̽��ֱ�� of Cambridge - geophysics

Machine learning used to predict earthquakes in a lab setting

sc604 — Mon, 23 Oct 2017 00:28:01 +0000

̽��ֱ��team, from the ̽��ֱ�� of Cambridge, Los Alamos National Laboratory and Boston ̽��ֱ��, identified a hidden signal leading up to earthquakes and used this ‘fingerprint’ to train a machine learning algorithm to predict future earthquakes. Their results, which could also be applied to avalanches, landslides and more, are reported in the journal Geophysical Review Letters.

For geoscientists, predicting the timing and magnitude of an earthquake is a fundamental goal. Generally speaking, pinpointing where an earthquake will occur is fairly straightforward: if an earthquake has struck a particular place before, the chances are it will strike there again. ̽��ֱ��questions that have challenged scientists for decades are how to pinpoint when an earthquake will occur, and how severe it will be. Over the past 15 years, advances in instrument precision have been made, but a reliable earthquake prediction technique has not yet been developed.

As part of a project searching for ways to use machine learning techniques to make gallium nitride (GaN) LEDs more efficient, the study’s first author, Bertrand Rouet-Leduc, who was then a PhD student at Cambridge, moved to Los Alamos National Laboratory in New Mexico to start a collaboration on machine learning in materials science between Cambridge ̽��ֱ�� and Los Alamos. From there the team started helping the Los Alamos Geophysics group on machine learning questions.

̽��ֱ��team at Los Alamos, led by Paul Johnson, studies the interactions among earthquakes, precursor quakes (often very small earth movements) and faults, with the hope of developing a method to predict earthquakes. Using a lab-based system that mimics real earthquakes, the researchers used machine learning techniques to analyse the acoustic signals coming from the ‘fault’ as it moved and search for patterns.

̽��ֱ��laboratory apparatus uses steel blocks to closely mimic the physical forces at work in a real earthquake, and also records the seismic signals and sounds that are emitted. Machine learning is then used to find the relationship between the acoustic signal coming from the fault and how close it is to failing.

̽��ֱ��machine learning algorithm was able to identify a particular pattern in the sound, previously thought to be nothing more than noise, which occurs long before an earthquake. ̽��ֱ��characteristics of this sound pattern can be used to give a precise estimate (within a few percent) of the stress on the fault (that is, how much force is it under) and to estimate the time remaining before failure, which gets more and more precise as failure approaches. ̽��ֱ��team now thinks that this sound pattern is a direct measure of the elastic energy that is in the system at a given time.

“This is the first time that machine learning has been used to analyse acoustic data to predict when an earthquake will occur, long before it does, so that plenty of warning time can be given – it’s incredible what machine learning can do,” said co-author Professor Sir Colin Humphreys of Cambridge’s Department of Materials Science & Metallurgy, whose main area of research is energy-efficient and cost-effective LEDs. Humphreys was Rouet-Leduc’s supervisor when he was a PhD student at Cambridge.

“Machine learning enables the analysis of datasets too large to handle manually and looks at data in an unbiased way that enables discoveries to be made,” said Rouet-Leduc.

Although the researchers caution that there are multiple differences between a lab-based experiment and a real earthquake, they hope to progressively scale up their approach by applying it to real systems which most resemble their lab system. One such site is in California along the San Andreas Fault, where characteristic small repeating earthquakes are similar to those in the lab-based earthquake simulator. Progress is also being made on the Cascadia fault in the Pacific Northwest of the United States and British Columbia, Canada, where repeating slow earthquakes that occur over weeks or months are also very similar to laboratory earthquakes.

“We’re at a point where huge advances in instrumentation, machine learning, faster computers and our ability to handle massive data sets could bring about huge advances in earthquake science,” said Rouet-Leduc.

Reference:
Bertrand Rouet-Leduc et al. ‘Machine Learning Predicts Laboratory Earthquakes.’ Geophysical Research Letters (2017). DOI: 10.1002/2017GL074677

A group of researchers from the UK and the US have used machine learning techniques to successfully predict earthquakes. Although their work was performed in a laboratory setting, the experiment closely mimics real-life conditions, and the results could be used to predict the timing of a real earthquake.

