For more complete publication list of Prof. Sonnewald including review articles and white papers see her personal site or Google Scholar.

Journal Articles

  1. 1 Lai C-Y, Hassanzadeh P, Sheshadri A, Sonnewald M, Ferrari R, Balaji V. Machine learning for climate physics and simulations. 2024. doi:10.48550/arXiv.2404.13227.
  2. 2 Dräger S, Sonnewald M. The Importance of Architecture Choice in Deep Learning for Climate Applications. 2024. doi:10.48550/arXiv.2402.13979.
  3. 3 Sonnewald M, Reeve KA, Lguensat R. A Southern Ocean supergyre as a unifying dynamical framework identified by physics-informed machine learning. Communications Earth and Environment 2023; 4: 153.
  4. 4 Jones DC, Sonnewald M, Zhou S, Hausmann U, Meijers AJS, Rosso I et al. Unsupervised classification identifies coherent thermohaline structures in the Weddell Gyre region. Ocean Science 2023; 19: 857–885.
  5. 5 Yik W, Sonnewald M, Clare MCA, Lguensat R. Southern Ocean Dynamics Under Climate Change: New Knowledge Through Physics-Guided Machine Learning. 2023. doi:10.48550/arXiv.2310.13916.
  6. 6 Krasting JP, De Palma M, Sonnewald M, Dunne JP, John JG. Regional sensitivity patterns of Arctic Ocean acidification revealed with machine learning. Communications Earth and Environment 2022; 3: 91.
  7. 7 Clare MCA, Sonnewald M, Lguensat R, Deshayes J, Balaji V. Explainable Artificial Intelligence for Bayesian Neural Networks: Toward Trustworthy Predictions of Ocean Dynamics. Journal of Advances in Modeling Earth Systems 2022; 14: e2022MS003162.
  8. 8 Kaiser BE, Saenz JA, Sonnewald M, Livescu D. Automated identification of dominant physical processes. Engineering Applications of Artificial Intelligence 2022; 116: 105496.
  9. 9 Sonnewald M, Lguensat R. Revealing the Impact of Global Heating on North Atlantic Circulation Using Transparent Machine Learning. Journal of Advances in Modeling Earth Systems 2021; 13: e2021MS002496.
  10. 10 Sonnewald M, Lguensat R, Jones DC, Dueben PD, Brajard J, Balaji V. Bridging observations, theory and numerical simulation of the ocean using machine learning. Environmental Research Letters 2021; 16: 073008.
  11. 11 Irrgang C, Boers N, Sonnewald M, Barnes EA, Kadow C, Staneva J et al. Will Artificial Intelligence supersede Earth System and Climate Models? arXiv e-prints 2021; : arXiv:2101.09126.
  12. 12 Sonnewald M, Dutkiewicz S, Hill C, Forget G. Elucidating ecological complexity: Unsupervised learning determines global marine eco-provinces. Science Advances 2020; 6: eaay4740.
  13. 13 Alexander-Astiz Le Bras I, Sonnewald M, Toole JM. A Barotropic Vorticity Budget for the Subtropical North Atlantic Based on Observations. Journal of Physical Oceanography 2019; 49: 2781–2797.
  14. 14 Sonnewald M, Wunsch C, Heimbach P. Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions. Earth and Space Science 2019; 6: 784–794.

