CloseHelpPrint
Kies de Nederlandse taal
Course module: 202100108
202100108
Uncertainty Quantification & Data-driven Modeling
Course infoSchedule
Course module202100108
Credits (ECTS)5
Course typeCourse
Language of instructionEnglish
Contact persondr. M. Guo
E-mailm.guo@utwente.nl
Lecturer(s)
Contactperson for the course
dr. M. Guo
Examiner
dr. M. Guo
Academic year2021
Starting block
2A
Application procedureYou apply via OSIRIS Student
Registration using OSIRISYes
Aims
After following this course, the student is able to
  • numerically solve elliptic PDEs with random parameters (Forward problems)
  • infer system parameters via Bayesian approaches (Inverse problems)
  • use sampling techniques to estimate characteristic outputs of interest (Uncertainty propagation)
  • build data-driven surrogate models for multi-query simulations (Acceleration)
  • quantify uncertainties in the research of their own discipline (Interdisciplinary understanding)
Content
Uncertainty quantification aims at the synthesis of probability, statistics, model development, mathematical and numerical analysis, large-scale simulations, experiments, and domain sciences to provide a computational framework for quantifying input and response uncertainties in a manner that facilitates predictions with quantified and reduced uncertainty. More recently, data-driven modeling benefits from the powerful tools of machine learning and provides brand new perspectives for physics-based simulation science, which lays the foundation of physics-informed machine learning.

In this course, we will discuss both the forward propagation of uncertainties from inputs to responses and the inverse estimation of system parameters through Bayesian frameworks. For the speed-up of multi-query simulations that are required by uncertainty quantification, major surrogate modeling techniques will be introduced as well. This course covers the basics of uncertainty quantification and is also closely connected to the research frontier of computational science. With the aid of this course, the students are expected to acquire
competence to independently solve uncertainty quantification problems in their own research disciplines.

Main topics include:
  • Fundamentals of probability and statistics
  • Numerical discretization for PDEs with random parameters
  • Sampling techniques: Monte Carlo, importance sampling, and subset simulation
  • Bayesian inference and its applications
  • Gaussian processes for surrogate modeling
  • Basics of projection-based reduced order modeling
  • Multi-fidelity surrogate modeling
Assessment
Oral Exam (65%) and Final Project Report (35%)

Assumed previous knowledge

Required: 
  • Solid knowledge in
    • linear algebra, e.g., via AM module 1 202001325, CS module 3 202001205, BMT module 3 202001203, EE module 4 202001209, ME module 4 202001210, or their equivalent,
    • vector calculus. e.g., via AM module 3 202001229, BMT module 5 202001225, EE module 3 202001231, ME module 5 202001228, or their equivalent, and
    • probability theory, e.g., via AM module 4 202001344, CS module 4 202001233, EE module 8 202001235, or their equivalent.
  • Programming experience in Matlab or Python.
  • Working knowledge of numerical analysis, e.g., via Numerical Mathematics (202001356) or its equivalent.
Recommended
  • Knowledge of machine learning, e.g., via Machine Learning I (201600070) or Deep learning – From Theory to Practice (201800177).
  • Knowledge of numerical methods for PDEs, e.g., via Numerical Techniques for PDE (191551150) or Fundamentals of Numerical Methods (201900074).
Participating study
Master Applied Mathematics
Participating study
Master Biomedical Engineering
Participating study
Master Computer Science
Participating study
Master Electrical Engineering
Participating study
Master Mechanical Engineering
Participating study
Master Nanotechnology
Participating study
Master Technical Medicine
Required materials
Handouts
Lecture notes, available digitally.
Recommended materials
Book
Uncertainty Quantification: Theory, Implementation, and Applications - R.C. Smith. ISBN 9781611973211
Book
Gaussian Processes for Machine Learning - C.E. Rasmussen and C. Williams. ISBN 9780262182539.
Book
Reduced Basis Methods for Partial Differential Equations: An Introduction - A. Quarteroni, A. Manzoni and N. Federico. ISBN 9783319154305
Instructional modes
Lecture

Project unsupervised

Q&A

Tutorial

Tests
Oral Exam, Final Project Report

CloseHelpPrint
Kies de Nederlandse taal