Results 31 to 40 of about 11,198,121 (288)

Emergent physics-informed design of deep learning for microscopy [PDF]

, 2021
Funding: UK Engineering and Physical Sciences Research Council through grant EP/P030017/1.Deep learning has revolutionised microscopy, enabling automated means for image classification, tracking and transformation.
Wijesinghe, Philip, Dholakia, Kishan, Wijesinghe, Philip; id_orcid, Philip Wijesinghe, Kishan Dholakia   +4 more
core   +1 more source

Physics-informed machine learning with conditional Karhunen-Loève expansions [PDF]

Journal of Computational Physics, 2021
We present a new physics-informed machine learning approach for the inversion of PDE models with heterogeneous parameters. In our approach, the space-dependent partially-observed parameters and states are approximated via Karhunen-Loève expansions (KLEs).
Alexandre M. Tartakovsky, David A. Barajas-Solano, QiZhi He   +2 more
openaire   +2 more sources

Physics-Informed Machine Learning Simulator for Wildfire Propagation

CoRR, 2020
The aim of this work is to evaluate the feasibility of re-implementing some key parts of the widely used Weather Research and Forecasting WRF-SFIRE simulator by replacing its core differential equations numerical solvers with state-of-the-art physics-informed machine learning techniques to solve ODEs and PDEs, in order to transform it into a real-time ...
Luca Bottero, Francesco Calisto, Giovanni Graziano, Valerio Pagliarino, Martina Scauda, Sara Tiengo, Simone Azeglio   +6 more
openaire   +3 more sources

Machine Learning for PAC1D and SESE [PDF]

, 2023
This document outlines various machine learning approaches that were taken in an effort to surrogate numerical models Python Ablation Code 1-Dimension (PAC1D) and Scalable Effects Simulation Environment (SESE), with the ultimate objective of discovering ...
Seman, Matthew G., Oian, Chad A., Khan, Taufiquar, Kurz, Jason A., Bowman, Brett A.   +4 more
core  

Physics-informed machine learning of the correlation functions in bulk fluids [PDF]

, 2023
The Ornstein-Zernike (OZ) equation is the fundamental equation for pair correlation function computations in the modern integral equation theory for liquids.
Chen, Wenqian, Stinis, Panos, Gao, Peiyuan   +2 more
core   +1 more source

Advancing material property prediction: using physics-informed machine learning models for viscosity. [PDF]

J Cheminform
In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging.
Chew AK, Sender M, Kaplan Z, Chandrasekaran A, Chief Elk J, Browning AR, Kwak HS, Halls MD, Afzal MAF.   +8 more
europepmc   +4 more sources

Physics-informed Machine Learning for Modeling Turbulence in Supernovae

The Astrophysical Journal, 2022
Abstract Turbulence plays an important role in astrophysical phenomena, including core-collapse supernovae (CCSNe), but current simulations must rely on subgrid models, since direct numerical simulation is too expensive. Unfortunately, existing subgrid models are not sufficiently accurate.
Platon I. Karpov, Chengkun Huang, Iskandar Sitdikov, Chris L. Fryer, Stan Woosley, Ghanshyam Pilania   +5 more
openaire   +2 more sources

Learning to use information: Informed learning in the undergraduate classroom [PDF]

, 2013
“Informed learning” is a pedagogy that focuses on learning subject content through engaging with academic or professional information practices.
Rebmann, Kristen, Bruce, Christine S., Bruce, Christine Susan, Lupton, Mandy, Maybee, Clarence   +4 more
core   +2 more sources

Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes

Nature Communications, 2023
Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and temporal ...
Prabhav Borate, Jacques Rivière, Chris Marone, Ankur Mali, Daniel Kifer, Parisa Shokouhi   +5 more
doaj   +1 more source

Superstructure magnetic anisotropy in Fe3O4 nanoparticle chains

Nature Communications
Magnetic anisotropy is essential for many applications of ferromagnetic/ferrimagnetic materials, including permanent magnets and magnetic recording media.
Jeotikanta Mohapatra, Pramanand Joshi, Hur Abbas, Markus Gusenbauer, Kaifu Bian, Ping Lu, Hongyou Fan, Thomas Schrefl, J. Ping Liu   +8 more
doaj   +1 more source