Fine-tuning the storm forecast with artificial intelligence


Given the death and destruction Hurricane Ian has inflicted on Florida communities, it’s only reasonable to ask: What could have been done to minimize the storm’s deadly impact — and what could be done to mitigate the next to make natural disasters less devastating ?

Of particular concern is that so many Florida residents were caught completely unprepared by the deadly Category 4 storm. It wasn’t her fault. In the days leading up to Hurricane Ian’s landfall, the models used to forecast storms provided conflicting information about Ian’s likely course and intensity.

It didn’t have to be. Recent advances in artificial intelligence have made it possible to model extreme weather events and predict their timing, course and severity with impressive accuracy. AI can also play a pivotal role in alerting the public when a storm is imminent and determining how best to manage a storm’s aftermath.

If we are to avoid another Ian-sized tragedy in the future, the development of these tools and their widespread adoption are absolutely critical.

The damage done by Hurricane Ian was far worse than most expected. According to recent reports, the storm claimed more than 100 lives — and is among the three deadliest storms to hit American soil this century and among the worst to hit Florida since 1935. Even after Ian subsided, the survivors had to deal with massive flooding, power outages and water damage like nothing in recent memory. The psychological distress was also acute, and many survivors will need help to recover from their trauma.

At least some of that suffering and hardship may have been inevitable given the storm’s tremendous strength. But what made Hurricane Ian so catastrophic had less to do with the weather and more to do with the technologies used to predict it.

Consider that as the storm approached, America’s main forecasting model, the Global Forecast System, predicted that Ian would bypass South Florida and hit the Panhandle as a manageable Category 2 storm. Meanwhile, however, an alternative European model, as well as a British model, suggested the storm would actually make landfall in Tampa or South Florida — albeit at a lower intensity than Ian actually delivered.

Such conflicting assessments made it immensely difficult to alert those in the hurricane’s path, organize evacuations, and allocate resources.

All of this suggests that a more consistent forecasting system could have saved lives. And the latest AI technologies are already providing just that.

For example, scientists at NASA’s Jet Propulsion Laboratory have made impressive strides in using machine learning models to better predict the intensity of a hurricane – a task that existing models have long struggled to accomplish. And researchers at Michigan State University recently proposed a “deep learning framework” for predicting a hurricane’s trajectory, which has proven to be significantly more accurate than existing forecast models. Meanwhile, recent work on recurrent neural networks by researchers at Florida International University and Ganzfried Research could improve hurricane trajectory predictions in the near future.

But storm predictions are only part of the challenge of managing natural disasters. Communicating accurate, timely information, assessing storm damage, and effectively allocating resources are also critical to a successful response. Here, too, AI can make a major contribution.

For example, the AI ​​Box developed by Remark AI can be integrated with existing cameras to detect serious wind or flood damage and alert the relevant authorities – all in real time. AI voicebots from companies like Skit can help ensure emergency hotlines and other critical lines of communication remain fully open during a storm, providing timely information to prevent call centers from being overwhelmed during peak demand.

Some AI tools are already making a difference in responding to Hurricane Ian. For example, a collaboration between Google and nonprofit GiveDirectly uses AI to identify communities hardest hit by the storm and send cash assistance to residents via their smartphones.

However, given the potential of AI to revolutionize the way we deal with natural disasters, these tools are still underutilized. And that has to change. As Hurricane Ian demonstrated, relying heavily on outdated technology and systems can be fatal. And by using AI to take the guesswork out of disaster relief, we can ensure that tragedies like the one still unfolding in South Florida are far less common.

Kevin Gerrity is a Naples resident and Chairman of the Greater Naples Fire Commission. He previously served as Chief of Fire for the Cleveland Fire Department.


Comments are closed.