Learning dynamical systems from data: An introduction to physics-guided deep learning

R Yu, R Wang - Proceedings of the National Academy of Sciences, 2024 - pnas.org
Modeling complex physical dynamics is a fundamental task in science and engineering.
Traditional physics-based models are first-principled, explainable, and sample-efficient …

Scientific machine learning for modeling and simulating complex fluids

KR Lennon, GH McKinley… - Proceedings of the …, 2023 - National Acad Sciences
The formulation of rheological constitutive equations—models that relate internal stresses
and deformations in complex fluids—is a critical step in the engineering of systems involving …

Augmenting astrophysical scaling relations with machine learning: Application to reducing the Sunyaev–Zeldovich flux–mass scatter

D Wadekar, L Thiele… - Proceedings of the …, 2023 - National Acad Sciences
Complex astrophysical systems often exhibit low-scatter relations between observable
properties (eg, luminosity, velocity dispersion, oscillation period). These scaling relations …

Finite volume neural network: Modeling subsurface contaminant transport

T Praditia, M Karlbauer, S Otte, S Oladyshkin… - arXiv preprint arXiv …, 2021 - arxiv.org
Data-driven modeling of spatiotemporal physical processes with general deep learning
methods is a highly challenging task. It is further exacerbated by the limited availability of …

Reconstructing gene regulatory networks of biological function using differential equations of multilayer perceptrons

G Mao, R Zeng, J Peng, K Zuo, Z Pang, J Liu - BMC bioinformatics, 2022 - Springer
Background Building biological networks with a certain function is a challenge in systems
biology. For the functionality of small (less than ten nodes) biological networks, most …

Learning compact physics‐aware delayed photocurrent models using dynamic mode decomposition

J Hanson, P Bochev… - Statistical Analysis and …, 2021 - Wiley Online Library
Radiation‐induced photocurrent in semiconductor devices can be simulated using complex
physics‐based models, which are accurate, but computationally expensive. This presents a …

[PDF][PDF] From the hydrocli-matic disaster to the forced (re) con-struction: Case study of the Akatani watershed in Japan. Proceedings 2022, 69, x

M Dumont, G Arnaud-Fas-setta, C Gomez, C Lissak… - 2022 - sciforum.net
In 5th–6th July 2017 (J17), an unusual train of rainfalls induced a concentration of
precipitations in Northern Kyūshū, Japan, reaching 516 mm for 24 h in Asakura City, a first in …

[引用][C] Physics-informed neural networks for learning dynamic, distributed and uncertain systems

T Praditia - 2023 - Stuttgart: Eigenverlag des Instituts …