
dc.title Early Prediction of Margalefidinium polykrikoides Bloom Using a LSTM Neural Network Model in the South Sea of Korea -
dc.type Article -
dc.citation.endPage 242 -
dc.citation.startPage 236 -
dc.citation.title JOURNAL OF COASTAL RESEARCH -
dc.citation.volume 90 -
dc.citation.number sp1 -
dc.contributor.alternativeName 신지선 -
dc.contributor.alternativeName 김수미 -
dc.contributor.alternativeName 손영백 -
dc.contributor.alternativeName 김근용 -
dc.contributor.alternativeName 유주형 -
dc.identifier.bibliographicCitation JOURNAL OF COASTAL RESEARCH, v.90, no.sp1, pp.236 - 242 -
dc.identifier.doi 10.2112/SI90-029.1 -
dc.identifier.wosid 000485714500030 -
dc.type.docType Article -
dc.description.journalClass 1 -
dc.description.isOpenAccess N -
dc.subject.keywordPlus HARMFUL DINOFLAGELLATE -
dc.subject.keywordPlus COASTAL WATERS -
dc.subject.keywordPlus ALGAL BLOOMS -
dc.subject.keywordPlus RED TIDES -
dc.subject.keywordPlus COCHLODINIUM -
dc.subject.keywordPlus SURFACE -
dc.subject.keywordPlus GROWTH -
dc.subject.keywordAuthor Harmful algal blooms (HABs) -
dc.subject.keywordAuthor Margalefidinium polykrikoides -
dc.subject.keywordAuthor HAB occurrence prediction -
dc.subject.keywordAuthor LSTM neural network -
dc.subject.keywordAuthor South Sea of Korea (SSK) -
dc.relation.journalWebOfScienceCategory Environmental Sciences -
dc.relation.journalWebOfScienceCategory Geography, Physical -
dc.relation.journalWebOfScienceCategory Geosciences, Multidisciplinary -
dc.description.journalRegisteredClass scie -
dc.description.journalRegisteredClass scopus -
dc.relation.journalResearchArea Environmental Sciences & Ecology -
dc.relation.journalResearchArea Physical Geography -
dc.relation.journalResearchArea Geology -
Appears in Collections:
Marine Industry Research Division > Maritime ICT & Mobility Research Department > 1. Journal Articles
Marine Digital Resources Department > Korea Ocean Satellite Center > 1. Journal Articles
Jeju Research Institute > Tropical & Subtropical Research Center > 1. Journal Articles
Files in This Item:
There are no files associated with this item.

qrcode

Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse