Contact us

AI-TT workshop (Montreal)

Machine Learning for Ocean Prediction: Methods, Applications & Challenges

Recent developments in artificial intelligence (AI) capabilities (including neural network approaches, machine learning and deep learning related tools) have demonstrated the ability to provide accurate forecasts in weather and environmental forecasting. The OceanPredict Artificial Intelligence Task Team (AI-TT) aims to create a forum to discuss recent developments in the application of AI to ocean prediction, to share best practices, and to explore areas for future development.

This 2-day meeting will provide an overview of ongoing and planned activities in machine learning ocean prediction across the global community. Topics span the full breadth of ocean prediction applications, and include downscaling, forecast emulation, hybrid modelling, data assimilation and ensembles, and challenges in evaluating machine learning emulators compared to numerical models.

The workshop will include keynote speakers (details to follow shortly), oral presentations, posters and breakout discussions.

 

  • Create a forum to share progress and experience in the application of AI methods to Ocean Forecasting
  • Provide networking opportunities promoting future collaborations and partnerships
  • Enable breakout discussions on challenges in this field, including best practices in the evaluation methodology used to understand the added value of AI based forecast (improved performance on which variables, physical consistency, etc….)
  • Identify areas for future work and development
  • AI-TT workshop – Montreal
  • 2-day event
  • 13 & 14 April 2026
  • In-person with hybrid options

We invite submissions for the upcoming workshop, “Machine Learning for Ocean Prediction: Methods, Applications & Challenges”. This workshop aims to bring together experts and practitioners exploring the transformative role of machine learning for modelling and prediction of the ocean. Interest areas span global and regional focuses, ocean, sea ice and bio-geo-chemistry, time frames from hours to seasons and beyond, and reanalysis and data-assimilation.

SUBMIT YOUR ABSTRACT

 

Key topics of interest include (but workshop scope is not limited to the following):

  1. Machine Learning Emulators: Design, development, and application of machine learning, including generative approaches, as fast, surrogate models for complex ocean processes 
  2. Hybrid Approaches: Integration of physics-based ocean models and machine learning techniques to enhance predictive accuracy and efficiency, eg. use of ML components (parameterisations, etc) in state-of-the-art physical ocean models, and combining physics and deep learning within in a single differentiable programming framework
  3. Deep Learning for Data Assimilation, and inversion schemes: Innovative uses of deep learning architectures to assimilate diverse oceanographic datasets, including satellite and in-situ observations. Use of ML for ocean state estimation and forecasting.
  4. Evaluation Challenges: Strategies and benchmarks for assessing the performance, robustness, and reliability of deep learning-based emulators in operational settings.
  5. Technical challenges: Operationalization, Novel architectures, Managing and sharing large datasets, etc.
  6. Other relevant ML applications for Ocean prediction (e.g. downscaling applications, ensemble forecasting)

We encourage contributions in the form of oral presentations and posters. Submissions should clearly outline objectives, methodologies, and relevance to the workshop themes.

Join us to advance the science of ocean prediction through cutting-edge machine learning approaches!

Please note that everyone who is planning to attend the AI-TT meeting must register using the link below.

If you like to submit an abstract you have to use the abstract submission form in addition.

 REGISTRATION

NOW CLOSED

 

 ABSTRACT SUBMISSION

NOW CLOSED

You can upload a maximum of 2 abstract. The abstract should be provided as a .doc or .docx file, be no longer than 300 words and should ideally not include a graphic.

Please view a simple template here.

All submitted abstracts are available in the table below in pdf format (some exceptions).

Sorted alphabetically by author.

