Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385979210> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4385979210 abstract "Abstract. Marine heatwaves (MHWs) have significant social and ecological impacts, necessitating the prediction of these extreme events to prevent and mitigate their negative consequences and provide valuable information to decision-makers about MHW-related risks. In this study, machine learning (ML) techniques are applied to predict Sea Surface Temperature (SST) time series and Marine Heatwaves (MHWs) in 16 regions of the Mediterranean Sea. ML algorithms, including Random Forest (RForest), Long short-term memory (LSTM), and Convolutional Neural Network (CNN), are used to create competitive predictive tools for SST. The ML models are designed to forecast SST and MHWs up to 7 days ahead. Alongside SST, other relevant atmospheric variables are utilized as potential predictors of MHWs. Datasets from the European Space Agency Climate Change Initiative (ESA CCI SST) v2.1 and the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA5 reanalysis from 1981 to 2021 are used to train and test the ML techniques. The results show that ML methods, particularly RForest and LSTM, performed well with minimum Root Mean Square Errors (RMSE) of about 0.1 °C at a 1-day lead time and maximum values of about 0.8 °C at a 7-day lead time. Importantly, the ML techniques outperform the dynamical Copernicus Mediterranean Forecasting System (MedFS) for both SST and MHW forecasts, especially in the early forecast days. For MHW forecasting, ML methods outperform MedFS up to 3-day lead time in most regions, while MedFS shows superior skill at 5-day lead time in 9 out of 16 regions. All methods in all regions predict the occurrence of MHWs with a confidence level greater than 50 %. Additionally, the study highlights the importance of incoming solar radiation as a significant predictor of SST variability along with SST itself." @default.
- W4385979210 created "2023-08-19" @default.
- W4385979210 creator A5036116091 @default.
- W4385979210 creator A5041801697 @default.
- W4385979210 creator A5059822941 @default.
- W4385979210 creator A5068367927 @default.
- W4385979210 creator A5087843546 @default.
- W4385979210 date "2023-08-18" @default.
- W4385979210 modified "2023-10-06" @default.
- W4385979210 title "Machine learning methods to predict Sea Surface Temperature and Marine Heatwave occurrence: a case study of the Mediterranean Sea" @default.
- W4385979210 doi "https://doi.org/10.5194/egusphere-2023-1847" @default.
- W4385979210 hasPublicationYear "2023" @default.
- W4385979210 type Work @default.
- W4385979210 citedByCount "0" @default.
- W4385979210 crossrefType "posted-content" @default.
- W4385979210 hasAuthorship W4385979210A5036116091 @default.
- W4385979210 hasAuthorship W4385979210A5041801697 @default.
- W4385979210 hasAuthorship W4385979210A5059822941 @default.
- W4385979210 hasAuthorship W4385979210A5068367927 @default.
- W4385979210 hasAuthorship W4385979210A5087843546 @default.
- W4385979210 hasBestOaLocation W43859792101 @default.
- W4385979210 hasConcept C111368507 @default.
- W4385979210 hasConcept C127313418 @default.
- W4385979210 hasConcept C127413603 @default.
- W4385979210 hasConcept C134097258 @default.
- W4385979210 hasConcept C153294291 @default.
- W4385979210 hasConcept C166957645 @default.
- W4385979210 hasConcept C205649164 @default.
- W4385979210 hasConcept C21547014 @default.
- W4385979210 hasConcept C2779043415 @default.
- W4385979210 hasConcept C2781468064 @default.
- W4385979210 hasConcept C39432304 @default.
- W4385979210 hasConcept C41008148 @default.
- W4385979210 hasConcept C4646841 @default.
- W4385979210 hasConcept C49204034 @default.
- W4385979210 hasConceptScore W4385979210C111368507 @default.
- W4385979210 hasConceptScore W4385979210C127313418 @default.
- W4385979210 hasConceptScore W4385979210C127413603 @default.
- W4385979210 hasConceptScore W4385979210C134097258 @default.
- W4385979210 hasConceptScore W4385979210C153294291 @default.
- W4385979210 hasConceptScore W4385979210C166957645 @default.
- W4385979210 hasConceptScore W4385979210C205649164 @default.
- W4385979210 hasConceptScore W4385979210C21547014 @default.
- W4385979210 hasConceptScore W4385979210C2779043415 @default.
- W4385979210 hasConceptScore W4385979210C2781468064 @default.
- W4385979210 hasConceptScore W4385979210C39432304 @default.
- W4385979210 hasConceptScore W4385979210C41008148 @default.
- W4385979210 hasConceptScore W4385979210C4646841 @default.
- W4385979210 hasConceptScore W4385979210C49204034 @default.
- W4385979210 hasFunder F4320318240 @default.
- W4385979210 hasLocation W43859792101 @default.
- W4385979210 hasOpenAccess W4385979210 @default.
- W4385979210 hasPrimaryLocation W43859792101 @default.
- W4385979210 hasRelatedWork W2001977500 @default.
- W4385979210 hasRelatedWork W2020822748 @default.
- W4385979210 hasRelatedWork W2085015525 @default.
- W4385979210 hasRelatedWork W2099980359 @default.
- W4385979210 hasRelatedWork W2105863468 @default.
- W4385979210 hasRelatedWork W2149938466 @default.
- W4385979210 hasRelatedWork W2353357840 @default.
- W4385979210 hasRelatedWork W3021991339 @default.
- W4385979210 hasRelatedWork W306193203 @default.
- W4385979210 hasRelatedWork W3081257409 @default.
- W4385979210 isParatext "false" @default.
- W4385979210 isRetracted "false" @default.
- W4385979210 workType "article" @default.