Name: SAMM 2020: Learning Models from Data
Start: 2020-07-27T13:30:00+02:00
End: 2020-07-31T19:45:00+02:00
Location: Virtual event

SAMM 2020: Learning Models from Data

from Monday, July 27, 2020 (1:30 PM) to Friday, July 31, 2020 (7:45 PM)

Monday, July 27, 2020

1:40 PM Opening
Opening
1:40 PM - 2:00 PM
2:00 PM Lecture/exercises 1 - Feliks Nüske (Paderborn University)
Lecture/exercises 1
- Feliks Nüske (Paderborn University)
2:00 PM - 3:30 PM
Introduction to Stochastic Dynamics and Transition Operators - Markov Property and Transition Kernels - Perron-Frobenius and Koopman Operator - Examples (ODEs, Brownian Motion) - Stationarity, Reversibility
4:00 PM Lecture/exercises 1 - Benjamin Peherstorfer (New York University)
Lecture/exercises 1
- Benjamin Peherstorfer (New York University)
4:00 PM - 5:30 PM
Introduction to traditional (intrusive, projection-based) model reduction - POD/PCA, greedy - Galerkin ROMs - DEIM
6:00 PM Lecture/exercises 1 - J. Nathan Kutz (University of Washington)
Lecture/exercises 1
- J. Nathan Kutz (University of Washington)
6:00 PM - 7:30 PM
Introduction to data-driven modeling - DMD - Koopman - Time-delay embeddings (HAVOK)
7:30 PM
7:30 PM - 8:30 PM
Contributions

7:30 PM Optimizing Intense Laser-Plasma Interactions with Evolutionary Algorithms and Machine Learning - Joseph Smith (The Ohio State University)

7:30 PM Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks - Colby Wight (PNNL)

7:30 PM Learning Constitutive Relations using Symmetric Positive Definite Neural Networks - Kailai Xu (Stanford University)

7:30 PM Nonlinear model reduction for one-dimensional solidification process in additive manufacturing - Parisa Khodabakhshi (Oden Institute for Computational Engineering and Sciences, UT Austin)

7:30 PM Analysis of bubble dynamics using data-driven dynamical systems and machine learning - Andrew J. Gibson (Department of Mechanical and Aerospace Engineering, University of Colorado Colorado Springs)

7:30 PM Analyzing the Transition to Buffeting of a 2D Airfoil using the Dynamic Mode Decomposition - Sathsara Dias (Clarkson University)

7:30 PM Discovering the governing PDE of an active nematic system from video data - Connor Robertson (New Jersey Institute of Technology)

7:30 PM Extrapolating Nuclear Masses using Bayesian Gaussian Process Regression - Rahul Jain (Michigan State University )

7:30 PM System Identification by Sparse Bayesian Learning - Luning Sun (University of Notre Dame)

7:30 PM Machine learning for parameters identification in structural joints models - Simone Gallas (KU Leuven, Department of Mechanical Engineering, Division LMSD; Core Lab DMMS-D, Flanders Make)

7:30 PM Analytical and Learning Model of a Hybrid-Fluidic Elastomer Actuator for Reliable Control and Perturbation Detection - Uksang Yoo (The University of Texas at Austin)

7:30 PM An optimization-based approach for the reduction of parametrized conservation laws with discontinuities - Marzieh Alireza Mirhoseini (University of Notre Dame)

7:30 PM Analytical Modeling and Evaluation of Curvature-Dependent Distributed Friction Force in Tendon-Driven Continuum Manipulators - Yang Liu (The University of Texas at Austin)

7:30 PM Learning the Interfacial Area Equation from Data - Stephen Chen (University of California San Diego)

7:30 PM Analytical and Data-driven Models to Predict Algae Biofilm Growth in Water Treatment - Gerald Jones (Utah State University)

7:30 PM PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parametric PDEs on Irregular Domain - Han Gao (University Of Notre Dame)