No/ ID First name Last name Affiliation Abstract title
1 Kunihiro Aoki Meteorological Research Institute, Japan Meteorological Agency Variational autoencoder-based clustering for geophysical fluid circulations with small sample size
3 Daniele Bigoni CMCC Foundation, Italy Assimilation of sea surface temperature in the Mediterranean Sea using ML-based operators
4 Daria Botvynko IMT Atlantique Short-term neural forecasts of ocean dynamics from sparse satellite observations
5 Annalisa Bracco (1) Euro-Mediterranean Center on Climate Change (CMCC) Foundation A Physics Informed Emulator for Ocean Oxygen
6 Annalisa Bracco (2) Euro-Mediterranean Center on Climate Change (CMCC) Foundation Uncovering marine connectivity through sea surface temperature and machine learning
7 Jacopo Dall’Aglio University of Bologna Machine Learning Forecast Correction for Geophysical Fields
8 Alessandro De Lorenzis CMCC Foundation – Euro-Mediterranean Center on Climate Change From Coarse Models to Coastal Detail: A Deep Learning Approach to AI based Statistical Downscaling in the Adriatic Sea
9 Michael Dunphy Institute of Ocean Sciences, Fisheries and Oceans Canada, Sidney, BC, Canada Development of machine-learning emulators for harbour-scale ocean prediction
10 Anass El Aouni (1) Mercator Ocean International OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
11 Anass El Aouni (2) Mercator Ocean International Toward Scalable and Probabilistic Neural Ocean Forecasting
12 Ronan Fablet IMT Atlantique Training end-to-end neural mapping schemes from simulation data for the reconstruction of global-scale sea surface fields
13 Rachel Furner ECMWF Developing a data-driven global ocean and sea-ice model at ECMWF
14 Daniel Holmberg University of Helsinki Accurate Mediterranean Sea forecasting via graph-based deep learning
15 Fang Hou National Marine Environmental Forecasting Center Application and Verification of the Global Wave Intelligent Forecast Model
16 Xudong Huang Department of Oceanography, Dalhousie University Detection and Discrimination of Marine Oil Spills and Look-alike Phenomena in Synthetic Aperture Radar Imagery
17 Geon Min Lee Pukyong National University, Republic of Korea A Deep-Learning Observation Operator for Subsurface Thermohaline Reconstruction from Satellite Surface Observations
18 Xiaoyan Li Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) AI-driven Nanming Model for Three-dimension Ocean Variable Forecasting
19 Mateusz Matuszak Norwegian Meteorological Institute A data driven limited area storm surge model
20 Andrew Moore University of California Santa Cruz Linear Stochastic Emulators of the Ocean Circulation – A Lesson, perhaps, for Machine Learning
21 Jae-Hun Park Department of Ocean Sciences, Inha University Prediction of sea surface currents around the Korean peninsula using artificial neural networks
22 Francois Roy ECCC Application of Deep learning (DL) in the Gulf of St. Lawrence and Estuary
23 Simone Spada National Institute of Oceanography and Applied Geophysics – OGS Bridging Scales in Mediterranean Biogeochemical Prediction: A High-Order Ensemble Assimilation Coupled with AI-Driven Downscaling
24 Joanna Staneva Helmholtz Zentrum HEREON Integrated AI_Physics Approaches for Coastal Prediction Across the Open-to-Coastal Ocean Continuum
25 Christopher Subich Environment & Climate Change Canada Fix the double penalty in data-driven forecasting by modifying the loss function
26 Teresa Tonelli (1) OGS (National Institute of Oceanography and Applied Geophysics), University of Trieste Two-Phase CNN for Model Data Fusion: Predicting 3D Chlorophyll-a in the Mediterranean Sea
27 Teresa Tonelli (2) OGS (National Institute of Oceanography and Applied Geophysics), University of Trieste Filling the Ocean’s Gaps: a Self-Supervised Neural Network for Argo Profiles Data Augmentation
28 Liying Wan National Marine Environmental Forecasting Center AI perform on high resolution three-dimensional ocean forecasting: remote sensing data driven becomes a new possibility
29 Biao Zhang Dalhousie University Hybrid Physics-Guided Data-Driven Estimation of Wave-Induced Doppler shifts for SAR Ocean Surface Current Retrival
30 Xueming Zhu Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) Intelligent forecasting of marine environmental elements in the South China Sea

You can download the latest agenda version here (14 April 2026)

(It includes the presentation assignments but no fixed times yet.)

