Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems

Saleh Rezaeiravesh; Yuki Morita; Narges Tabatabaei; Ricardo Vinuesa; Koji Fukagata; Philipp Schlatter

doi:10.1007/978-3-030-80716-0_18

Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems

Saleh Rezaeiravesh, Yuki Morita, Narges Tabatabaei, Ricardo Vinuesa, Koji Fukagata, Philipp Schlatter^*

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

Bayesian optimisation based on Gaussian process regression (GPR) is an efficient gradient-free algorithm widely used in various fields of data sciences to find global optima. Based on a recent study by the authors, Bayesian optimisation is shown to be applicable to optimisation problems based on simulations of different fluid flows. Examples range from academic to more industrially-relevant cases. As a main conclusion, the number of flow simulations required in Bayesian optimisation was found not to exponentially grow with the dimensionality of the design parameters (hence, no curse of dimensionality). Here, the Bayesian optimisation method is outlined and its application to the shape optimisation of a two-dimensional lid-driven cavity flow is detailed.

Original language	English
Title of host publication	Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021
Editors	Ramis Örlü, Alessandro Talamelli, Joachim Peinke, Martin Oberlack
Publisher	Springer Nature
Pages	137-143
Number of pages	7
ISBN (Print)	9783030807153
DOIs	https://doi.org/10.1007/978-3-030-80716-0_18
Publication status	Published - 2021
Event	9th iTi Conference on Turbulence, iTi 2021 - Virtual, Online Duration: 25 Feb 2021 → 26 Feb 2021

Publication series

Name	Springer Proceedings in Physics
Volume	267
ISSN (Print)	0930-8989
ISSN (Electronic)	1867-4941

Conference

Conference	9th iTi Conference on Turbulence, iTi 2021
City	Virtual, Online
Period	25/02/21 → 26/02/21

Access to Document

10.1007/978-3-030-80716-0_18

Cite this

Rezaeiravesh, S., Morita, Y., Tabatabaei, N., Vinuesa, R., Fukagata, K., & Schlatter, P. (2021). Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems. In R. Örlü, A. Talamelli, J. Peinke, & M. Oberlack (Eds.), Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021 (pp. 137-143). (Springer Proceedings in Physics; Vol. 267). Springer Nature. https://doi.org/10.1007/978-3-030-80716-0_18

Rezaeiravesh, Saleh ; Morita, Yuki ; Tabatabaei, Narges et al. / Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems. Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021. editor / Ramis Örlü ; Alessandro Talamelli ; Joachim Peinke ; Martin Oberlack. Springer Nature, 2021. pp. 137-143 (Springer Proceedings in Physics).

@inproceedings{b967bd0cbc1c4d109663645bb9f94461,

title = "Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems",

abstract = "Bayesian optimisation based on Gaussian process regression (GPR) is an efficient gradient-free algorithm widely used in various fields of data sciences to find global optima. Based on a recent study by the authors, Bayesian optimisation is shown to be applicable to optimisation problems based on simulations of different fluid flows. Examples range from academic to more industrially-relevant cases. As a main conclusion, the number of flow simulations required in Bayesian optimisation was found not to exponentially grow with the dimensionality of the design parameters (hence, no curse of dimensionality). Here, the Bayesian optimisation method is outlined and its application to the shape optimisation of a two-dimensional lid-driven cavity flow is detailed.",

author = "Saleh Rezaeiravesh and Yuki Morita and Narges Tabatabaei and Ricardo Vinuesa and Koji Fukagata and Philipp Schlatter",

note = "Funding Information: Acknowledgements SR acknowledges the financial support from the FLOW Centre at KTH and the EXCELLERAT project which has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreement No 823691. YM acknowledges the Keio-KTH double degree program and the financial support from the NSK Schol-arship Foundation. PS, NT and SR also acknowledge funding by the Knut and Alice Wallenberg Foundation via the KAW Academy Fellow programme. KF acknowledges the financial support from the Japan Society for the Promotion of Science (KAKENHI grant number: 18H03758). Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 9th iTi Conference on Turbulence, iTi 2021 ; Conference date: 25-02-2021 Through 26-02-2021",

