Skip to content

GitHub: maikejulie

Maike Sonnewald

      Developing pathways between theoretical, observational and computational oceanography






Associate Research Scholar at Princeton University and GFDL

Modern oceanography is interdisciplinary: the field is becoming data rich from observations and models, creating a need for new tools. I am a physical oceanographer using computer science/dynamical systems tools to explore decadal ocean dynamics. Passionate about bringing together different branches of oceanography, my goal is to discover the underlying principles that govern ocean dynamics from small to global scales. My work connects to observational efforts and model parameterizations, and I also work on ocean acidification and ecology in collaborative efforts. I focus on the global ocean, using scalable methods, with a special interest in the Southern Ocean and the North Atlantic.


I currently focus on understanding how small scale dynamics impact global features like heat transport in simulations allowing mesoscale turbulence. This work continues the development of the SAGE (Systematic AGgregated Eco-province) method, combining statistical tools, unsupervised machine learning and graphs, designed to work with non-linear data ubiquitous in oceanography and beyond. Overall, my research areas include:

  • Discovery of coherent regions in ocean dynamics, ecological and acidification
  • Vorticity dynamics
  • Predictability of Sea Level
  • Small scale interactions with bathymetry
  • Machine learning applications
  • Application of dynamical systems theory


My work using unsupervised machine learning to discover ocean dynamical regimes was featured on: MIT News, Artificial Intelligence Research,, and ECN magazine.