7:30 PM MUQ-hIPPYlib: A Bayesian Inference Software Framework Integrating Data with Complex Predictive Models under Uncertainty - Ki-Tae Kim (University of California, Merced)

7:30 PM Learning age-related chronic disease progression from cognitive measurements - Cindy Catherine Orozco Bohorquez (Stanford University)

7:30 PM Modulus-based iterative methods for constrained $\ell_p$-$\ell_q$ minimization - Mirjeta Pasha (Arizona State University)

7:30 PM A function space random feature model for PDE solution maps - Nicholas H. Nelsen (Caltech)

7:30 PM Weak SINDy: Galerkin-Based Data-Driven Model Selection - Daniel Messenger (University of Colorado Boulder)
Tuesday, July 28, 2020
2:00 PM Lecture/exercises 2 - Feliks Nüske (Paderborn University)
Lecture/exercises 2
- Feliks Nüske (Paderborn University)
2:00 PM - 3:30 PM
Stochastic Calculus - Stochastic Integral and SDEs - Ito’s Formula - The Generator of an SDE - Examples
4:00 PM Lecture/exercises 2 - Benjamin Peherstorfer (New York University)
Lecture/exercises 2
- Benjamin Peherstorfer (New York University)
4:00 PM - 5:30 PM
- Intrusive ROMs: Error bounds: residual-based; offline-online splitting - Recovering reduced models from data with operator inference (re-projection) and relation to DMD
6:00 PM Lecture/exercises 2 - J. Nathan Kutz (University of Washington)
Lecture/exercises 2
- J. Nathan Kutz (University of Washington)
6:00 PM - 7:30 PM
Introduction to DMD/Koopman for ROMs data-driven modeling - DMD integration into Galerkin ROMs - Koopman/DMD models for ROMs
7:30 PM Social event
Social event
7:30 PM - 8:30 PM
Wednesday, July 29, 2020
2:00 PM Lecture/exercises 3 - Feliks Nüske (Paderborn University)
Lecture/exercises 3
- Feliks Nüske (Paderborn University)
2:00 PM - 3:30 PM
(E)DMD for Stochastic Dynamics - Basic EDMD - Variational Principle for Reversible Dynamics - Generator EDMD
4:00 PM Lecture/exercises 3 - Benjamin Peherstorfer (New York University)
Lecture/exercises 3
- Benjamin Peherstorfer (New York University)
4:00 PM - 5:30 PM
- Operator inference (non-Markovian terms for partial observations) - Probabilistic generalization bounds in limited situations for operator inference
6:00 PM Lecture/exercises 3 - J. Nathan Kutz (University of Washington)
Lecture/exercises 3
- J. Nathan Kutz (University of Washington)
6:00 PM - 7:30 PM
Introduction to neural networks for DMD & Koopman approximations - NN for learning coordinate transformations - Koopman reductions more linear ROMs
7:30 PM
7:30 PM - 8:30 PM
Contributions

7:30 PM One size does not fit all: Parameterized biomechanical models for crashworthiness simulations - Göktürk Kuru (Siemens Digital Industries Software)

7:30 PM Wavelet based dynamic mode decomposition - Manu Krishnan (PhD Candidate, Department of Aerospace and Ocean Engineering, Virginia Tech)

7:30 PM Adaptive Interpolatory MOR by Learning the Error Estimator in the Parameter Domain - Sridhar Chellappa (Max Planck Institute for Dynamics of Complex Technical Systems)

7:30 PM Sensor selection for hyper-parameterized linear Bayesian inverse problems - Nicole Aretz-Nellesen (RWTH Aachen)

7:30 PM Data-Driven Identification and Reduction of Dynamical Systems with the Loewner Framework - Dimitrios S. Karachalios (MPI-DRI)

7:30 PM Artificial neural network for bifurcating phenomena modelled by nonlinear parametrized PDEs - Federico Pichi (SISSA, International School for Advanced Studies)

