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 - http://www.scopus.com/inward/record.url?scp=85118969542&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118969542&partnerID=8YFLogxK
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 Science and Business Media Deutschland GmbH
T2 - 9th iTi Conference on Turbulence, iTi 2021
Y2 - 25 February 2021 through 26 February 2021
ER -