Deep learning for universal linear embeddings of nonlinear dynamics

Autor: Bethany Lusch, J. Nathan Kutz, Steven L. Brunton

Publikováno v: Nature Communications, Vol 9, Iss 1, Pp 1-10 (2018)

It is often advantageous to transform a strongly nonlinear system into a linear one in order to simplify its analysis for prediction and control. Here the authors combine dynamical systems with deep learning to identify these hard-to-find transformat

Externí odkaz: https://doaj.org/article/d72f7d260a5d4c2a905fed768a9492b8

Efficient high-dimensional variational data assimilation with machine-learned reduced-order models

Autor: Romit Maulik, Vishwas Rao, Jiali Wang, Gianmarco Mengaldo, Emil Constantinescu, Bethany Lusch, Prasanna Balaprakash, Ian Foster, Rao Kotamarthi

Data assimilation (DA) in geophysical sciences remains the cornerstone of robust forecasts from numerical models. Indeed, DA plays a crucial role in the quality of numerical weather prediction and is a crucial building block that has allowed dramatic

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f54a52b9534d4dca24711b4b6e45c899
https://gmd.copernicus.org/articles/15/3433/2022/

DATA-DRIVEN MODEL REDUCTION OF MULTIPHASE FLOW IN A SINGLE-HOLE AUTOMOTIVE INJECTOR

Autor: Roberto Torelli, Gina M. Magnotti, Bethany Lusch, Petro Junior Milan

Publikováno v: Atomization and Sprays. 30:401-429

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::dfe3cba6888add4380616b830fe70b09
https://doi.org/10.1615/atomizspr.2020034830

AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification

Autor: Romain Egele, Romit Maulik, Krishnan Raghavan, Bethany Lusch, Isabelle Guyon, Prasanna Balaprakash

Publikováno v: 26TH International Conference on Pattern Recognition
26TH International Conference on Pattern Recognition, Aug 2022, Montréal, Canada. pp.1908-1914

International audience; Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is competitive with approaches based on Bayesian ne

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51edfa6fba9cfae3dc581011d10483d6
http://arxiv.org/abs/2110.13511

Surrogate multi-fidelity data and model fusion for scientific discovery and uncertainty quantification in Earth System Models

Autor: Romit Maulik, Virendra Ghate, William Pringle, Yan Feng, Vishwas Rao, Julie Bessac, Bethany Lusch

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d1c4e9c108f39f406c67cd1f305e90cd
https://doi.org/10.2172/1769781