Professor Haymet is an emeritus distinguished professor of oceanography. He has researched and taught for many years in Australia and in the United States, including as Established Chair of Theoretical Chemistry at the University of Sydney.

From 2002 to 2006, Prof Haymet was chief of CSIRO Marine and Atmospheric Research, based in Hobart, Tasmania. From 2006 to 2012, he was Vice-Chancellor, Director and Distinguished Professor of Oceanography, at the Scripps Institution of Oceanography at the University of California, San Diego.

He is a Fellow of the Australian Academy of Technological Sciences and Engineering (ATSE) and the Royal Australian Chemical Institute (RACI).

The Australian Institute of Marine Science (AIMS) relies extensively on remotely sensed data to monitor marine ecosystems. These data include imagery, video, hydro acoustic recordings, and satellite observations, collected at spatial and temporal scales that make manual analysis impractical.

This talk reflects on ten years of applying deep learning in an operational marine science context. It will present examples where these approaches have delivered substantial improvements in efficiency and capability, alongside cases where technical, data related, or contextual limitations reduced their effectiveness.

As AI becomes increasingly central to environmental monitoring and reporting, this talk aims to support more transparent, trustworthy, and responsible use of deep learning in the study of a changing marine environment.

While data assimilation is well established in numerical weather prediction, its application in spectral wave models remains limited, particularly in operational forecasting, due to data constraints and computational cost.

This study presents the development and implementation of a computationally efficient data assimilation capability within the open-source third-generation spectral wave model WaveWatch-III.

Results show consistent improvements in significant wave height forecasts, with globally averaged errors reduced by approximately 20% within the first 12 hours.

Our oceans and coasts are at the heart of our economic, social, cultural, and environmental well-being, with more than 85% of Australians living and working in coastal regions. Our marine industries alone currently contribute over $120 billion to Australia’s annual GDP.

Our oceans are changing faster than ever due to climate change and population growth. Coastal erosion, storm surge flooding, marine heatwaves, declining marine water quality, and marine pollution are just some of the challenges already proving costly to society.

At this time of change, our Centre will bring together Australia’s leading oceanography and coastal science communities to deliver the best information and tools available, empowering partners in government, industry and the community to make informed decisions both now and into the future.

The ocean is 361 million square kilometres. Our data covers a small, uneven fraction of it. What we train on shapes what we build, and most maritime AI has been trained on less than 3% of the waters it will eventually operate in.

This presentation introduces the Sparse Ocean Effect: the idea that maritime AI systems do not learn the ocean; they learn the data collected about it.

Most offshore infrastructure either rests on or is tethered to the seabed. To design foundations and anchors efficiently, we need to understand seabed properties, layering, and mechanical behaviour at different depths.

This talk explores how data science combined with field data can help identify likely seabed properties at any location and depth, with quantified uncertainty.

Australia’s Integrated Marine Observing System (IMOS) is a research infrastructure collecting sustained ocean observations throughout coastal and open oceans.

IMOS data are used across coastal, ocean, weather and climate modelling, supporting decision-making in fishing, aquaculture, shipping, oil and gas, offshore energy, maritime safety, defence and resource management.

Earth system models have been used for decades to assess the future state of ocean ecosystems in response to environmental and climate-change-driven pressures.

Several decades of satellite observations now enable machine learning approaches to help constrain projections of phytoplankton response under different emissions scenarios.

Global seasonal and climate forecasts provide valuable large-scale ocean information, but their coarse resolution is insufficient for coastal decision-making.

This talk presents a statistical downscaling framework that efficiently reconstructs high-resolution coastal sea surface temperature fields from coarse-resolution forecasts.

CX Protect is a risk control and decision-making system that combines computer vision, edge computing and AI software to monitor environments and provide real-time alerts for risks to people, property and plant.

This talk will present real-world case studies demonstrating how data-driven technologies can improve safety outcomes, reduce operational risk, and drive cost efficiencies in port and offshore environments.

Academic–industry collaboration in data science offers substantial benefits by combining theoretical rigor with real-world relevance.

However, such collaborations also present challenges including differences in goals, data privacy, intellectual property, confidentiality, mismatched timelines and communication barriers.

ACCESS is Australia’s global climate modelling framework, used for climate projections and by the research community.

As part of building the next-generation ACCESS model, ACCESS-OM3 introduces an ocean-sea ice model with a new coupling framework, improved vertical coordinates, high-resolution options, ice-shelf interaction capability, tides and biogeochemistry.

Measuring sea surface currents directly is challenging. Instead, sea surface currents are often inferred from indirect measurements like altimetry, which generally provide large-scale velocity estimates.

This presentation introduces a statistical inversion model using remotely sensed sea surface temperature data to predict fine-scale sea surface currents, producing predictions and prediction uncertainties.

Artificial Intelligence (AI) is now making substantial and interesting contributions to discovery across a number of scientific fields – from mathematics and physics to geology and biology.

These contributions are based on growing collaboration between scientists and AI practitioners, and the development of new AI techniques that can address the particular challenges of different sciences.

This talk will highlight key areas of science where AI is genuinely having a significant impact on discovery and explore some of the more interesting AI approaches now being applied to such problems.