Home
Kristian Gundersen's picture
Photo:
Mette Gundersen

Kristian Gundersen

Postdoctoral Fellow
  • E-mailkristian.gundersen@uib.no
  • Phone+47 55 58 26 86
  • Visitor Address
    Allégaten 41
    Realfagbygget
    5007 Bergen
  • Postal Address
    Postboks 7803
    5020 Bergen

Statistics

Academic article
  • Show author(s) (2021). Semi-conditional variational auto-encoder for flow reconstruction and uncertainty quantification from limited observations. Physics of Fluids. 23 pages.
  • Show author(s) (2020). Binary time series classification with Bayesian convolutional neural networks when monitoring for marine gas discharges . Algorithms. 24 pages.
Report
  • Show author(s) (2019). Underpinning data for monitoring activities (including current statistics and carbon tracer quantifications). .
Academic lecture
  • Show author(s) (2019). Bayesian convolutional neural networks as a tool to detect discharges of pollutants to marine waters through time series classification.
  • Show author(s) (2018). The need for proper environmental statistics to design adequate monitoring for offshore geological storage of CO2 projects.
  • Show author(s) (2018). Machine Learning in CO2 leak detection.
  • Show author(s) (2018). Ensuring efficient and robust offshore storage – the role of marine system modelling.
  • Show author(s) (2018). Combining Models and Machine Learning Techniques to Design Leak Detection Monitoring .
  • Show author(s) (2018). Combining Environmental Statistics and Marine Process Modelling to Design Monitoring Programs for Offshore CO2 Storage.
Doctoral dissertation
  • Show author(s) (2021). Bayesian Variational Methods in Carbon Storage Monitoring.
Poster
  • Show author(s) (2020). Reconstruction of Currents Based on Sparse Observations with Deep Learning.
  • Show author(s) (2019). Ensuring efficient and robust carbon storage: marine modelling for environmental monitoring.
  • Show author(s) (2018). Model Reduction for Tracer Transport and Applications.
  • Show author(s) (2018). Mathematical methods for detection and localization of CO2 leaks.
  • Show author(s) (2017). Bayes’ theorem as the fundament to design monitoring programs.
  • Show author(s) (2017). Assessment of machine learning methods as a tool in detecting leakages.
  • Show author(s) (2017). Assessment of Topological Data Analysis and Machine Learning Technologies as Tools for Seep Detection.
Article in business/trade/industry journal
  • Show author(s) (2020). Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations. arXiv.

More information in national current research information system (CRIStin)