Modeling of Dynamic Stochastic Systems

Methodological Research

• Data Assimilation: Development in the field of data assimilation focuses on nonparametric Bayesian methods such as particle filtering.
• Modelling using Stochastic Differential Equation: Stochastic differential equations are used to describe many systems with true noise and simplified models. Its application opens for a wide range of tools for model building and selection.
• Model Evaluation: Model evaluation is one of the kernels of the statistical methodology, and is fundamental for model building, hypothesis checking, and for the forecasting application.  

Applied Research

• Statistics in Finance: For more than a decade the section has developed methods for applying statistical methods in mathematical finance. The initative bridges the gap between econometrics and the pure mathematical finance. The section has developed new methods for efficient use of statistics in finance. Our focus have been on methods for modelling financial derivatives using stochastic differential equations.
• Pharmaceutical Modelling: Development of new drugs involves many experiments and including very costly clinical trials. So proper modelling of pharmacokinetics and pharmacodynamics is an important tool increasing the knowledge gain from the experiments.
• Bacterial Growth and Evolution Modelling: The main focus is on using stochastic mathematical modelling to acquire new insights in bacterial life in collaboration with microbiologists.
• Environmental Modelling:
• Population modeling: Our research includes models for spread of disease and tracing animals, e.g. fish.
• Well Field Modelling: The idea is to combine a water distribution model with groundwater model by stochastic dynamic modelling, such that the groundwater model is recalibrated based on available real-time measurements.
• Modelling of Thermal Dynamical Systems: