Back to Table of contents

Primeur weekly 2017-09-04

Special

ETP4HPC to lay out roadmap for tangible HPC products within Europe ...

Focus

Primeur Magazine team unveils the largest directory of HPC organisations in the universe ...

Primeur Magazine team unveils the largest directory of HPC organisations in the universe ...

Quantum computing

First quantum annealing computer in the U.S. to have more than 2000 qubits installed and operational ...

Is the world on the brink of a computing revolution? - Quantum computing at the 5th Heidelberg Laureate Forum ...

Focus on Europe

Smart tomographic sensors control industrial processes of tomorrow ...

DeepL to launch DeepL Translator ...

Middleware

Learning Database speeds queries from hours to seconds ...

Unifying statistics, computer science, and applied mathematics ...

New theorems help robots to correct errors on-the-fly and learn from each other ...

Ace Computers delivers BeeGFS parallel file system for supercomputers ...

Embry-Riddle Aeronautical University acquires Cray CS cluster supercomputer to advance aerospace research ...

Hardware

ScaleMP completes $10 million funding round to accelerate growth ...

Optalysys and Earlham Institute demonstrate results of breakthrough optical processing for sequence alignment ...

University of Southern Mississippi gains campus-wide HPC cluster for research ...

Applications

New boarding procedures, smaller cabin size may limit infection on planes ...

Shaden Smith and Yang You announced as recipients of 2017 ACM/IEEE-CS George Michael Memorial HPC Fellowships ...

A new cosmic lab to view the Big Bang movie ...

Optical control of magnetic memory - New insights into fundamental mechanisms ...

Machine-learning earthquake prediction in lab shows promise ...

Caching system could make data centres more energy efficient ...

Supercomputing the weather with Thor ...

The Cloud

VMware and Dell EMC partner to deliver first data protection solution for VMware Cloud on AWS ...

Oracle expands IoT Cloud portfolio, enabling customers to accelerate intelligence and ROI from connected assets ...

VMware advances software to help customers modernize data centres ...

Fujitsu and VMware extend global partnership to empower organisations' digital transformations ...

VMware and AWS announce initial availability of VMware Cloud on AWS ...

VMware and Pivotal launch Pivotal Container Service (PKS) and collaborate with Google Cloud to bring Kubernetes to enterprise customers ...

Machine-learning earthquake prediction in lab shows promise


Researchers at Los Alamos National Laboratory have developed a two-dimensional tabletop simulator that models the buildup and release of stress along an artificial fault. In this image, the simulator is viewed through a polarized camera lens, photo-elastic plates reveal discrete points of stress buildup along both sides of the modeled fault as the far (upper) plate is moved laterally along the fault. Credit: Los Alamos National Laboratory.
30 Aug 2017 Los Alamos - By listening to the acoustic signal emitted by a laboratory-created earthquake, a computer science approach using machine learning can predict the time remaining before the fault fails.

"At any given instant, the noise coming from the lab fault zone provides quantitative information on when the fault will slip", stated Paul Johnson, a Los Alamos National Laboratory fellow and lead investigator on the research, which was published inGeophysical Research Letters.

"The novelty of our work is the use of machine learning to discover and understand new physics of failure, through examination of the recorded auditory signal from the experimental set-up. I think the future of earthquake physics will rely heavily on machine learning to process massive amounts of raw seismic data. Our work represents an important step in this direction", he stated.

Not only does the work have potential significance to earthquake forecasting, Paul Johnson said, but the approach is far-reaching, applicable to potentially all failure scenarios including nondestructive testing of industrial materials brittle failure of all kinds, avalanches and other events.

Machine learning is an artificial intelligence approach to allowing the computer to learn from new data, updating its own results to reflect the implications of new information.

The machine learning technique used in this project also identifies new signals, previously thought to be low-amplitude noise, that provide forecasting information throughout the earthquake cycle. "These signals resemble Earth tremour that occurs in association with slow earthquakes on tectonic faults in the lower crust", Paul Johnson stated. "There is reason to expect such signals from Earth faults in the seismogenic zone for slowly slipping faults."

