Publications listed on Google Scholar, see CV for full list, '*' indicates student advised
Review articles:
- Sonnewald, M., Brajard, J., Duben, P., Lguensat, R. and Balaji, V.
Bridging theory,
simulation, and observations of the global ocean using Machine Learning,
2021, Environmental Research Letters
- Lai, C.-Y., Hassanzadeh, P., Sheshadri, A., Sonnewald, M., Ferrari R., Balaji, V. Machine learning
for climate physics and simulations, in press, Annual Reviews of Condensed Matter Physics.
- Irrgang, C., Boers, N., Sonnewald, M., Elizabeth A. Barnes, Christopher Kadow,
Staneva, J., and Saynisch-Wagner, J.
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science,
2021, Nature Machine Intelligence
- Bronner, U., Sonnewald, M. and Wisbeck, M., 2023, Marine modelling as the key to sustainable use and protection of
the marine environment. 2023, invited contribution to the centennial edition of The International Hydrographic Review.
Peer reviewed publications:
- Khatri, H., Griffies, S.M., Storer, B.A., Buzzicotti, M., Aluie, H., Sonnewald, M., Dussin,
R. and Shao, A., A scale-dependent analysis of the barotropic vorticity budget in a global ocean
simulation. Journal of Advances in Modeling Earth Systems
- Yik, W.*, Sonnewald, M., Clare, M.*, Lguensat, R., Southern Ocean Dynamics Under Climate Change: New Knowledge Through Physics-Guided Machine Learning. 2023, NeurIPS Climate Change AI workshop..
- Sonnewald, M., Reeve, K., and Lguensat, R., The Southern Ocean supergyre: a unifying dynamical framework identified by machine learning. 2023, Nature Communications Earth & Environment.
- Jones, D., Sonnewald, M., Rosso, I., Zhou, S., and Boehme, L., Unsupervised classification identifies coherent thermohaline structures in the Weddell Gyre. 2023, Ocean Science.
- Clare, M.*, Sonnewald, M., Lguensat, R., Deshayes, J. and Balaji, V., Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics. 2022, Journal of Advances in Modeling Earth Systems.
- Kaiser, B., Saenz, J.A., Sonnewad, M. and Livescu, D., Objective discovery of dominant dynamical processes with machine learning. 2022, Engineering Applications of Artificial Intelligence.
- Krasting, J., M. De Palma, M., Sonnewald, M., J. Dunne, J., and John, J.,
Regional Sensitivity Patterns of Arctic Ocean Acidification Revealed With
Machine Learning. 2022, Nature Communications Earth & Environment.
- Sonnewald, M., and Lguensat, R. Revealing
the impact of global warming on climate modes using transparent machine learning. 2021, Journal of Advances in Modeling Earth Systems
- Sonnewald, M., Lguensat, R., Radhakrishnan, A., Sayibou*, Z., Wittenberg, A.T. and Balaji, V.
Revealing the impact of global
heating on North Atlantic circulation using transparent machine learning. 2021, International Conference on Machine Learning: Spotlight paper at ClimateChangeAI Workshop.
- Sonnewald, M., Dutkiewitz, S., Hill, C. and Forget, G. Elucidating Ecological Complexity: Unsupervised Learning determines global marine eco-provinces, 2020, Science Advances.
- Le Bras, I., Sonnewald, M., Toole, J.M. A Barotropic Vorticity Budget for the Subtropical North Atlantic Based on Observations , 2019, Journal of Physical Oceanography
- Sonnewald, M., Wunsch, C. and Heimbach, P. Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions, 2019, Journal of Earth and Space Science ed. ''Geoscience paper of the future''
Featured on MIT News, Artificial Intelligence Research
- Sonnewald, M., Wunsch, C. and Heimbach, P., 2018. Linear predictability: A sea surface height case study, 2018, Journal of Climate
- Bulczak, A.I., Bacon, S., Naveira Garabato, A.C., Ridout, A., Sonnewald, M., and Laxon, S.W. Seasonal Variability of Sea Surface Height in the Coastal Waters and Deep Basins of the Nordic Seas, 2014, Geophysical Research Letters
- Sonnewald, M., Hirschi, J.J.-M., Marsh, R., McDonagh, E.L. and King, B.A. Atlantic meridional ocean heat transport at 26N: impact on subtropical ocean heat content variability, 2013, Ocean Science
Grey literature:
- Gille, S., Abernathey, R., Chereskin, T., Cornuelle, B., Heimbach, P., Mazloff, M., Menemenlis, D., Rocha, C., Soares, S., Sonnewald. M., Villas Boas, B., Wang, J.