year = "2021",

doi = "10.1007/978-3-030-80716-0\_18",

language = "English",

isbn = "9783030807153",

series = "Springer Proceedings in Physics",

publisher = "Springer Nature",

pages = "137--143",

editor = "Ramis {\"O}rl{\"u} and Alessandro Talamelli and Joachim Peinke and Martin Oberlack",

booktitle = "Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021",

address = "United States",

}

Rezaeiravesh, S, Morita, Y, Tabatabaei, N, Vinuesa, R, Fukagata, K & Schlatter, P 2021, Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems. in R Örlü, A Talamelli, J Peinke & M Oberlack (eds), Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021. Springer Proceedings in Physics, vol. 267, Springer Nature, pp. 137-143, 9th iTi Conference on Turbulence, iTi 2021, Virtual, Online, 25/02/21. https://doi.org/10.1007/978-3-030-80716-0_18

Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems. / Rezaeiravesh, Saleh; Morita, Yuki; Tabatabaei, Narges et al.
Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021. ed. / Ramis Örlü; Alessandro Talamelli; Joachim Peinke; Martin Oberlack. Springer Nature, 2021. p. 137-143 (Springer Proceedings in Physics; Vol. 267).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems

AU - Rezaeiravesh, Saleh

AU - Morita, Yuki

AU - Tabatabaei, Narges

AU - Vinuesa, Ricardo

AU - Fukagata, Koji

AU - Schlatter, Philipp

N1 - Funding Information: Acknowledgements SR acknowledges the financial support from the FLOW Centre at KTH and the EXCELLERAT project which has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 823691. YM acknowledges the Keio-KTH double degree program and the financial support from the NSK Schol-arship Foundation. PS, NT and SR also acknowledge funding by the Knut and Alice Wallenberg Foundation via the KAW Academy Fellow programme. KF acknowledges the financial support from the Japan Society for the Promotion of Science (KAKENHI grant number: 18H03758). Publisher Copyright: © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2021

Y1 - 2021

N2 - Bayesian optimisation based on Gaussian process regression (GPR) is an efficient gradient-free algorithm widely used in various fields of data sciences to find global optima. Based on a recent study by the authors, Bayesian optimisation is shown to be applicable to optimisation problems based on simulations of different fluid flows. Examples range from academic to more industrially-relevant cases. As a main conclusion, the number of flow simulations required in Bayesian optimisation was found not to exponentially grow with the dimensionality of the design parameters (hence, no curse of dimensionality). Here, the Bayesian optimisation method is outlined and its application to the shape optimisation of a two-dimensional lid-driven cavity flow is detailed.

AB - Bayesian optimisation based on Gaussian process regression (GPR) is an efficient gradient-free algorithm widely used in various fields of data sciences to find global optima. Based on a recent study by the authors, Bayesian optimisation is shown to be applicable to optimisation problems based on simulations of different fluid flows. Examples range from academic to more industrially-relevant cases. As a main conclusion, the number of flow simulations required in Bayesian optimisation was found not to exponentially grow with the dimensionality of the design parameters (hence, no curse of dimensionality). Here, the Bayesian optimisation method is outlined and its application to the shape optimisation of a two-dimensional lid-driven cavity flow is detailed.

UR - https://www.scopus.com/pages/publications/85118969542

U2 - 10.1007/978-3-030-80716-0_18

DO - 10.1007/978-3-030-80716-0_18

M3 - Conference contribution

AN - SCOPUS:85118969542

SN - 9783030807153

T3 - Springer Proceedings in Physics

SP - 137

EP - 143

BT - Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021

A2 - Örlü, Ramis

A2 - Talamelli, Alessandro

A2 - Peinke, Joachim

A2 - Oberlack, Martin

PB - Springer Nature

T2 - 9th iTi Conference on Turbulence, iTi 2021

Y2 - 25 February 2021 through 26 February 2021

ER -

Rezaeiravesh S, Morita Y, Tabatabaei N, Vinuesa R, Fukagata K, Schlatter P. Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems. In Örlü R, Talamelli A, Peinke J, Oberlack M, editors, Progress in Turbulence IX - Proceedings of the iTi Conference in Turbulence, 2021. Springer Nature. 2021. p. 137-143. (Springer Proceedings in Physics). doi: 10.1007/978-3-030-80716-0_18

Bayesian Optimisation with Gaussian Process Regression Applied to Fluid Problems

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this