7:30 PM Learning from Data for Traffic Control - Urs Baumgart (Fraunhofer ITWM)

7:30 PM Multipopulation mortality rates modelling and forecasting: The multivariate functional principal component analysis approach - Ka Kin Lam (University of Leicester)

7:30 PM Deep learning of multibody minimal coordinates for estimation - Andrea Angeli (KU Leuven, Flanders Make)

7:30 PM A Hamiltonian Monte Carlo Bayesian Inference Approach Using Deep Learning for Modeling Metabolism - Christina Schenk (Basque Center for Applied Mathematics)

7:30 PM Real-time virtual acoustics using physics-informed data-driven techniques - Finnur Pind (Technical University of Denmark)

7:30 PM Machine learning for parameter identification and model reduction of gradient-enhanced damage models for metal forming processes - Robin Schulte (Institute of Mechanics, TU Dortmund University)

7:30 PM Model adaptation for hyperbolic balance laws employing constraint aware neural networks - Hrishikesh Joshi (Technical University of Darmstadt)

7:30 PM Towards Deep Learning Based Controllers with Nominal Closed Loop Stability Guarantees - Hoang Hai Nguyen (Otto-von-Guericke University Magdeburg, Magdeburg, Germany)

7:30 PM Convolutional Neural Networks for object detection in professional appliances - Laura Meneghetti (SISSA)

7:30 PM Kernel-based Active Subspaces with application to CFD problems using Discontinuous Galerkin method - Francesco Romor (SISSA)

7:30 PM Deep Neural Networks for Hyperbolic Conservation laws with Non-convex Flux - Hadi Minbashian (Technical University of Darmstadt)

7:30 PM Data-driven reduced-order modeling from noisy measurements: new results and future perspectives - Ion Victor Gosea (MPI Magdeburg)

7:30 PM Prediction-Based Nature-Inspired Dynamic Optimization - Almuth Meier (SCHOTT AG)

7:30 PM Reduced order modelling for data assimilation in parametrized optimal control framework - Maria Strazzullo (SISSA, mathLab)

7:30 PM Fusing Online Gaussian Process-Based Learning and Control for Scanning Quantum Dot Microscopy - Maik Pfefferkorn (Otto-von-Guericke University Magdeburg)

7:30 PM Data-driven metamodelling in Global Sensitivity Analysis - Panagiotis Demis (Department of Chemical and Process Engineering, University of Surrey)
Thursday, July 30, 2020
1:00 PM
1:00 PM - 2:00 PM
Contributions

1:00 PM Deep learning based model reduction approaches in flow models - Yiran Wang (The Chinese University of Hong Kong)

1:00 PM The use of machine learning in Computational Fluid Dynamics for an economic approach to flow optimization problems. - Georg Schatzdorfer (TU Graz)

1:00 PM Deep learning of superstructures in turbulence - Manuel Schaller (TU Ilmenau) Friedrich Philipp (TU Ilmenau) Mitsuru Wilson (TU Ilmenau)

1:00 PM The Construction and Application of Surrogate Models for Sensitivity Analysis - Xifu Sun (Australian National University)

1:00 PM Data-based soil-tool interaction force prediction based on measurements and the Discrete Element Method - Jonathan Jahnke (Fraunhofer ITWM)

1:00 PM Machine Learning Algorithms for Learning Nonlinear Terms of Reduced Mechanical Models in Explicit Structural Dynamics - Jonas Kneifl (Institute of Engineering and Computational Mechanics)

1:00 PM Basis Generation Techniques for Symplectic Model Order Reduction - Patrick Buchfink (University of Stuttgart)

1:00 PM Physics Guided Deep-Learning Based Nonlinear Reduced Order Model for Aeroelastic Applications - Rahul Halder (National University of Singapore)

1:00 PM Enhancing battery recharge performance by combined Machine Learning and PDE modelling - Angela Monti (University of Salento)

