Can Artificial Intelligence be Used to Predict Disasters?
Various U.S. government agencies believe that artificial intelligence (AI) can be used to predict disasters. Generally speaking, most school of thought around this concept applies to war and military operations, but there are clearly other good applications as well – for instance, enhancing utilities’ ability to predict a cyberattack, terroristic infrastructure attack, and of course, weather events.
How AI can Predict Disasters
In the case of military applications, pilot programs are already being conducted. The North American Aerospace Defense Command (NORAD) and U.S. Northern Command (NORTHCOM) conducted a series of 3 AI-prediction experiments during an 8-month period from December 2020 to July 2021. By all accounts, the experiments proved that the technology could be used to predict disasters.
The AI platforms tested are called Gaia, Lattice, and Cosmos. In total, these tools provide real-time situational awareness by compiling and analyzing satellite imagery, reports and data from government agencies and various other sources, data acquired from self-powered sensors, and communications intelligence.
Although the testing was considered a success, as with any kind of AI-enabled technology there are some challenges to overcome. That said, once the kinks are worked out, why couldn’t the technology be expanded to the utility sector? Seems like a natural next step to me.
From a utility emergency preparedness perspective, the ability to actually predict disasters – especially non-weather-related events – is generally lacking. We are great at reacting to major events via restoration and recovery operations, but any kind of non-weather emergency typically catches us off guard.
That’s why the concept of AI-predictive tools is so appealing. If utilities could somehow know days, or even hours, ahead of time prior to a cyberattack or act of terrorism, the appropriate preventative measures could be taken.
So, given the benefits and challenges of the technology, will the utility industry be able to leverage it to better predict disasters like system hacking in the near future? The answer is…I certainly hope so!
