Isam Elafi , Nabila Zrira , Assia Kamal-Idrissi , Haris Ahmad Khan , Aziz Ettouhami
{"title":"STA-SST: Spatio-temporal time series prediction of Moroccan Sea surface temperature","authors":"Isam Elafi , Nabila Zrira , Assia Kamal-Idrissi , Haris Ahmad Khan , Aziz Ettouhami","doi":"10.1016/j.seares.2024.102515","DOIUrl":null,"url":null,"abstract":"<div><p>Global Sea Surface Temperature (SST) trends have garnered significant attention in several ocean-related domains, including global warming, marine biodiversity, and environmental protection. This involves having an accurate and efficient forecast of future SST to ensure early detection and response in time to these events. Deep learning algorithms have become popular in SST prediction recently, although directly obtaining optimal prediction results from historical observation data is not simple. In this paper, we propose STA-SST, a new deep learning approach for forecasting SST, by combining the temporal dependencies of SST using the Bidirectional Long Short-Term Memory (BiLSTM) model, spatial features extracted from the convolution layer, and relevant information from the attention mechanism. To assess how well the Attention-BiLSTM with convolution layer predicts SST, we conducted a case study in the Moroccan Sea, concentrating on five different areas. The proposed model was compared against alternative forecasting models, including LSTM, XGBoost, Support Vector Regression (SVR), and Random Forest (RF). The experimental results show that STA-STT produces noticeably the best prediction results and is a solid choice for field implementation.</p></div>","PeriodicalId":50056,"journal":{"name":"Journal of Sea Research","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1385110124000480/pdfft?md5=7bb92d5f156221fad4655ecd2f92ac4d&pid=1-s2.0-S1385110124000480-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Sea Research","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1385110124000480","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MARINE & FRESHWATER BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Global Sea Surface Temperature (SST) trends have garnered significant attention in several ocean-related domains, including global warming, marine biodiversity, and environmental protection. This involves having an accurate and efficient forecast of future SST to ensure early detection and response in time to these events. Deep learning algorithms have become popular in SST prediction recently, although directly obtaining optimal prediction results from historical observation data is not simple. In this paper, we propose STA-SST, a new deep learning approach for forecasting SST, by combining the temporal dependencies of SST using the Bidirectional Long Short-Term Memory (BiLSTM) model, spatial features extracted from the convolution layer, and relevant information from the attention mechanism. To assess how well the Attention-BiLSTM with convolution layer predicts SST, we conducted a case study in the Moroccan Sea, concentrating on five different areas. The proposed model was compared against alternative forecasting models, including LSTM, XGBoost, Support Vector Regression (SVR), and Random Forest (RF). The experimental results show that STA-STT produces noticeably the best prediction results and is a solid choice for field implementation.
期刊介绍:
The Journal of Sea Research is an international and multidisciplinary periodical on marine research, with an emphasis on the functioning of marine ecosystems in coastal and shelf seas, including intertidal, estuarine and brackish environments. As several subdisciplines add to this aim, manuscripts are welcome from the fields of marine biology, marine chemistry, marine sedimentology and physical oceanography, provided they add to the understanding of ecosystem processes.