Agenda overview

Keynote presentation

Chair: Fraser Davidson (ECCC), Rapporteur: Kristian Mogensen (ECMWF)

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems Anass El Aouni Mercator Ocean International Recording

 

Block 1 talks: Ocean Emulators

Chair: Rachel Furner (ECMWF), Rapporteur: Anass El Aouni (MOI)

Toward Scalable and Probabilistic Neural Ocean Forecasting (not avialable) Simon van Gennip Mercator Ocean International, France Recording
Application of Deep learning (DL) in the Gulf of St. Lawrence and Estuary Francois Roy ECCC, Canada Recording
Prediction of sea surface currents around the Korean peninsula using artificial neural networks Jae-Hun Park Department of Ocean Sciences, Inha University, Republic of Korea Recording

Block 2 talks: Observations and Data Assimilation

Chair: Jae-Hun Park (Inha University), Rapporteur: Vikram Khade (ECCC)

Training end-to-end neural mapping schemes from simulation data for the reconstruction of global-scale sea surface fields Daniel Zhu IMT Atlantique, France Recording
Short-term neural forecasts of ocean dynamics from sparse satellite observations Daria Botvynko IMT Atlantique, France Recording
Two-Phase CNN for Model Data Fusion: Predicting 3D Chlorophyll-a in the Mediterranean Sea Teresa Tonelli OGS, University of Trieste, Italy Recording
A Deep-Learning Observation Operator for Subsurface Thermohaline Reconstruction from Satellite Surface Observations Geon Min Lee Pukyong National University, Republic of Korea Recording
AI perform on high resolution three-dimensional ocean forecasting: remote sensing data driven becomes a new possibility  Liying Wan NMEFC, China Recording

Block 3 talks: Emulators

Chair: Charlie Hebert-Pinard (ECCC), Rapporteur: Daniele Bigoni (CMCC)

Linear Stochastic Emulators of the Ocean Circulation – A Lesson, perhaps, for Machine Learning Andrew Moore University of California Santa Cruz, US Recording
A data driven limited area storm surge model Mateusz Matuszak Norwegian Meteorological Institute, Norway Recording
A Physics Informed Emulator for Ocean Oxygen (remote presentation) Annalisa Bracco CMCC,  Italy Recording
Application and Verification of the Global Wave Intelligent Forecast Model  Fang Hou NMEFC, China Recording

Block 4 talks: Downscaling, and other ML applications

Chair: Frederic Dupont (ECCC), Rapporteur: Simon Corbeil-Letourneau (ECCC)

Development of machine-learning emulators for harbour-scale ocean prediction Michael Dunphy Institute of Ocean Sciences, Fisheries and Oceans Canada Recording
From Coarse Models to Coastal Detail: A Deep Learning Approach to AI based Statistical Downscaling in the Adriatic Sea (remote presentation) Alessandro De Lorenzis CMCC, Italy Recording
Integrated AI_Physics Approaches for Coastal Prediction Across the Open-to-Coastal Ocean Continuum Joanna Staneva Helmholtz Zentrum HEREON, Germany Recording
Fix the double penalty in data-driven forecasting by modifying the loss function Christopher Subich ECCC. Canada Recording
Variational autoencoder-based clustering for geophysical fluid circulations with small sample size Kunihiro Aoki Meteorological Research Institute, Japan Meteorological Agency Recording

Posters

Chair: Anass El Aouni (MOI)

Filling the Ocean’s Gaps: a Self-Supervised Neural Network for Argo Profiles Data Augmentation Teresa Tonelli OGS, University of Trieste, Italy Flash talk: Pdf and recording
Assimilation of sea surface temperature in the Mediterranean Sea using ML-based operators Daniele Bigoni CMCC, Italy Flash talk: Pdf and recording
Bridging Scales in Mediterranean Biogeochemical Prediction: A High-Order Ensemble Assimilation Coupled with AI-Driven Downscaling Simone Spada OGS, Italy Flash talk: Pdf and recording
Data-driven ocean modelling at ECMWF Rachel Furner ECMWF Flash talk: Pdf and recording
Physics-Informed Neural Data Assimilation for High-Resolution: Coastal SPM Reconstruction from Model and Satellite data Wei Chen Helmholtz-Zentrum Hereon No flash talk or recording available
Toward an AI-enhanced hydro-morphodynamic model for nature-based solutions in coastal erosion mitigation (abstract only) Nour Dammak Helmholtz-Zentrum Hereon No flash talk or recording available