Conferences and Workshops

  1. 1 Sonnewald M, Reeve KA, Lguensat R. The Southern Ocean supergyre: a unifyingdynamical framework identified by machinelearning. In: EGU General Assembly Conference Abstracts. 2023, pp EGU-10304.
  2. 2 Sonnewald M. A quasi-circumpolar super gyre modulates the global overturning through upwelling in the Southern Ocean. In: AGU Fall Meeting Abstracts. 2022, pp OS32B–1017.
  3. 3 Lessig C, Luise I, Sonnewald M, Subramanian A, Schultz M. AtmoRep: Representation Learning for Spatio-Temporal Data in the Earth Sciences. In: AGU Fall Meeting Abstracts. 2022, pp GC21C–04.
  4. 4 Jones D, Sonnewald M, Rosso I, Zhou S, Boehme L. Unsupervised classification identifies coherent thermohaline structures in the Weddell Gyre. In: EGU General Assembly Conference Abstracts. 2022, pp EGU22–10528.
  5. 5 Jones D, Zhou S, Sonnewald M, Rosso I, Boehme L. Unsupervised classification identifies coherent thermohaline structures in the Weddell Gyre. In: AGU Fall Meeting Abstracts. 2021, pp OS15D–1016.
  6. 6 Sonnewald M, Dutkiewicz S, Hill C, Forget G. Elucidating ecological complexity: Unsupervised learning determines global marine eco-provinces. In: AGU Fall Meeting Abstracts. 2021, pp GC41A–08.
  7. 7 Sonnewald M, Lguensat R. Revealing the impact of climate change on North Atlantic circulation using transparent machine learning. In: AGU Fall Meeting Abstracts. 2021, pp A14C–06.
  8. 8 Sayibou Z, Sonnewald M, Radhakrishnan A, Wittenberg A, Lguensat R, Balaji V. Linking ENSO to Oceanic Dynamical Regimes using Transparent Machine Learning. In: AGU Fall Meeting Abstracts. 2021, pp A14C–02.
  9. 9 Sonnewald M, Lguensat R, Balaji V. Revealing mechanisms of change in the Atlantic Meridional Overturning Circulation under global heating. In: EGU General Assembly Conference Abstracts. 2021, pp EGU21–6321.
  10. 10 Kaiser B, Saenz J, Sonnewald M, Livescu D. Objective discovery of fluid dynamical regimes with unsupervised machine learning. In: APS Division of Fluid Dynamics Meeting Abstracts. 2021, p H31.009.
  11. 11 Sonnewald M. Inferring mechanisms of ocean circulation change in CMIP models using deep learning. In: AGU Fall Meeting Abstracts. 2020, pp A040–0008.
  12. 12 Sonnewald M, Nurser AJG, Firing Y, Hirschi J, Coward A, Hyder P. Increasing ocean model resolution reveals impact of tuning eddy permitting models. In: AGU Fall Meeting Abstracts. 2019, pp PP13B–1436.
  13. 13 Sonnewald M, Wunsch C, Heimbach P. Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions. In: AGU Fall Meeting Abstracts. 2019, pp A43E–01.
  14. 14 Sonnewald M, Wunsch C, Heimbach P. Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions. In: EGU General Assembly Conference Abstracts. 2019, p 15646.

Prof. Sonnewald invited talks (selected)

2024 (Total: 5)

Symposium: The Role of Federal Fishery Disaster Assistance in a Climate Change-Driven World

CoE Dean’s Executive Committee

2023 (Total: 17)

AI for Good by the United Nations’ International Telecommunication Union

University of Toronto, Nobel Seminar Series

Others: U. Miami, UC Davis, U. Liege

2022 (Total: 14)

CLIVAR, Physical Oceanography review panel.

NOAA GFDL HQ site review, Discovering and using ocean regimes at GFDL.

Climate Informatics, Asking how the Southern Ocean responds to global heating and understanding why the answer emerged.

SIAM Geoscience, Understanding the ocean’s response in a future climate.

U. Cambridge, Environmental Data Science Group, Intelligent solutions to monitor ocean health.

Others: SIAM DS, U. Wisconsin-Madison, Max Planck Institute for Meteorology, UC Berkeley, MIT for EAPS and Mechanical Engineering, U. Rhode Island, IMSI, U. Chicago.

2021 (Total: 14)

AGU, Revealing the impact of climate change on North Atlantic circulation using ML.

Dept of Energy, workshop, Requested topic: Ocean Grand Challenges: Using AI/ML to push the frontiers.

Climate Change AI, A robust blueprint for trustworthy AI for climate analysis.

NOAA, workshop, Revealing the impact of global warming on climate modes using transparent machine learning and a suite of climate models.

Others: KITP, Scripps Institute of Oceanography, U. Washington, U. Chicago, International Conference on Machine Learning, Summit: Incorporating Data Science and Open Science in Aquatic Research, University Corporation for Atmospheric Research (UCAR), U. California, Santa Cruz, GEOMAR Helmholtz Centre for Ocean Research, Technical U. Munich, Potsdam Institute for Climate Impact.

2022 (Total: 7)

Second NOAA Workshop on Leveraging AI in the Environmental Sciences, Elucidating Ecological Complexity: Unsupervised Learning determines global marine eco-provinces.

NOAA Senior Management Meeting, Oceanic and Atmospheric Research, Building geographies of ocean dynamical regimes.

Others: Los Alamos National Laboratory, U. Washington, U. Washington, U. British Columbia, NOAA, workshop, U. Washington.

2019 (Total: 7)

AGU, The case for machine learning in geoscience.

Norway-US bilateral AI workshop, Elucidating Ecological Complexity.

Others: Princeton University, Norway-US bilateral AI workshop, WHOI, U. Troms&oe, U. Bergen.

2012-2018 (Total: 17)

WHOI, Unsupervised learning classifies global ocean dynamical regions.

Columbia University, LDEO, Linear predictability: A sea surface height case study.

Yale University, Ocean model utility dependence on horizontal resolution.

Others: MIT, (2018 & 2015), Stony Brook University, U. Texas at Austin, U. Washington, Oregon State University, U. Oxford, MIT, U. Bristol, NOCS, (2015, 2014 & 2013) and MONCACO meeting.