Jo Eidsvik

Jo Eidsvik is a Professor at the Department of Mathematical Sciences, Norwegian University of Science and Technology (NTNU). He holds a MSc in applied mathematics from the University of Oslo (1997) and a PhD from NTNU (2003). His research focuses on spatio-temporal statistics, computational statistics, and their applications in Earth sciences, including geophysics and oceanography. He leads projects like the Center for Geophysical Forecasting (SFI-CGF) and Maritime Autonomous Sampling and Control (MASCOT). Eidsvik has supervised over 60 graduate students and is an associate editor for *Mathematical Geosciences* and *Statistics and Computing*. His work bridges theory and practice, addressing challenges in data assimilation, value of information analysis, and autonomous systems for environmental monitoring.

**Education & Background**: MSc (University of Oslo), PhD (NTNU). Industry experience includes roles at Statoil and the Norwegian Defense Research Establishment. Visiting scholar at Stanford University, Duke University, and SAMSI.

**Research Themes**: Spatio-temporal modeling, machine learning for irregular time series, and decision analysis in geological contexts. Key projects include geophysical forecasting, CO₂ storage monitoring, and autonomous underwater vehicle (AUV) sampling strategies. His book *Value of Information in the Earth Sciences* (Cambridge Press) synthesizes methodologies for optimizing data-driven decisions.

**Awards & Recognition**: While no specific awards are listed, his editorial roles and project leadership reflect scholarly impact. His work emphasizes interdisciplinary collaboration, with applications in climate science, energy systems, and robotics.

**Advising & Grants**: Supervised 60+ MSc students and 12 PhD students. Active in NTNU’s Physics and Mathematics program and Industrial Mathematics initiatives. Projects funded by SFI, EU, and industry partners.

**Teams & Labs**: Involved with NTNU’s GEOPARD (data assimilation in geological models), Havvarsel (oceanographic data assimilation), and ML4ITS (machine learning for irregular time series). Collaborates with international institutions like Stanford and Duke.