Artificial Intelligence for Disaster Relief: A Primer

  2 m, 37 s

Governments and agencies are struggling to coordinate effective disaster relief programs. Artificial intelligence (AI), machine learning (ML), and natural language processing can help. Here’s how.

The cost of natural disasters

<billion-dollar disaster relief events><noscript><img src=Natural disasters wreak havoc around the world every year. Just 15 events caused more than $22 billion in damages in 2017, according to the National Oceanic and Atmospheric Administration. That’s just in the United States, and doesn’t include the Northern California Wildfires or the biggest hurricanes. Hurricane Harvey’s price tag will probably top $190 billion, according to USA Today. Hurricanes Irma ($64-92 billion) and Maria ($40-80 billion) reduced much of Puerto Rico, the U.S. Virgin Islands, and the Caribbean to ruins. And the humanitarian impact is incalculable.

But these numbers only tell part of the story.

Image source:

Disaster relief programs are struggling

In late September, CNN reported that 10,000 supply containers were sitting at San Juan Port in Puerto Rico, while officials struggled to distribute them effectively. This is not an isolated case. Governments around the world are struggling to coordinate effective, efficient programs. There’s lots of data out there, but making of use of it is easier said than done. Disaster data is often fragmented, incomplete, or difficult to access. The scope is challenging, too. There’s just so much data out there.

Relief agencies and governments need to turn this information into useful insights. But while many techniques for processing crisis data already exist (satellite imagery and seismometers, for example), the technology often fall short. Experts are looking for new ways.

Enter AI and machine learning

Recent advances in machine learning and artificial intelligence are allowing researchers, engineers, and scientists to access and analyze new and bigger data sources than ever before. By combining AI and ML with data analytics technologies like natural language processing, experts are creating a new breed of AI. These systems enable their users to ask specific, targeted questions and receive useful answers drawn from messy, real-world datasets. Governments and relief agencies are leveraging these smarter analytics tools to improve their ability coordinate effective, efficient, disaster relief programs.

Smarter analysis, better disaster relief

<disaster relief twitter pattern><noscript><img src=

Some of the most-actionable information during a crisis comes from citizens, social media users, and on-the-ground aid workers. Images and comments from Twitter, Facebook, Instagram, and Youtube can help experts make initial damage assessments. This info can also help rescue workers find more victims in less time. In addition, social media posts can help relief workers identify and map new disaster sites in need of aid. Other digital content from Twitter, Facebook, and even Youtube can provide early warnings, ground-level location data, and real-time report verification.

Larger-scale behavior and movement data, run through predictive machine learning models, can help officials distribute supplies to where people are going, rather than where they were. Predictive programs like these are still in their early stages, but offer a promising new approach to disaster relief.

Further reading

Categories: Artificial Intelligence, Insights, Machine Learning, Special Interest