1:00 PM Stochastic frequency domain surrogate models for linear structural dynamics - Felix Schneider (Technical University of Munich)

1:00 PM Data-driven Reduced Order Model of Flow-Induced Piezoelectric Energy Harvesters - Lan Shang (University of Luxembourg)

1:00 PM Data-Driven Learning of Reduced-Order Dynamics for a Parametrized Shallow Water Equation - Süleyman Yildiz (Institute of Applied Mathematics, Middle East Technical University, Ankara, Turkey)

1:00 PM Deep Kernel approaches with a Neural-Network-like structure - Tizian Wenzel (University of Stuttgart)

1:00 PM Chance-constrained optimal control of hyperbolic supply systems - Kerstin Lux (Technical University of Munich)

1:00 PM Stochastic Grey-box Model of the Flow-Front Dynamics - Rishi Relan (Siemens Energy, Technical University of Denmark, BML Munjal University)

1:00 PM Data-driven computational continuum mechanics - Vu Chau (University of Luxembourg )

1:00 PM Quantifying incompressible two-phase flow fields from the interface movement using physics-informed neural networks - Aaron Buhendwa (Technical University Munich, Chair of Aerodynamics and Fluid mechanics)

1:00 PM A data-driven physics-informed finite-volume scheme for nonclassical undercompressive shocks - Deniz A Bezgin (Technical University of Munich)

1:00 PM Model Reduction for Advection Dominated Problems - Davide Torlo (University of Zurich)

1:00 PM Data-based Approach for Fault Diagnosis of Hydropower Rotors - Christian Sperber (Voith Hydro Holding GmbH & Co. KG)

1:00 PM Insights into squealing disk brakes through explainable machine learning for time series data - Merten Stender (Hamburg University of Technology)

1:00 PM Can machine learning methods be used to create parametrized reduced models of vibro-acoustic systems? - Quirin Aumann (Technical University of Munich, Chair of Structural Mechanics)
2:00 PM Lecture/exercises 4 - Feliks Nüske (Paderborn University)
Lecture/exercises 4
- Feliks Nüske (Paderborn University)
2:00 PM - 3:30 PM
Introduction to Kernel Methods for Data Driven Modeling - Kernel-based EDMD and Generator EDMD
4:00 PM Lecture/exercises 4 - Benjamin Peherstorfer (New York University)
Lecture/exercises 4
- Benjamin Peherstorfer (New York University)
4:00 PM - 5:30 PM
- Interpolatory model reduction: transfer function, H2 norm, Loewner - Learning in the frequency domain: Loewner noise, AAA, vector fitting
5:30 PM Virtual group photo
Virtual group photo
5:30 PM - 5:35 PM
6:00 PM Lecture/exercises 4 - J. Nathan Kutz (University of Washington)
Lecture/exercises 4
- J. Nathan Kutz (University of Washington)
6:00 PM - 7:30 PM
Introduction to data-driven learning of physics models - The SINDy method - PDE-FIND - ROMs with SINDy
Friday, July 31, 2020
2:00 PM Lecture/exercises 5 - Feliks Nüske (Paderborn University)
Lecture/exercises 5
- Feliks Nüske (Paderborn University)
2:00 PM - 3:30 PM
Coarse Graining for SDEs - Effective Dynamics - Reduced Generator - Parameter Estimation
4:00 PM Lecture/exercises 5 - Benjamin Peherstorfer (New York University)
Lecture/exercises 5
- Benjamin Peherstorfer (New York University)
4:00 PM - 5:30 PM
Multifidelity and using data-fit models together with traditional model for, e.g., uncertainty quantification
6:00 PM Lecture/exercises 5 - J. Nathan Kutz (University of Washington)
Lecture/exercises 5
- J. Nathan Kutz (University of Washington)
6:00 PM - 7:30 PM
Learning coordinates and models - SINDy autoencoders - Koopman autoencoders
7:30 PM Closing
Closing
7:30 PM - 7:45 PM

Choose timezone