ProfessorsProfessors of Harvard UniversityPetros Koumoutsakos

Petros Koumoutsakos

Harvard University

H-index: 86

North America-United States

About Petros Koumoutsakos

Petros Koumoutsakos, With an exceptional h-index of 86 and a recent h-index of 53 (since 2020), a distinguished researcher at Harvard University, specializes in the field of computational science and engineering, AI for science, uncertainty quantification, supercomputing, fluid mechanics.

His recent articles reflect a diverse array of research interests and contributions to the field:

Path planning of magnetic microswimmers in high-fidelity simulations of capillaries with deep reinforcement learning

The Volume of Healthy Red Blood Cells is Optimal for Advective Oxygen Transport in Arterioles

Solving inverse problems in physics by optimizing a discrete loss: Fast and accurate learning without neural networks

Scientific Multi-Agent Reinforcement Learning for Turbulence Closures and Flow Control

Multi-agent reinforcement learning for subgrid-scale modeling of environmental turbulence

Learning in two dimensions and controlling in three: Generalizable drag reduction strategies for flows past circular cylinders through deep reinforcement learning

Generative Learning for Forecasting the Dynamics of Complex Systems

Closure Discovery for Coarse-Grained Partial Differential Equations using Multi-Agent Reinforcement Learning

Petros Koumoutsakos Information

University	Harvard University
Position	/ ETH Zurich
Citations(all)	32670
Citations(since 2020)	14083
Cited By	23894
hIndex(all)	86
hIndex(since 2020)	53
i10Index(all)	240
i10Index(since 2020)	168
Email	Access Email
University Profile Page	Harvard University
Google Scholar	View Google Scholar Profile

Petros Koumoutsakos Skills & Research Interests

computational science and engineering

AI for science

uncertainty quantification

supercomputing

fluid mechanics

Top articles of Petros Koumoutsakos

Title	Journal	Author(s)	Publication Date
Path planning of magnetic microswimmers in high-fidelity simulations of capillaries with deep reinforcement learning	arXiv preprint arXiv:2404.02171	Lucas Amoudruz Sergey Litvinov Petros Koumoutsakos	2024/3/29
The Volume of Healthy Red Blood Cells is Optimal for Advective Oxygen Transport in Arterioles	Biophysical Journal	Lucas Amoudruz Athena Economides Petros Koumoutsakos	2024/4/18
Solving inverse problems in physics by optimizing a discrete loss: Fast and accurate learning without neural networks	PNAS nexus	Petr Karnakov Sergey Litvinov Petros Koumoutsakos	2024/1
Scientific Multi-Agent Reinforcement Learning for Turbulence Closures and Flow Control	Bulletin of the American Physical Society	Petros Koumoutsakos Sergey Litvinov	2024/3/7
Multi-agent reinforcement learning for subgrid-scale modeling of environmental turbulence	Bulletin of the American Physical Society	Rambod Mojgani Daniel Wälchli Yifei Guan Petros Koumoutsakos Pedram Hassanzadeh	2024/3/4
Learning in two dimensions and controlling in three: Generalizable drag reduction strategies for flows past circular cylinders through deep reinforcement learning	Physical Review Fluids	Michail Chatzimanolakis Pascal Weber Petros Koumoutsakos	2024/4/4
Generative Learning for Forecasting the Dynamics of Complex Systems	arXiv preprint arXiv:2402.17157	Han Gao Sebastian Kaltenbach Petros Koumoutsakos	2024/2/27
Closure Discovery for Coarse-Grained Partial Differential Equations using Multi-Agent Reinforcement Learning	arXiv preprint arXiv:2402.00972	Jan-Philipp von Bassewitz Sebastian Kaltenbach Petros Koumoutsakos	2024/2/1
An interpretable wildfire spreading model for real-time predictions	arXiv preprint arXiv:2306.01766	Konstantinos Vogiatzoglou Costas Papadimitriou Konstantinos Ampountolas Michail Chatzimanolakis Petros Koumoutsakos ...	2023/5/27
Extreme event prediction with multi-agent reinforcement learning-based parametrization of atmospheric and oceanic turbulence	arXiv preprint arXiv:2312.00907	Rambod Mojgani Daniel Waelchli Yifei Guan Petros Koumoutsakos Pedram Hassanzadeh	2023/12/1
Gas generating membrane-less electrolyser		Demetri Psaltis Petros Koumoutsakos Pooria Hadikhani Sylvain Jacky Reinauer Steven Alexandre Schenk	2023
The stress-free state of human erythrocytes: Data-driven inference of a transferable RBC model	Biophysical Journal	Lucas Amoudruz Athena Economides Georgios Arampatzis Petros Koumoutsakos	2023/4/18
Adaptive learning of effective dynamics for online modeling of complex systems	Computer Methods in Applied Mechanics and Engineering	Ivica Kičić Pantelis R Vlachas Georgios Arampatzis Michail Chatzimanolakis Leonidas Guibas ...	2023/10/1
Learning from predictions: Fusing training and autoregressive inference for long-term spatiotemporal forecasts	arXiv preprint arXiv:2302.11101	Pantelis R Vlachas Petros Koumoutsakos	2023/2/22
Discovering individual rewards in collective behavior through inverse multi-agent reinforcement learning	arXiv preprint arXiv:2305.10548	Daniel Waelchli Pascal Weber Petros Koumoutsakos	2023/5/17
Optimizing the Discrete Loss for the Solution for Inverse problems in fluid mechanics: multiresolution and automatic differentiation	Bulletin of the American Physical Society	Petros Koumoutsakos Petr Karnakov Sergey Litvinov	2023/11/20
Data assimilation for compressible flows by optimizing a discrete loss (ODIL) with automatic differentiation	Bulletin of the American Physical Society	Petr Karnakov Deniz Bezgin Aaron Buhendwa Nikolaus Adams Petros Koumoutsakos	2023/11/20
Adaptive learning of effective dynamics: Adaptive real-time, online modeling for complex systems	arXiv preprint arXiv:2304.01732	Ivica Kičić Pantelis R Vlachas Georgios Arampatzis Michail Chatzimanolakis Leonidas Guibas ...	2023/4/4
The volume of healthy red blood cells maximizes oxygen transport	arXiv preprint arXiv:2305.02197	Lucas Amoudruz Athena Economides Petros Koumoutsakos	2023/4/28
Interpretable Learning of Effective Dynamics for multiscale systems	arXiv preprint arXiv:2309.05812	Emmanuel Menier Sebastian Kaltenbach Mouadh Yagoubi Marc Schoenauer Petros Koumoutsakos	2023/9/11