From hurricanes and floods to volcanoes and earthquakes, the Earth is continuously evolving in fits and spurts of dramatic activity. Earthquakes and subsequent tsunamis alone have caused massive destruction in the last decade—even over the course of writing this post, there were earthquakes in New Caledonia, Southern California, Iran, and Fiji, just to name a few.

Earthquakes typically occur in sequences: an initial “mainshock” (the event that usually gets the headlines) is often followed by a set of “aftershocks.” Although these aftershocks are usually smaller than the main shock, in some cases, they may significantly hamper recovery efforts.  Although the timing and size of aftershocks has been understood and explained by established empirical laws, forecasting the locations of these events has proven more challenging.

We teamed up with machine learning experts at Google to see if we could apply deep learning to explain where aftershocks might occur, and today we’re publishing a paper on our findings. But first, a bit more about how we got here: we started with a database of information on more than 118 major earthquakes from around the world.

From there, we applied a neural net to analyze the relationships between static stress changes caused by the mainshocks and aftershock locations. The algorithm was able to identify useful patterns.  

The end result was an improved model to forecast aftershock locations and while this system is still imprecise, it’s a motivating step forward. Machine learning-based forecasts may one day help deploy emergency services and inform evacuation plans for areas at risk of an aftershock.

There was also an unintended consequence of the research: it helped us to identify physical quantities that may be important in earthquake generation. When we applied neural networks to the data set, we were able to look under the hood at the specific combinations of factors that it found important and useful for that forecast, rather than just taking the forecasted results at face value. This opens up new possibilities for finding potential physical theories that may allow us to better understand natural phenomena.

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.

We think everyone should be able to express themselves online, so we want to make conversations more inclusive. That’s why we created tools like Perspective, an API that uses machine learning to detect abuse and harassment online. Perspective scores comments based on their similarity to other comments that others have marked as toxic.

However, sometimes the labels we use to describe ourselves and our loved ones can be used in a negative way to harass people online. And because machine learning models like the one used for Perspective are sensitive to the data sets on which they are trained, that means they might make the mistake of identifying sentences that use words like “gay,” “lesbian” or “transgender” in positive ways as negative. (Within the ML community, we talk about this as insufficient diversity in the training data.)

That’s why we created Project Respect. We’re creating an open dataset that collects diverse statements from the LGBTIQ+ community, such as “I’m gay and I’m proud to be out” or “I’m a fit, happy lesbian that has just retired from a wonderful career” to help reclaim positive identity labels. These statements from the LGBTIQ+ community and their supporters will be made available in an open dataset, which coders, developers and technologists all over the world can use to help teach machine learning models how the LGBTIQ+ community speak about ourselves. The hope is that by expanding the diversity of training data, these models will be able to better parse what’s actually toxic and what’s not.

We launched the Project Respect site in March. But we need more input and help to make conversations more inclusive, so we’ve begun taking Project Respect on tour to Pride events around the world—starting in Sydney and Auckland before coming to San Francisco Pride last month. We’ll continue to roll out in other parts of the world, meaning the data we gather will represent the LGBTIQ+ community on a global scale.

LGBTIQ+ individuals should feel safe and accepted wherever they are, both in the real world and online. That’s why efforts like Project Respect are important, and why we hope you’ll share your positive identity statement about yourself or the people you love in the LGBTIQ+ community. Share your statement at g.co/projectrespect

http://g.co/projectrespect

 to help make conversations more inclusive.