{"title":"Deep-learning model for sea surface temperature prediction near the Korean Peninsula","authors":"Hey-Min Choi , Min-Kyu Kim , Hyun Yang","doi":"10.1016/j.dsr2.2023.105263","DOIUrl":null,"url":null,"abstract":"<div><p><span>Recently, sea surface temperatures<span><span> (SSTs) near the Korean Peninsula have increased rapidly due to </span>global warming<span>; this phenomenon can lead to high water temperatures and extensive damage to Korean fish farms. To reduce such damage, it is necessary to predict high water temperature events in advance. In this study, we developed a method for predicting high water temperature events using time series SST data for the Korean Peninsula obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA5 product and a long short-term memory (LSTM) network designed for time series data prediction. First, the SST prediction model was used to predict SSTs. Predicted SSTs exceeding 28 °C, which is the Korean government standard for issuing high water temperature warnings, were designated as high water temperatures. To evaluate the prediction accuracy of the SST prediction model, 1-to 7-day predictions were evaluated in terms of the coefficient of determination (R</span></span></span><sup>2</sup><span>), root mean square error (RMSE), and mean absolute percentage error (MAPE). The R</span><sup>2</sup>, RMSE, and MAPE values of the 1-day prediction SST model were 0.985, 0.14 °C, and 0.38%, respectively, whereas those of the 7-day prediction SST model were 0.574, 0.74 °C, and 2.26%, respectively. We also calculated F1 scores to evaluate high water temperature classification accuracy. The F1 scores of the 1- and 7-day SST prediction models were 0.963 and 0.739, respectively.</p></div>","PeriodicalId":11120,"journal":{"name":"Deep-sea Research Part Ii-topical Studies in Oceanography","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Deep-sea Research Part Ii-topical Studies in Oceanography","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0967064523000139","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OCEANOGRAPHY","Score":null,"Total":0}
引用次数: 0
Abstract
Recently, sea surface temperatures (SSTs) near the Korean Peninsula have increased rapidly due to global warming; this phenomenon can lead to high water temperatures and extensive damage to Korean fish farms. To reduce such damage, it is necessary to predict high water temperature events in advance. In this study, we developed a method for predicting high water temperature events using time series SST data for the Korean Peninsula obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA5 product and a long short-term memory (LSTM) network designed for time series data prediction. First, the SST prediction model was used to predict SSTs. Predicted SSTs exceeding 28 °C, which is the Korean government standard for issuing high water temperature warnings, were designated as high water temperatures. To evaluate the prediction accuracy of the SST prediction model, 1-to 7-day predictions were evaluated in terms of the coefficient of determination (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE). The R2, RMSE, and MAPE values of the 1-day prediction SST model were 0.985, 0.14 °C, and 0.38%, respectively, whereas those of the 7-day prediction SST model were 0.574, 0.74 °C, and 2.26%, respectively. We also calculated F1 scores to evaluate high water temperature classification accuracy. The F1 scores of the 1- and 7-day SST prediction models were 0.963 and 0.739, respectively.
期刊介绍:
Deep-Sea Research Part II: Topical Studies in Oceanography publishes topical issues from the many international and interdisciplinary projects which are undertaken in oceanography. Besides these special issues from projects, the journal publishes collections of papers presented at conferences. The special issues regularly have electronic annexes of non-text material (numerical data, images, images, video, etc.) which are published with the special issues in ScienceDirect. Deep-Sea Research Part II was split off as a separate journal devoted to topical issues in 1993. Its companion journal Deep-Sea Research Part I: Oceanographic Research Papers, publishes the regular research papers in this area.