This is the first time that machine learning has been used to analyse acoustic data to predict when an earthquake will occur.

Colin Humphreys

United Nations Development Programme

Haiti Earthquake

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. For image use please see separate credits above.

Yes

Licence type:

Attribution-Noncommerical

Royal Astronomical Society announces honours

bjb42 — Thu, 21 Jan 2010 00:00:00 +0000

Douglas Gough, Leverhulme Emeritus Fellow, formerly Professor of Theoretical Astrophysics has been awarded the society's highest honour: the Gold Medal for Astronomy.

Professor Gough studied for his BA in mathematics and PhD in astrophysics at Cambridge, returning to the Institute of Astronomy in 1969, becoming Deputy Director in 1993 and then Director from 1999 to 2004.

His main research interests are in the internal dynamics of stars; he discovered early in his career that the sun's oscillations could be used to probe the solar interior.

Holding an internationally leading role over more than four decades in stellar astrophysics, Professor Gough is also an inspiring teacher who has made extensive contributions to education.

Professor Gough said: 'As is the case in so much of modern astrophysics, my scientific contributions are not the result of mere solitary activity, but are the outcome of collaboration with other astrophysicists and astronomers; I thank the many colleagues, now friends, with whom I have had the pleasure of working over the decades.'

Professor of Image Science, Dr Craig Mackay has been awarded ̽��ֱ��Jackson-Gwilt Medal for his long-term work on astronomical instrumentation.

Dr Mackay completed his first degree in physics at the ̽��ֱ�� of Edinburgh and then came to Cambridge to do a PhD in radio astronomy. Since then he has been increasingly interested in the use of modern detectors and computers for astronomical and other applications.

He has worked on a variety of visible and infrared detector systems including one of the main instruments on the Hubble Space Telescope.

Using a technique known as "Lucky Imaging ", his most recent work has given astronomers on ground-based telescopes, images that have three times the resolution of the best pictures from Hubble.

Dr Mackay said "This award is at least in part recognition of the remarkable contribution of British instrument builders to the development of charge coupled device detectors. Now widely used in cameras, video cams and mobile phones, the origins of CCDs were very much in astronomy. It is an excellent example of the way that government investment in astronomy has contributed to British industrial competitiveness."

̽��ֱ��Fowler Prize for astronomy has been awarded to Visiting Researcher Dr Barbara Ercolano for her work and development on the MOCASSIN code, one of the most important astrophysical tools to have been created in the last decade.

Born in Naples, she completed her undergraduate studies at ̽��ֱ�� College London, where she now holds an Advanced Fellowship.

Dr Ercolano completed her post-doctorate at Cambridge in April 2009, but has sustained an ongoing scientific collaboration with the Institute of Astronomy.

She said of the award 'I am absolutely delighted to receive this award from the RAS. I am extremely grateful to my colleagues at UCL, Harvard, the ̽��ֱ�� of Cambridge and elsewhere who have helped, inspired and supported this work over the years.'

̽��ֱ��prizes will be awarded at the 2010 National Astronomy Meeting, which will be held in Glasgow between the 12 and 16 April.

̽��ֱ��Royal Astronomical Society, founded in 1820, encourages and promotes the study of astronomy, solar-system science, geophysics and closely related branches of science.

̽��ֱ��RAS organizes scientific meetings, published international research and review journals, recognizes outstanding achievements, maintains an extensive library and represents UK astronomy nationally and internationally.

For more information please use the links top right of this page.

Cambridge academics have been honoured for their outstanding contribution to astronomy by the Royal Astronomical Society (RAS).

As is the case in so much of modern astrophysics, my scientific contributions are not the result of mere solitary activity, but are the outcome of collaboration with other astrophysicists and astronomers; I thank the many colleagues, now friends, with whom I have had the pleasure of working over the decades.

Professor Douglas Gough

Jeremy Sanders - Institute of Astronomy

Perseus alpha x-rays

This work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page.

Yes