Weather forecasts are expected to become more accurate in the future thanks to artificial intelligence. Forecasters at the National Weather Service are already using AI on a daily basis and say they have high hopes for what AI can do in the next 5 to 10 years.
Chris Strong has been a forecaster at the National Weather Service in Sterling, Virginia for 30 years now, which means he's seen big shifts in technology. One of the new things his team is using to predict the weather is AI.
"We are starting to use AI in our modeling as well," Strong said.
Strong takes you into how AI can help with weather forecasting
"It's really going to be transformative. It's going to be another big jump in technology which is going to open a lot of things that we don't foresee now," Strong said.
Current weather forecasts rely on three things: climatology, observations, and mathematical equations to predict where storms will end up. But Strong says AI works a little different by placing a larger emphasis on past events that have occurred.
"When your using AI for weather forecasting you are looking at patterns of the past to figure out what's going to happen in the future," Strong said.
Weather forecasting requires a lot of computing power, and it takes several hours for a weather model to take observations and turn it into a forecast. But Strong says AI can process this information much faster, allowing for quick forecasts.
"It's allowing us to model the weather in different ways we can with less computing power see what the atmosphere will do in the future based on its past," Strong said.
Strong says there are some pitfalls to using AI, such as when there is a once-in-a-century type of storm.
"By looking just at pattern recognition it can sometimes go off the rails and can forecast things that can't happen," Strong said.
This is because the technology relies heavily on previous events to forecast future events, meaning weather events that are uncommon but catastrophic, such as the flooding events in Ellicott City or Superstorm Sandy, will be harder for AI to predict.
"Is it all of a sudden going to be a light switch with the forecast never being wrong again? No. But it will continue to improve our accuracy and continue to improve our skill," Strong said.
Strong is most excited to see how AI performs when it comes to severe storms.
"One of the things I'm excited to see is the visualisation of those forecasts. So rather than being able to tell people, especially when it comes to dangerous weather, this severe thunderstorm is coming. If you can actually show a quick video 'this is what It's going to look like 20 minutes from now', people will be more likely to respond and protect themselves," Strong said.
When asked if he's worried AI could be coming for his job, Strong said human forecasters will still be needed.
"We're always going to need people to take the data, take the information and convey it to people so working with the public, working with emergency managers, snow plow groups in the winter time, you're always going to need that connection from the computing and the modeling to action and people," Strong said.
It's important to note that forecasters say they need to test AI's ability to forecast and then verify the accuracy of those forecasts based on observations, a process that will take many years. But the future looks hopeful.
This story was reported on-air by a journalist and has been converted to this platform with the assistance of AI. Our editorial team verifies all reporting on all platforms for fairness and accuracy.