Machine learning algorithms can predict failure times of laboratory quakes with remarkable accuracy. The acoustic emission (AE) signal, which characterizes the instantaneous physical state of the system, reliably predicts failure far into the future. This is a surprise, Paul Johnson pointed out, as all prior work had assumed that only the catalog of large events is relevant, and that small fluctuations in the AE signal could be neglected.

To study the phenomena, the team analyzed data from a laboratory fault system that contains fault gouge, the ground-up material created by the stone blocks sliding past one another. An accelerometer recorded the acoustic emission emanating from the shearing layers.

Following a frictional failure in the labquake, the shearing block moves or displaces, while the gouge material simultaneously dilates and strengthens, as shown by measurably increasing shear stress and friction. "As the material approaches failure, it begins to show the characteristics of a critical stress regime, including many small shear failures that emit impulsive acoustic emissions", Paul Johnson described.

"This unstable state concludes with an actual labquake, in which the shearing block rapidly displaces, the friction and shear stress decrease precipitously, and the gouge layers simultaneously compact", he stated. Under a broad range of conditions, the apparatus slide-slips fairly regularly for hundreds of stress cycles during a single experiment. And importantly, the signal - due to the gouge grinding and creaking that ultimately leads to the impulsive precursors - allows prediction in the laboratory, and we hope will lead to advances in prediction in Earth, Paul Johnson said.

The paper is titled " Machine learning predicts laboratory earthquakes " and appeared inGeophysical Research Letters. The funding was provided by Los Alamos National Laboratory Directed Research and Development (LDRD).
Source: DOE/Los Alamos National Laboratory

Back to Table of contents

Primeur weekly 2017-09-04

Special

ETP4HPC to lay out roadmap for tangible HPC products within Europe ...

Focus

Primeur Magazine team unveils the largest directory of HPC organisations in the universe ...

Primeur Magazine team unveils the largest directory of HPC organisations in the universe ...

Quantum computing

First quantum annealing computer in the U.S. to have more than 2000 qubits installed and operational ...

Is the world on the brink of a computing revolution? - Quantum computing at the 5th Heidelberg Laureate Forum ...

Focus on Europe

Smart tomographic sensors control industrial processes of tomorrow ...

DeepL to launch DeepL Translator ...

Middleware

Learning Database speeds queries from hours to seconds ...

Unifying statistics, computer science, and applied mathematics ...

New theorems help robots to correct errors on-the-fly and learn from each other ...

Ace Computers delivers BeeGFS parallel file system for supercomputers ...

Embry-Riddle Aeronautical University acquires Cray CS cluster supercomputer to advance aerospace research ...

Hardware

ScaleMP completes $10 million funding round to accelerate growth ...

Optalysys and Earlham Institute demonstrate results of breakthrough optical processing for sequence alignment ...

University of Southern Mississippi gains campus-wide HPC cluster for research ...

Applications

New boarding procedures, smaller cabin size may limit infection on planes ...

Shaden Smith and Yang You announced as recipients of 2017 ACM/IEEE-CS George Michael Memorial HPC Fellowships ...

A new cosmic lab to view the Big Bang movie ...

Optical control of magnetic memory - New insights into fundamental mechanisms ...

Machine-learning earthquake prediction in lab shows promise ...

Caching system could make data centres more energy efficient ...

Supercomputing the weather with Thor ...

The Cloud

VMware and Dell EMC partner to deliver first data protection solution for VMware Cloud on AWS ...

Oracle expands IoT Cloud portfolio, enabling customers to accelerate intelligence and ROI from connected assets ...

VMware advances software to help customers modernize data centres ...

Fujitsu and VMware extend global partnership to empower organisations' digital transformations ...

VMware and AWS announce initial availability of VMware Cloud on AWS ...

VMware and Pivotal launch Pivotal Container Service (PKS) and collaborate with Google Cloud to bring Kubernetes to enterprise customers ...