DO009
From Global Models to Local Seas: Statistical and Machine Learning Approaches to Ocean Downscaling
Session ID#: 253589
Session Description:
Global Climate Models (GCMs) have too coarse spatial resolution to provide the localized climate information needed for resource management. While dynamical downscaling improves spatial resolution by explicitly solving the physical and biogeochemical equations, it is computationally expensive and requires substantial resources. Statistical downscaling complements dynamical downscaling by offering computationally efficient methods for refining GCM outputs, enabling high-resolution projections which are essential for informed decision-making in diverse ocean regions. Statistical downscaling can be applied to historical reconstructions, seasonal forecasts, and probabilistic projections of future climate. Methods span traditional statistical methods to cutting-edge machine learning tools. Sharing examples across regions will advance the science of statistical downscaling in the ocean because the appropriate method is determined by the specifics of the problem and data availability. This session invites contributions that apply and explore statistical downscaling methods in all areas of ocean science.
Co-Sponsor(s):
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1637 Regional climate change [GLOBAL CHANGE]
4255 Numerical modeling [OCEANOGRAPHY: GENERAL]
4805 Biogeochemical cycles, processes, and modeling [OCEANOGRAPHY: BIOLOGICAL AND CHEMICAL]
Primary Chair: Dr. Amber M. Holdsworth, MSc PhD , Fisheries and Oceans Canada, Institute of Ocean Sciences, Sidney, BC, Canada
Co-chairs: Albert J Hermann, University of Washington, Cooperative Institute for Climate, Ocean, and Ecosystem Studies (CICOES), Seattle, United States and Susan Allen, University of British Columbia, Earth, Ocean and Atmospheric Sciences, Vancouver, BC, Canada
Advanced weather typing for downscaling of wave climate and storm surge at a UK nuclear power station (2007102)
Zehua Zhong1, Hachem Kassem1, Ivan David Haigh1, Dafni Sifnioti2, Ben Gouldby3, Ye Liu3 and Paula Camus4, (1)University of Southampton, Ocean and Earth Science, Southampton, United Kingdom, (2)EDF R&D, London, United Kingdom, (3)HR Wallingford, Wallingford, United Kingdom, (4)Universidad de Cantabria, GeoOcean, Santander, Spain
A computationally efficient alternative to dynamic downscaling: a case study on coastal heatwaves (2021155)
Jian Su1, Tian Tian2, Elena Tomasi3 and Gabriele Franch3, (1)Danish Meteorological Institute, Copenhagen, DENMARK, (2)Danish Meteorological Institute, Copenhagen, Denmark, (3)Fondazione Bruno Kessler, Data Science for Industry and Physics, Trento, Italy
CMIP6-based projections of future wave climate offshore of the Brazilian southeastern coast: a statistical downscaling application (2021277)
Rafael Goncalves1, Tomas Carlotto1, Laura Cagigal2, Fernando J. Mendez3, Antonio Henrique da Fontoura Klein1 and Antonio F. H. Fetter Filh1, (1)Federal University of Santa Catarina, Florianópolis, Brazil, (2)University of Cantabria, GeoOcean, Santander, Spain, (3)Universidad de Cantabria, GeoOcean, Santander, Spain
A nonlinear mapping of ocean climate projections toward observations with species tolerance in eastern Canadian marine regions (2022764)
Rick Danielson1, Erin McKee2, Brendan DeTracey2, Marc Skinner2, Blair J W Greenan2, Ellen Kenchington2 and Zeliang Wang2, (1)Bedford Institute of Oceanography, Halifax, NS, CANADA, (2)Fisheries and Oceans Canada, Dartmouth, Canada
Upscaling of the Porous Shallow Water Equations through the Use of Periodic Homogenization (2026650)
Lisa Patrascu, University of Toronto, Institute for Aerospace Studies, Toronto, ON, Canada, Nicholas Kevlahan, McMaster University, Department of Mathematics and Statistic, Hamilton, Canada, Laurent Debreu, Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, France and Patrick Marchesiello, Institut de Recherche pour le Développement (IRD), Laboratoire d'Etudes en Géophysique et Océanographie Spatiales (LEGOS), Toulouse, France
Novel approach to climate emulation reveals future changes in Oregon coastal flood drivers (2029846)
Nathaniel Fillman1, Carson Williams2, David Earl Rupp3, Peter Ruggiero4, Felicia Olmeta-Schult5 and Esthela Carvajal1, (1)Oregon State University, College of Earth, Ocean, and Atmospheric Sciences, Corvallis, United States, (2)Oregon State University, College of Earth, Ocean, and Atmospheric Science, Corvallis, OR, United States, (3)Oregon State University, Oregon Climate Change Research Institute, Corvallis, United States, (4)Oregon State University, Corvallis, OR, United States, (5)Oregon Sea Grant, Corvallis, United States
CNN-based Multimodel Statistical Downscaling of Coastal Winds in the Peruvian Upwelling System Under SSP5-8.5 Scenario (2031575)
André Ruiz Ccori1,2, Adolfo Chamorro3, Sophie Giffard-Roisin4, Jorge Tam2, Vincent Echevin5 and Francois Colas6, (1)Universidad Peruana Cayetano Heredia, Lima, Peru, (2)Instituto del Mar del Perú (IMARPE), Callao, Peru, (3)Pontificia Universidad Católica del Perú, Lima, Peru, (4)Univ. Grenoble Alpes, Univ. Savoie Mont Blanc, CNRS, IRD, Univ. Gustave Eiffel, ISTerre, Grenoble, France, (5)LOCEAN-IPSL, IRD/CNRS/Sorbonne Universités (UPMC)/MNHN, UMR 7159, Paris, France, (6)LOPS, IRD/CNRS/Université Bretagne Occidentale/IFREMER, IUEM, Plouzane, France
From Large to Local Scale: A Unified Deep Learning Framework for Statistical Ocean Downscaling in the Adriatic Sea (2034869)
Leonardo Saccotelli1, Alessandro de Lorenzis1, Giorgia Verri1 and Rosalia Maglietta1,2, (1)CMCC Foundation - Euro-Mediterranean Center on Climate Change, Lecce, Italy, (2)Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing, CNR-STIIMA, Bari, Italy
Analysing future risk of coral bleaching on the Great Barrier Reef using machine learning (2037583)
Ajitha Cyriac, Commonwealth Scientific and Industrial Research Organisation, Perth, AUSTRALIA, Chaojiao Sun, CSIRO, Environment, Perth, Western Australia, Australia, John Taylor, Australian National University, Canberra, Australia; CSIRO Data61, Canberra, Australia, Richard Matear, CSIRO, Oceans & Atmosphere, Hobart, TAS, Australia, Jyoteeshkumar Papari, CSIRO Hobart, Hobart, TAS, Australia, Scott Condie, CSIRO, Environment, Hobart, Australia and Tongliang Liu, University of Sydney, Sydney, Australia
