Google, Harvard to use machine learning to predict earthquake aftershock locations

AI earthquakes

AI earthquakes

"This approach is more accurate because it was developed without a strongly held prior belief about where aftershocks ought to occur", DeVries, a post-doctoral fellow at Harvard, told AFP.

Earlier this week, researchers from Harvard University and Google published a study in the journal Nature that details how deep learning techniques could allow for extremely accurate natural disaster aftershock predictions when compared to existing systems.

In order to achieve this, Meade and DeVries started by accessing a database of observations made after over 199 major earthquakes.

Typically, major earthquakes are followed up by aftershocks, which are usually smaller, less intense tremors, but also occasionally quite powerful in their own right.

"We looked at the output of the neural network and then we looked at what we would expect if different quantities controlled aftershock forecasting", she said.

"We are looking forward to seeing what machine learning can do in the future to unravel the mysteries behind earthquakes, in an effort to mitigate their harmful effects", DeVries said.

Victoria Azarenka looking to 'enjoy every second' of US Open return
But who will come out on top? However, the 10-minute heat break between the second and third sets proved a timely boost. Bhambri, who is world No. 96, lost 3-6, 6-7 (3-7), 5-7 to Herbert in a match that lasted almost two and half hours.

Alongside the study, in another article published in Nature, he said that the research specifically had focused on only one set of changes caused by earthquakes but can also affect where aftershocks occur. "Aftershock forecasting in particular is a challenge that's well-suited to machine learning because there are so many physical phenomena that could influence aftershock behavior and machine learning is extremely good at teasing out those relationships".

While it can be hard to predict main earthquakes and/or aftershocks with accuracy due to all the factors that could skew analysis and eliminate the possibility of a one-size-fits-all solution for all earthquakes, the Verge wrote that the use of AI in the Harvard/Google study was noteworthy because the system was able to detect patterns that scientists had previously failed to recognize.

To do that, the researchers utilized a type of artificial intelligence called as deep learning the model of which somewhat the same as the human brain makes connections. "When we first trained the neural network, we noticed it did pretty well at predicting the locations of aftershocks, but we thought it would be important if we could interpret what factors it was finding were important or useful for that forecast".

Nowadays there are many earthquakes play out in phases. "We definitely agree that this work is a motivating beginning, rather than an ending", she said in Nature.

A salient feature of machine learning is predictive analysis.

However, Brendan Meade, a professor of earth and planetary sciences at Harvard and a co-author on the study, said experts are still "a very long way" from any real-time aftershock forecasting. "It's not an idea that's totally out there anymore".

Recommended News

We are pleased to provide this opportunity to share information, experiences and observations about what's in the news.
Some of the comments may be reprinted elsewhere in the site or in the newspaper.
Thank you for taking the time to offer your thoughts.