Back to Table of contents

Primeur weekly 2018-06-11

Focus

Exchange of experience and focus on specialisation are key to Europe regaining status in EuroHPC and e-Infrastructures ...

Quantum computing

Atos Quantum Learning Machine available at SURFsara ...

Silicon provides means to control quantum bits for faster algorithms ...

Designer materials with completely random structures might enable quantum computing ...

Rutgers-led research could lead to more efficient electronics ...

Focus on Europe

Researchers at CNAG-CRG developed a novel computational tool named BigSCale to analyze millions of single cells simultaneously ...

Pawsey and PRACE to jointly promote the use of supercomputing ...

Bright and BeeGFS share plans for TERATEC 2018 Forum ...

GCS supports three German university teams in 2018 ISC Student Cluster Competition ...

Hardware

Dell EMC PowerEdge servers enable University of Sydney's world-leading artificial intelligence research ...

Comino announces Comino Grando, a liquid-cooled supercomputer set to disrupt cryptocurrency mining and solve its energy crisis ...

National Science Foundation supports development of new nationwide data storage network ...

Pushing boundaries for CPUs and GPUs, AMD shows next-generation of Ryzen, Radeon and EPYC product leadership at Computex 2018 ...

GARR powers National Research and Education Network in Italy with Infinera Cloud Xpress 2 ...

Supermicro brings resource saving green computing to Computex Taipei 2018 ...

Applications

Cray partners with Digital Catapult's Machine Intelligence Garage to drive UK artificial intelligence innovation ...

Swimming in schools saves energy ...

Researchers use artificial intelligence to identify, count, and describe wild animals ...

Scientists find ordered magnetic patterns in disordered magnetic material ...

New model sheds light on key physics of magnetic islands that halt fusion reactions ...

TOP500

Oak Ridge National Laboratory launches Summit supercomputer ...

Swimming in schools saves energy

A follower interacts judiciously with the wake generated by two leading fish, which increases its swimming-effieciency substantially. Credit: CSElab / ETH Zurich. 6 Jun 2018 Lugano - Researchers at ETH Zurich have clarified the previously unresolved question of whether fish save energy by swimming together in schools. They achieved this by simulating the complex physics on the supercomputer 'Piz Daint' and combining detailed flow simulations with a reinforcement learning algorithm for the first time.

The schooling behaviour of fish fascinates engineers as much as biologists. Fish in schools swim in a flow environment full of mechanical energy generated by the movements of their fellow swimmers. Researchers from ETH Zurich's Computational Science & Engineering Lab (CSElab) have now answered the longstanding question of whether fish gain an energetic advantage by swimming in schooling formations - and the answer is "yes". Researchers also gained detailed knowledge about this process, which may have implications for energy-efficient swimming or flying swarms of drones.

For their study, the scientists developed a highly detailed simulation of the complex interplay between swimming fish and their flow environment. Fish schooling was previously only tackled with very simplified models that did not account accurately for the fluid dynamics of the fish swimming. However, the supercomputer 'Piz Daint' at the Swiss National Supercomputing Centre (CSCS) has now enabled for the first time these state-of-the-art computationally intensive simulations without simplifications.

The scientists also combined for the first time the realistic flow simulations with reinforcement learning, a potent machine learning algorithm. This kind of learning algorithm has been used in games such as 'Go', enabling the computer to outperform humans. Deploying reinforcement learning on complex physical systems, however, has never been done before, as the algorithm requires thousands of iterations.

The algorithm is reminiscent of Pavlov's dog, the scientists from CSElab said: The agents learn an optimal strategy for achieving a goal by receiving a reward. Here, it was used to train the fish for optimal swimming behaviour and to let them decide independently how to most efficiently react to the unsteady flow fields of their fellow swimmers. "We created the mathematical conditions and gave the fish the single goal of swimming as efficiently as possible", stated Guido Novati, a PhD candidate at CSElab and the developer of the simulations' software. Surprisingly, the fish opted to swim in each other’s wake in order to save energy even when given the option of swimming independently.

