Zobrazeno 1 - 10
of 548
pro vyhledávání: '"Tartakovsky, Daniel M"'
The development of efficient surrogates of partial differential equations (PDEs) is a critical step towards scalable modeling of complex, multiscale systems-of-systems. Convolutional neural networks (CNNs) have gained popularity as the basis for such
Externí odkaz:
http://arxiv.org/abs/2410.12241
Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov-Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We dem
Externí odkaz:
http://arxiv.org/abs/2410.11587
Langevin (stochastic differential) equations are routinely used to describe particle-laden flows. They predict Gaussian probability density functions (PDFs) of a particle's trajectory and velocity, even though experimentally observed dynamics might b
Externí odkaz:
http://arxiv.org/abs/2403.04913
Autor:
Muhammad, Ressi Bonti, Srivastava, Apoorv, Alyaev, Sergey, Bratvold, Reidar Brumer, Tartakovsky, Daniel M.
Geosteering, a key component of drilling operations, traditionally involves manual interpretation of various data sources such as well-log data. This introduces subjective biases and inconsistent procedures. Academic attempts to solve geosteering dec
Externí odkaz:
http://arxiv.org/abs/2402.06377
Autor:
Dominguez-Vazquez, Daniel, Castiblanco-Ballesteros, Sergio A., Jacobs, Gustaaf B., Tartakovsky, Daniel M.
Eulerian-Lagrangian models of particle-laden (multiphase) flows describe fluid flow and particle dynamics in the Eulerian and Lagrangian frameworks respectively. Regardless of whether the flow is turbulent or laminar, the particle dynamics is stochas
Externí odkaz:
http://arxiv.org/abs/2312.07713
Autor:
Zhao, Hongli, Tartakovsky, Daniel M.
Discovery of mathematical descriptors of physical phenomena from observational and simulated data, as opposed to from the first principles, is a rapidly evolving research area. Two factors, time-dependence of the inputs and hidden translation invaria
Externí odkaz:
http://arxiv.org/abs/2309.05117
Autor:
Chandra, Abhishek, Kapoor, Taniya, Daniels, Bram, Curti, Mitrofan, Tiels, Koen, Tartakovsky, Daniel M., Lomonova, Elena A.
Hysteresis is a ubiquitous phenomenon in science and engineering; its modeling and identification are crucial for understanding and optimizing the behavior of various systems. We develop an ordinary differential equation-based recurrent neural networ
Externí odkaz:
http://arxiv.org/abs/2308.12002
Autor:
Kapoor, Taniya, Chandra, Abhishek, Tartakovsky, Daniel M., Wang, Hongrui, Nunez, Alfredo, Dollevoet, Rolf
A primary challenge of physics-informed machine learning (PIML) is its generalization beyond the training domain, especially when dealing with complex physical problems represented by partial differential equations (PDEs). This paper aims to enhance
Externí odkaz:
http://arxiv.org/abs/2308.08989
Autor:
Lu, Hannah, Tartakovsky, Daniel M.
We present a data-driven learning approach for unknown nonautonomous dynamical systems with time-dependent inputs based on dynamic mode decomposition (DMD). To circumvent the difficulty of approximating the time-dependent Koopman operators for nonaut
Externí odkaz:
http://arxiv.org/abs/2306.15618
Autor:
Chandra, Abhishek, Daniels, Bram, Curti, Mitrofan, Tiels, Koen, Lomonova, Elena A., Tartakovsky, Daniel M.
This article presents an approach for modelling hysteresis in piezoelectric materials, that leverages recent advancements in machine learning, particularly in sparse-regression techniques. While sparse regression has previously been used to model var
Externí odkaz:
http://arxiv.org/abs/2302.05313