Open Code Policy for NASA Space Science: A perspective from NASA-supported ocean modeling and ocean data analysis, 2018, NASA White Paper
- The ECCO Consortium, A Twenty-Year Dynamical Oceanic Climatology: 1994-2013. Part 1: Active Scalar Fields: Temperature, Salinity, Dynamic Topography, Mixed-Layer Depth, Bottom Pressure, 2017
- The ECCO Consortium, A Twenty-Year Dynamical Oceanic Climatology: 1994-2013. Part 2: Velocities and Property Transports, 2017
Selected publications in review and revision:
- Dräger, S. and Sonnewald, M. . The Importance of Architecture Choice in Deep Learning for Climate Applications. in revision
- Rosenfeld, K., Sonnewald, M., et al. Building understandable messaging for policy and evidence review. in review.
- Sonnewald, M., A hierarchical ensemble manifold methodology for new knowledge on spatial data: An application to ocean physics. In review, JAMES.
- Navarra, G.G*, Sonnewald, M., Deng, Y., Liguori, G. and Di Lorenzo, E. Using Deep Learning to forecast marine fishery indicators in the North Pacific. In review, Global Change Biology.
- Bingham, R. and Sonnewald, M. Stable Atlantic overturning circulation revealed by a dynamically-proximate reconstruction. In revision, Geophysical
Research Letters.
- Sonnewald, M. , Hirschi, J.J.-M., Nurser, A.G., Firing, Y., Coward, A. and Hyder, P. Increasing ocean model resolution reveals impact of tuning eddy permitting models. In revision. Journal of Advances in Modeling Earth Systems
2024
- UC San Diego, Scripps Institute of Oceanography: “Deciphering Southern Ocean Circulation: New Perspectives Through Machine Learning.
- Dynamics Days: “Equations as emergent phenomena determined using ma-
chine learning: An ocean case study.
2023
- UC Davis Atmospheric Science: “Physics-Informed Machine Learning to Push
the Ocean Frontier in Climate”
- UC Davis Applied Mathematics: “Physics-Informed Machine Learning to
Push the Ocean Frontier in Climate”
- CLIVAR Predictability, Predictions, and Applications Interface: “Escaping
'black box' machine learning to increase trust and accelerate discovery”.
- United Nations International Telecommunication Union: “Physics-informed
ML to push the ocean frontier in climate”.
- University of Toronto Nobel Seminar Series: “Elucidating driving mecha-
nisms in the North Atlantic and Southern Ocean dynamics: Physics-informed
and trustworthy ML for ocean science”
- University of Liege 54th international Liege colloquium on ocean dynamics
- UCLouvain: “Physics-informed machine learning to push the ocean frontier
in climate: A Southern Ocean case study”
- Institut Pierre-Simon Laplace - Sciences du climat (IPSL): “Physics-
informed machine learning to push the ocean frontier in climate: A Southern
Ocean case study.
- University of Miami: “Elucidating Driving Mechanisms in North Atlantic
and Southern Ocean Dynamics: Physics-Informed and Trustworthy Machine
Learning for Ocean Science”.
- UC Davis Computer Science: “Physics-informed and trustworthy computation for climate resilience
- Sorbonne University: “Elucidating Driving Mechanisms in North Atlantic
and Southern Ocean Dynamics: Physics-Informed and Trustworthy Machine
Learning for Ocean Science
2022
- CLIVAR Physical Oceanography: “A supergyre in the Southern Ocean modulates the global overturning: insight guided by interpretable machine learning
- Climate Informatics: “Asking how the Southern Ocean responds to global
heating and understanding why the answer emerged.”
- U. Cambridge: “Intelligent solutions to monitor ocean health.
- SIAM Mathematics of Data Science: “Developing and Learning from
Trust in Machine Learning".
- SIAM Geosciences Webinar Series: “Understanding the Ocean’s response
in a Future Climate".
