1 code implementation • 18 Sep 2023 • Jacob Wulff Wold, Florian Stadtmann, Adil Rasheed, Mandar Tabib, Omer San, Jan-Tore Horn
Atmospheric flows are governed by a broad variety of spatio-temporal scales, thus making real-time numerical modeling of such turbulent flows in complex terrain at high resolution computationally intractable.
1 code implementation • 24 Jun 2023 • Pu Ren, N. Benjamin Erichson, Shashank Subramanian, Omer San, Zarija Lukic, Michael W. Mahoney
Super-Resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of finer details, and improving the overall quality and fidelity of the data representation.
no code implementations • 16 Apr 2023 • Florian Stadtman, Adil Rasheed, Trond Kvamsdal, Kjetil André Johannessen, Omer San, Konstanze Kölle, John Olav Giæver Tande, Idar Barstad, Alexis Benhamou, Thomas Brathaug, Tore Christiansen, Anouk-Letizia Firle, Alexander Fjeldly, Lars Frøyd, Alexander Gleim, Alexander Høiberget, Catherine Meissner, Guttorm Nygård, Jørgen Olsen, Håvard Paulshus, Tore Rasmussen, Elling Rishoff, Francesco Scibilia, John Olav Skogås
The contribution of this article lies in its synthesis of the current state of knowledge and its identification of future research needs and challenges from an industry perspective, ultimately providing a roadmap for future research and development in the field of digital twin and its applications in the wind energy industry.
no code implementations • 14 Dec 2022 • Elias Mohammed Elfarri, Adil Rasheed, Omer San
By understanding the capability level of a digital twin, we can better understand its potential and limitations.
no code implementations • 15 Aug 2022 • Omer San, Suraj Pawar, Adil Rasheed
Physics-based models have been mainstream in fluid dynamics for developing predictive models.
no code implementations • 7 Jul 2022 • Omer San, Suraj Pawar, Adil Rasheed
In this paper, we introduce a decentralized digital twin (DDT) framework for dynamical systems and discuss the prospects of the DDT modeling paradigm in computational science and engineering applications.
no code implementations • 7 Jul 2022 • Omer San, Suraj Pawar, Adil Rasheed
A central challenge in the computational modeling and simulation of a multitude of science applications is to achieve robust and accurate closures for their coarse-grained representations due to underlying highly nonlinear multiscale interactions.
no code implementations • 17 Jun 2022 • Diana Alina Bistrian, Omer San, Ionel Michael Navon
Associating the dynamical process with a digital twin model of reduced complexity has the significant advantage to map the dynamics with high accuracy and reduced costs in CPU time and hardware to timescales over which that suffers significantly changes and so it is difficult to explore.
no code implementations • 7 Jun 2022 • Sindre Stenen Blakseth, Adil Rasheed, Trond Kvamsdal, Omer San
In the current work, we demonstrate how a hybrid approach combining the best of PBM and DDM can result in models which can outperform them both.
no code implementations • 25 May 2022 • Shady E. Ahmed, Omer San, Adil Rasheed, Traian Iliescu, Alessandro Veneziani
We propose a new physics guided machine learning (PGML) paradigm that leverages the variational multiscale (VMS) framework and available data to dramatically increase the accuracy of reduced order models (ROMs) at a modest computational cost.
no code implementations • 13 May 2022 • Haakon Robinson, Suraj Pawar, Adil Rasheed, Omer San
The success of the current wave of artificial intelligence can be partly attributed to deep neural networks, which have proven to be very effective in learning complex patterns from large datasets with minimal human intervention.
no code implementations • 30 Nov 2021 • Thomas Nakken Larsen, Amalie Heiberg, Eivind Meyer, Adil Rasheeda, Omer San, Damiano Varagnolo
Autonomous systems are becoming ubiquitous and gaining momentum within the marine sector.
1 code implementation • 15 Oct 2021 • Shady E. Ahmed, Omer San, Adil Rasheed, Traian Iliescu
Autoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space.
no code implementations • 24 May 2021 • Sindre Stenen Blakseth, Adil Rasheed, Trond Kvamsdal, Omer San
In this work, we introduce, justify and demonstrate the Corrective Source Term Approach (CoSTA) -- a novel approach to Hybrid Analysis and Modeling (HAM).
no code implementations • 26 Mar 2021 • Omer San, Adil Rasheed, Trond Kvamsdal
Most modeling approaches lie in either of the two categories: physics-based or data-driven.
no code implementations • 15 Mar 2021 • Tiril Sundby, Julia Maria Graham, Adil Rasheed, Mandar Tabib, Omer San
Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in the digital replica.
no code implementations • 22 Dec 2020 • Andrine Elsetrønning, Adil Rasheed, Jon Bekker, Omer San
A vital part of using the lung sound for disease detection is discrimination between normal lung sound and abnormal lung sound.
Sound Audio and Speech Processing
1 code implementation • 18 Dec 2020 • Suraj Pawar, Omer San, Burak Aksoylu, Adil Rasheed, Trond Kvamsdal
Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences.
no code implementations • 5 Aug 2020 • Shady Ahmed, Suraj Pawar, Omer San, Adil Rasheed, Mandar Tabib
We put forth a long short-term memory (LSTM) nudging framework for the enhancement of reduced order models (ROMs) of fluid flows utilizing noisy measurements for air traffic improvements.
no code implementations • 17 Jun 2020 • Simen Theie Havenstrøm, Adil Rasheed, Omer San
Control theory provides engineers with a multitude of tools to design controllers that manipulate the closed-loop behavior and stability of dynamical systems.
1 code implementation • 17 Jun 2020 • Shady E. Ahmed, Omer San, Kursat Kara, Rami Younis, Adil Rasheed
Complex natural or engineered systems comprise multiple characteristic scales, multiple spatiotemporal domains, and even multiple physical closure laws.
no code implementations • 16 Jun 2020 • Eivind Meyer, Amalie Heiberg, Adil Rasheed, Omer San
Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics.
no code implementations • 28 May 2020 • Shady Ahmed, Suraj Pawar, Omer San, Adil Rasheed
In this paper, we put forth a long short-term memory (LSTM) nudging framework for the enhancement of reduced order models (ROMs) of fluid flows utilizing noisy measurements.
Dynamical Systems Computational Physics Fluid Dynamics
1 code implementation • 21 May 2020 • Shady E. Ahmed, Kinjal Bhar, Omer San, Adil Rasheed
In this paper, we propose a variational approach to estimate eddy viscosity using forward sensitivity method (FSM) for closure modeling in nonlinear reduced order models.
Dynamical Systems Fluid Dynamics
no code implementations • 11 Feb 2020 • Herman Stavelin, Adil Rasheed, Omer San, Arne Johan Hestnes
In an effort to preserve maritime wildlife the Norwegian government has decided that it is necessary to create an overview over the presence and abundance of various species of wildlife in the Norwegian fjords and oceans.
no code implementations • 18 Dec 2019 • Eivind Meyer, Haakon Robinson, Adil Rasheed, Omer San
In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an underactuated autonomous surface vehicle to follow an a priori known path while avoiding collisions with non-moving obstacles along the way.
1 code implementation • 14 Dec 2019 • Shady E. Ahmed, Omer San, Adil Rasheed, Traian Iliescu
In the first layer, we utilize an intrusive projection approach to model dynamics represented by the largest modes.
Fluid Dynamics Dynamical Systems Computational Physics
no code implementations • 9 Oct 2019 • Haakon Robinson, Adil Rasheed, Omer San
It has been shown that neural networks with piecewise affine activation functions are themselves piecewise affine, with their domains consisting of a vast number of linear regions.