Discussion session 1: Expectations and requirements for AI in Ocean prediction, and how can the task team best support this

Chair: Gregory Smith (ECCC), Rapporteur: Rachel Furner (ECMWF)

Discussion session 2: Benchmarking, assessment and validation of ML models

Chair: Rachel Furner (ECMWF), Rapporteur: Simon Van Gennip (MOI)

 

Local information about venue, accommodation and transport

 

Transport

The Montreal International Airport (Pierre Elliott Trudeau – YUL) is conveniently located to the Southwest of Montreal in close proximity to the city centre.

The shuttle bus line “747” runs a 24/7 dedicated service to get you from the airport to downtown Montreal. Detailed information about the route and timetable can be found on the STM 747 website. Tickets for the bus are 10$, and can be purchased at airport ticket machines, from metro stations, kiosk and also from the driver, but only if you have exact change (coins only).

Alternative transport is available by taxi, Uber, etc. Information about routes and costs can be found here.

Flight connections to Montreal are very good, with many destinations being direct. Please check here if your airport directly connects to Pierre Trudeau airport (YUL).

If you booked a room at the Double Tree by Hilton, the best connection from the airport is to use the bus 747-2 and vacate the bus at Rene-Levesque / Jeanne-Mance. From there it is a 2 min walk to the hotel entrance. Please check for updates on fares and bus schedule.

 

Accommodation
Click to enlarge

There are many hotels near the meeting venue. Prices are reasonable considering we are in one of the second largest city in Canada. The map (right) shows the location of our venue.  Please check this link to view some of the hotels available nearby.

To book these hotels please make your own arrangements, by using the associated website and booking portals.

Montreal

Montreal is the most populous municipality in the Canadian province of Quebec and the second-most populous municipality in Canada. It is named after Mount Royal, the triple-peaked hill in the heart of the city. The city is centred on the Island of Montreal a few much smaller peripheral islands, the largest of which is Île Bizard. It has a distinct four-season continental climate with warm to hot summers and cold, snowy winters.

French is the city’s official language and is the language spoken at home by almost 50% of the city population, followed by English at 22.8% and 18.3% other languages. This makes Montreal one of the most bilingual cities in Quebec and Canada, with over 59% of the population able to speak both English and French.

Our meeting venue is very close to Old Montreal, a historic area southeast of downtown containing many attractions such as the Old Port of Montreal, Place Jacques-Cartier, Montreal City Hall, the Bonsecours Market, Place d’Armes, Pointe-à-Callière Museum, the Notre-Dame de Montréal Basilica, and the Montreal Science Centre.

Architecture and cobbled streets in Old Montreal have been maintained or restored and are frequented by horse-drawn buggies carrying tourists. Old Montreal is accessible from the downtown core via the underground city and is served by several STM bus routes and Metro stations, ferries to the South Shore and a network of bicycle paths.

The riverside area adjacent to Old Montreal is known as the Old Port. The Old Port was the site of the Port of Montreal, but its shipping operations have been moved to a larger site downstream, leaving the former location as a recreational and historical area maintained by Parks Canada. The new Port of Montreal is Canada’s largest container port and the largest inland port on Earth.

(Source: Wikipedia)

 

Date Description
September 2025 Save the date announcement
28 October 2025 Opening of Call for abstracts
2 January 2026 Call for abstracts closes – now closed
Mid-Jan 2026 Registration opens
End-Jan 2026 Abstract confirmation & early schedule announcement
Mid-February 2026 Registration deadline
13 & 14 April 2026 Workshop
  • AI-TT co-chairs
    • Santha Akella, NOAA
    • Rachel Furner, ECMWF
  • AI-TT members
    • Kristian Mogensen, ECMWF
    • Simon van Gennip, MOi
  • OPST co-chairs
    • Marie Drevillon, MOi
    • Greg Smith, ECCC
  • Local host
    • Greg Smith, ECCC
    • Frederic Dupont, ECCC
    • Fraser Davidson, ECCC
  • OP programme office
    • Stephanie Cuven, MOi
    • Kirsten Wilmer-Becker, Met Office

Share