- Max Planck Institute for Meteorology: “The response of the ocean’s overturning to global warming: A robust blueprint for trustworthy AI for climate
analysis”
- Institute for Mathematical and Statistical Innovation (IMSI) at U.
Chicago: “Elucidating drivers of Southern Ocean circulation change: A
blueprint for interpretable and explainable machine learning”
- MIT Earth Atmosphere and Planetary Science:“Intelligent solutions to monitor and predict ocean health”
- MIT Mechanical Engineering: “Intelligent solutions to monitor and predict
ocean health”
- UC Berkeley: “Data driven understanding of ocean systems”
- University of Liege: “Intelligent solutions to monitor and predict ocean
health”
- U. Wisconsin-Madison: “Revealing the impact of climate change on North
Atlantic circulation using transparent machine learning”
- U. Rhode Island: “Revealing the impact of climate change on North Atlantic
circulation using transparent machine learning”
2021
- American Geophysical Union (AGU): “Revealing the impact of climate
change on North Atlantic circulation using transparent machine learning”.
- Deptartment of Energy AI workshop: “Ocean Grand Challenges.
- Climate Change AI webinar: “A robust blueprint for trustworthy AI for
climate analysis”
- NOAA, AI workshop: “Revealing the impact of climate change on North
Atlantic circulation using transparent machine learning”.
- US National Center for Atmospheric Research CGD Series: “Reveal-
ing mechanisms of change in the Atlantic Meridional Overturning Circulation
under global heating”
- KITP ML for Climate Physics: “Revealing the Impact of Global Heating on the
Meridional Overturning Circulation with transparent machine learning
- IMSI U. Chicago: Elucidating ecological complexity: Unsupervised learning
determines global marine eco-provinces
- GEOMAR Helmholtz Centre for Ocean Research: “Solutions
to understand and monitor the ocean and climate"
- Summit for Incorporating Data Science and Open Science in Aquatic
Research: “Understanding the ocean’s response in a future climate: A robust
blueprint for trustworthy AI for climate analysis”
- International Conference on Machine Learning: “Revealing the impact
of global warming on climate modes using transparent machine learning”
- UC Santa Cruz: “Revealing the impact of global warming on ocean circulation: A robust blueprint for trustworthy AI for climate analysis”
- Scripps Institute of Oceanography “Revealing the Impact of Global Heating on the Meridional Overturning Circulation
- Potsdam Institute for Climate Impact: “Revealing the Impact of Global
Heating on the Meridional Overturning Circulation”
- Technical U. Munich: “Revealing the Impact of Global Heating on the
Meridional Overturning Circulation”
- U. Washington: “Revealing the Impact of Global Heating on the Meridional
Overturning Circulation”
2020
- Second NOAA Workshop on Leveraging AI in the Environmental
Sciences, “Elucidating Ecological Complexity: Unsupervised Learning determines global marine eco-provinces”
- Los Alamos National Laboratory, “Living on the Manifold: A geography
of ocean dynamical regimes from eddy to global scale
- U. Washington Department of Mechanical Engineering, “Living on the Manifold: A geography of ocean dynamical regimes from eddy to global scale”
- U. Washington, Department of Ocean Sciences, “Living on the Manifold: A
geography of ocean dynamical regimes from eddy to global scale”
- U. Washington, “Elucidating Ecological Complexity: Unsupervised Learning
determines global marine eco-provinces”
- U. British Columbia, “Ocean exploration with machine learning: An Antidote to Chaos?"
2019
- AGU: “Unsupervised Learning Reveals Geography of Global Ocean Dynamical
Regions”
- U. Bergen, “Ocean exploration with machine learning: An Antidote to
Chaos?”
- Princeton University, “Ocean exploration with machine learning: An Antidote to Chaos?”
- Norway-US bilateral AI workshop, “Elucidating ocean ecological complexity”
- Norway-US bilateral AI workshop, “Recognising ocean physical regimes”
- Woods Hole Oceanographic Institute: “Ocean exploration with machine
learning: An Antidote to Chaos?”
- U. Tromsø (Nor.): “Ocean exploration with machine learning: An Antidote
to Chaos?”
Others before 2019:: Yale University, WHOI, U. Texas at Austin, Oregon State University, U. Bristol, NOCS, MONCACO meeting, Stony Brook University, Columbia University, MIT, U. Oxford.