267 citations · 343 across the 11 of their papers we have counts for
13 papers
Strategic Governance of AI Models in Earth Science
Makoto Kelp, Amirhossein Arzani, Patricia Castellanos +6
AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their development and adoption are o…
Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks
Mahmoud Elhadidy, Siva Viknesh, Roshan M. D'Souza +1
Wall shear stress (WSS) governs near-wall transport dynamics and is a key hemodynamic indicator in cardiovascular flows, yet remains difficult to infer accurately due to the need f…
Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data
Mojgan Alishiri, Amirhossein Arzani
Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based architectures make them opaque mode…
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
Mahmoud Elhadidy, Roshan M. D'Souza, Amirhossein Arzani
Scientific machine learning is increasingly used to build surrogate models, yet most models are trained under a restrictive assumption in which future data follow the same distribu…
Symbolic--KAN: Kolmogorov-Arnold Networks with Discrete Symbolic Structure for Interpretable Learning
Salah A Faroughi, Farinaz Mostajeran, Amirhossein Arzani +1
Symbolic discovery of governing equations is a long-standing goal in scientific machine learning, yet a fundamental trade-off persists between interpretability and scalable learnin…
Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling
Siva Viknesh, Amirhossein Arzani
Scientific machine learning has enabled the extraction of physical insights and data-driven modeling of high-dimensional spatiotemporal data, yet achieving physically interpretable…
Physics-constrained coupled neural differential equations for one dimensional blood flow modeling
Hunor Csala, Arvind Mohan, Daniel Livescu +1
Computational cardiovascular flow modeling plays a crucial role in understanding blood flow dynamics. While 3D models provide acute details, they are computationally expensive, esp…
Role of flow topology in wind-driven wildfire propagation
Siva Viknesh, Ali Tohidi, Fatemeh Afghah +2
Wildfires propagate through intricate interactions between wind, fuel, and terrain, resulting in complex behaviors that pose challenges for accurate predictions. This study investi…
ADAM-SINDy: An Efficient Optimization Framework for Parameterized Nonlinear Dynamical System Identification
Siva Viknesh, Younes Tatari, Chase Christenson +1
Identifying dynamical systems characterized by nonlinear parameters presents significant challenges in deriving mathematical models that enhance understanding of physics. Tradition…
Interpreting and generalizing deep learning in physics-based problems with functional linear models
Amirhossein Arzani, Lingxiao Yuan, Pania Newell +1
Although deep learning has achieved remarkable success in various scientific machine learning applications, its opaque nature poses concerns regarding interpretability and generali…
Uncovering near-wall blood flow from sparse data with physics-informed neural networks
Amirhossein Arzani, Jian-Xun Wang, Roshan M. D'Souza
Near-wall blood flow and wall shear stress (WSS) regulate major forms of cardiovascular disease, yet they are challenging to quantify with high fidelity. Patient-specific computati…
Integrating multi-fidelity blood flow data with reduced-order data assimilation
Milad Habibi, Roshan M. D'Souza, Scott T. M. Dawson +1
High-fidelity patient-specific modeling of cardiovascular flows and hemodynamics is challenging. Direct blood flow measurement inside the body with in-vivo measurement modalities s…
Data-driven cardiovascular flow modeling: examples and opportunities
Amirhossein Arzani, Scott T. M. Dawson
High-fidelity modeling of blood flow is crucial for enhancing our understanding of cardiovascular disease. Despite significant advances in computational and experimental characteri…