In their simulation, the researchers observed the swimming behaviour of up to three fish, both in 2D and 3D, in various configurations. They remarked that no flow simulation has ever included more than one swimmer in three dimensions.

They analysed every detail of each individual flow vortex to understand the behaviour of the fish. "Intuitively, you assume that fish will avoid turbulent areas and swim in calmer water. But instead they learned to swim directly into the vortices", stated Siddhartha Verma, a postdoc at CSElab. Siddhartha Verma and guido Novati conducted the study, recently published online in theProceedings of the National Academy of Sciences(PNAS), under the leadership of ETH professor Petros Koumoutsakos.

The researchers determined that the fish swam most energetically when they swam not one after the other as previously suggested, but at an offset from the swimming direction of the leader. At such locations they harnessed the vortices generated by the leader by intercepting them with their head, splitting the vortex into fragments, that they then guided down their bodies. The progress of these fragmented vortices supplies the fish with thrust without robbing the leader of energy.

"This let us demonstrate that fish which suitably position themselves in a school can draw on energy from the prevailing fluid dynamics", stated Siddhartha Verma. He emphasises that in their simulations, they have not examined every aspect involved in the efficient swimming behaviour of fish. However, it is clear that the developed algorithms and physics learned can be transferred into autonomously swimming or flying robots.

An autonomous robot swimmer or flyer could handle unexpected flow situations - for example when delivering goods when flying between buildings in high winds or in the search and rescue operations in stormy conditions. "The possibility of letting aeroplanes with similar destinations fly in formation along certain routes to save fuel is also being considered. The algorithms developed in our work could also be put to use here", stated Guido Novati. The researchers are enthusiastic about the possibilities opened up by combining accurate and complex flow simulations with reinforcement learning and hope that in future, other researchers will incorporate judiciously machine learning into their simulations.

Verma S., Novati G. & Koumoutsakos P. are the authors of the paper titled " Efficient collective swimming by harnessing vortices through deep reinforcement learning ,PNASpublished ahead of print 21 May 2018.

Source: Swiss National Supercomputing Centre - CSCS

Back to Table of contents

Primeur weekly 2018-06-11

Focus

Exchange of experience and focus on specialisation are key to Europe regaining status in EuroHPC and e-Infrastructures ...

Quantum computing

Atos Quantum Learning Machine available at SURFsara ...

Silicon provides means to control quantum bits for faster algorithms ...

Designer materials with completely random structures might enable quantum computing ...

Rutgers-led research could lead to more efficient electronics ...

Focus on Europe

Researchers at CNAG-CRG developed a novel computational tool named BigSCale to analyze millions of single cells simultaneously ...

Pawsey and PRACE to jointly promote the use of supercomputing ...

Bright and BeeGFS share plans for TERATEC 2018 Forum ...

GCS supports three German university teams in 2018 ISC Student Cluster Competition ...

Hardware

Dell EMC PowerEdge servers enable University of Sydney's world-leading artificial intelligence research ...

Comino announces Comino Grando, a liquid-cooled supercomputer set to disrupt cryptocurrency mining and solve its energy crisis ...

National Science Foundation supports development of new nationwide data storage network ...

Pushing boundaries for CPUs and GPUs, AMD shows next-generation of Ryzen, Radeon and EPYC product leadership at Computex 2018 ...

GARR powers National Research and Education Network in Italy with Infinera Cloud Xpress 2 ...

Supermicro brings resource saving green computing to Computex Taipei 2018 ...

Applications

Cray partners with Digital Catapult's Machine Intelligence Garage to drive UK artificial intelligence innovation ...

Swimming in schools saves energy ...

Researchers use artificial intelligence to identify, count, and describe wild animals ...

Scientists find ordered magnetic patterns in disordered magnetic material ...

New model sheds light on key physics of magnetic islands that halt fusion reactions ...

TOP500

Oak Ridge National Laboratory launches Summit supercomputer ...