A group of Harvard scientists formed an intellectual research team adjoined with the tech giants of renowned IT firm Google for inventing innovative application using machine learning, which will be capable to predict where earthquake and aftershocks may occur. This innovative initiative will help to reduce the devastating impact of natural calamities on the lives and valuable infrastructure in this world in the future.
Most of the time, earthquakes occur sequentially – a commencing “mainshock” pursued by a series of “aftershocks”. Though the impacts of these aftershocks are smaller in magnitude, they affect the recovery and rescue efforts diversely and significantly.
Phoebe Devries the Post-Doctoral fellow at Harvard said in the Google Blogspot, that after estimating the size of aftershocks which is interpreted by the established factual laws, predicting the actual locations of the natural disaster has been proven quite challenging.
She added machine-learning based applications can forecast before the disaster and it helps greatly to unfold the emergency services and to make reach the significant alert to the specific areas which can be at risk due to the aftershock.
She said, “ We teamed up with machine learning experts at Google to see if we could apply deep learning to explain where aftershocks might occur ….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 defined that the team will use the specific and researched database information for forecasting the alert of earthquakes across the world.
She said, “ A neural net will be applied to analyze the relationship between static stress changes caused by the mainshocks and aftershock locations, and the algorithm will be able to identify usage patterns. The end result will be an improved model to forecast aftershock locations and while this system is still imprecise, it’s a motivating step forward.”