How Machine Learning Could Predict Rare Disastrous Events – Like Earthquakes or Pandemics

A team of researchers has developed a new framework which utilizes advanced machine learning and statistical algorithms to predict rare events without the need for large data sets. Scientists can use a combination of advanced machine learning and sequential sampling techniques to predict extreme events without the need for large data sets, according to researchers from Brown and MIT. When it comes to predicting disasters brought on by extreme events (think earthquakes, pandemics, or "rogue waves" that could destroy coastal structures), computational modeling faces an almost insurmountable challenge: Statistically speaking, these events are so rare that there's just not enough data on them to use predictive models to accurately forecast when they'll happen next. However, a group of scientists from Brown University and Massachusetts Institute of Technology suggests that it doesn't have to be that way. In a study published in Nature Computational Science, the researchers explain how they utilized statistical algorithms which require less data for accurate predictions, in combination with a powerful machine learning technique developed at Brown University.