Hybrid Analysis & Modeling

Overview

Hybrid Analysis and Modeling (HAM) represents a paradigm shift in computational modeling by combining physics-based models with data-driven machine learning approaches. This methodology leverages the interpretability and reliability of physics-based models while harnessing the flexibility and adaptability of AI/ML techniques.

I pioneered this approach at SINTEF and NTNU, establishing HAM as a new modeling paradigm that bridges the gap between traditional simulation and modern machine learning.

Research Topics

Corrective Source Term Approach

Using machine learning corrections to improve physics-based simulation fidelity.

Reduced Order Modeling

Developing low-dimensional efficient models to accelerate simulation and control.

Physics Informed Neural Network

Embedding physical laws into neural networks for constrained and data-efficient learning.

Physics Guided Machine Learning

Guiding machine learning with domain knowledge and principled priors for robustness.

Deep Operator Learning

Learning operators that map functions to functions for rapid PDE solution and inference.

Safe Reinforcement Learning

Designing reinforcement learning methods with formal or empirical safety guarantees for control.

Key Projects

Component ROM

RAPID

Hybrid analysis and modeling (10M NOK, 2020-2023)

CoSTA

PoroTwin

Digital twin of porous media flow using hybrid methods

CoSTA

Upgrid

Dynamic loading of cables under varying loads.

Optimal Sensor Placement and ROM

dThor

Structural health monitoring using HAM.

Diagnostic

Hole Cleaning Monitoring

Monitoring and predictive analytics for hole-cleaning operations using hybrid models.

Diagnostics

Bigpressure

High-pressure system monitoring and anomaly detection using physics-guided ML.

Key Publications

Enhancing Elasticity Models with Deep Learning: A Novel Corrective Source Term Approach for Accurate Predictions
Sørbø, S., Blakseth, S.S., Rasheed, A., Kvamsdal, T., San, O.
Applied Soft Computing, 111312, 2024
DOI
Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
Ahmed, S.E., San, O., Rasheed, A., Iliescu, T., Veneziani, A.
SIAM Journal on Scientific Computing, 45(3), 283-313, 2023
DOI
Combining physics-based and data-driven techniques for reliable hybrid analysis and modeling using the corrective source term approach
Blakseth, S.S., Rasheed, A., Kvamsdal, T. and San, O.
Applied Soft Computing, 128, 109533, 2022
DOI
Deep neural network enabled corrective source term approach to hybrid analysis and modeling
Blakseth, S.S., Rasheed, A., Kvamsdal, T., San, O.
Neural Networks, 146, 181-199, 2021
DOI
On closures for reduced order models - a spectrum of first-principle to machine-learned avenues
Ahmed, S., Pawar, S., San, O., Rasheed, A., Iliescu, T., Noack, B.
Physics of Fluids, 33, 091301, 2021
DOI
Model fusion with physics-guided machine learning: projection based reduced order modeling
Pawar, S., San, O., Aditya, N., Rasheed, A., Kvamsdal, T.
Physics of Fluids, 33, 067123, 2021
DOI
Memory embedded non-intrusive reduced order modeling of non-ergodic flows
Ahmed, S. E., Rahman, S. M., San, O., Rasheed, A., Navon, I. M.
Physics of Fluids, 31, 126602, 2019
DOI
A deep learning enabler for non-intrusive reduced order modeling of fluid flows
Pawar, S., Rahman, S. M., Vaddireddy, H., San, O., Rasheed, A., Vedula, P.
Physics of Fluids, 31, 085101, 2019
DOI

Reduced Order Modeling (selected)

Hybrid deep-learning POD-based parametric reduced order model for flow around wind-turbine blade
Tabib, M.V., Tsiolakis, V., Pawar, S., Ahmed, S.E., Rasheed, A., Kvamsdal, T., San, O.
Journal of Physics: Conference Series, 2022
Link
A Non-Intrusive Parametric Reduced Order Model for Urban Wind Flow Using Deep Learning and Grassmann Manifold
Tabib, M.V., Pawar, S., Ahmed, S.E., Rasheed, A., San, O.
Journal of Physics: Conference Series, 2018(1):012038 (published 2021)
Link
Reduced Order Models for Finite-Volume Simulations of Turbulent Flow Around Wind-Turbine Blades
Tsiolakis, V., Kvamsdal, T., Rasheed, A., Fonn, E., van Brummelen, H.
Journal of Physics: Conference Series, 2018(1):012042 (published 2021)
Link
Reduced Order Modeling of Fluid Flows: Machine Learning, Kolmogorov Barrier, Closure Modeling, and Partitioning
Ahmed, S.E., Pawar, S., San, O., Rasheed, A.
AIAA AVIATION 2020
DOI

Safe Reinforcement Learning (selected)

Modular Control Architecture for Safe Marine Navigation: Reinforcement Learning and Predictive Safety Filters
Vaaler, A., Husa, S., Menges, D., Nakken, T.L., Rasheed, A.
Artificial Intelligence, 336, 104201, 2024
DOI
Risk-based implementation of COLREGs for autonomous surface vehicles using deep reinforcement learning
Heiberg, A., Larsen, T.N., Meyer, E., Rasheed, A., San, O., Varagnolo, D.
Neural Networks, 152, 17-33, 2022
DOI
Comparing Deep Reinforcement Learning Algorithms' Ability to Safely Navigate Challenging Waters
Larsen, T.N., Teigen, H.Ø., Laache, T., Varagnolo, D., and Rasheed, A.
Frontiers in Robotics and Artificial Intelligence, 8, 287, 2021
DOI
Deep reinforcement learning controller for 3D path following and collision avoidance by autonomous underwater vehicles
Havenstrøm, S. T., Rasheed, A., San, O.
Frontiers in Robotics and AI, 7, 566037, 2021
DOI
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning
Meyer, E., Heiberg, A., Rasheed, A., San, O.
IEEE Access, 8, 165344-165364, 2020
IEEE