🔗 Share this article

When Tropical Storm Melissa swirled off the coast of Haiti, weather expert Philippe Papin had confidence it was about to escalate to a monster hurricane.

Serving as lead forecaster on duty, he forecasted that in just 24 hours the storm would become a category 4 hurricane and start shifting in the direction of the Jamaican shoreline. Not a single expert had ever issued such a bold prediction for quick intensification.

However, Papin had an ace up his sleeve: artificial intelligence in the form of Google’s recently introduced DeepMind cyclone prediction system – launched for the first time in June. And, as predicted, Melissa evolved into a system of remarkable power that tore through Jamaica.

Growing Reliance on AI Forecasting

Forecasters are increasingly leaning hard on Google DeepMind. During 25 October, Papin clarified in his official briefing that Google’s model was a primary reason for his confidence: “Approximately 40/50 Google DeepMind simulation runs indicate Melissa reaching a most intense storm. While I am not ready to forecast that strength yet given track uncertainty, that is still plausible.

“There is a high probability that a period of rapid intensification is expected as the system moves slowly over very warm ocean waters which is the most extreme marine thermal energy in the entire Atlantic basin.”

Surpassing Traditional Systems

The AI model is the first AI model dedicated to tropical cyclones, and currently the initial to outperform traditional meteorological experts at their own game. Through all tropical systems this season, the AI is top-performing – surpassing human forecasters on path forecasts.

Melissa ultimately struck in Jamaica at category 5 intensity, among the most powerful landfalls ever documented in almost 200 years of record-keeping across the region. Papin’s bold forecast likely gave people in Jamaica extra time to get ready for the disaster, potentially preserving people and assets.

The Way The System Works

Google’s model operates through identifying trends that conventional time-intensive scientific weather models may overlook.

“The AI performs far faster than their physics-based cousins, and the processing requirements is more affordable and demanding,” said Michael Lowry, a ex forecaster.

“This season’s events has proven in short order is that the recent AI weather models are on par with and, in certain instances, superior than the slower physics-based weather models we’ve traditionally leaned on,” Lowry said.

Understanding Machine Learning

It’s important to note, the system is an instance of AI training – a technique that has been employed in research fields like weather science for years – and is distinct from generative AI like ChatGPT.

Machine learning takes mounds of data and extracts trends from them in a such a way that its model only requires minutes to come up with an result, and can do so on a standard PC – in sharp difference to the flagship models that authorities have used for years that can take hours to run and need the largest supercomputers in the world.

Expert Reactions and Future Advances

Still, the fact that the AI could outperform earlier top-tier traditional systems so rapidly is truly remarkable to weather scientists who have dedicated their lives trying to predict the world’s strongest weather systems.

“I’m impressed,” commented James Franklin, a retired forecaster. “The data is sufficient that it’s pretty clear this is not just beginner’s luck.”

He noted that while Google DeepMind is outperforming all other models on forecasting the trajectory of storms globally this year, similar to other systems it sometimes errs on high-end intensity predictions inaccurate. It struggled with Hurricane Erin earlier this year, as it was similarly experiencing rapid intensification to maximum intensity above the Caribbean.

During the next break, Franklin said he intends to discuss with Google about how it can make the AI results more useful for experts by providing additional under-the-hood data they can utilize to evaluate exactly why it is producing its answers.

“A key concern that troubles me is that while these forecasts appear really, really good, the results of the system is essentially a opaque process,” remarked Franklin.

Broader Industry Trends

There has never been a commercial entity that has produced a top-level forecasting system which allows researchers a view of its methods – unlike most systems which are offered at no cost to the general audience in their entirety by the governments that designed and maintain them.

Google is not alone in starting to use AI to address difficult meteorological problems. The US and European governments also have their own AI weather models in the works – which have also shown improved skill over previous non-AI versions.

The next steps in artificial intelligence predictions seem to be startup companies tackling previously tough-to-solve problems such as sub-seasonal outlooks and better early alerts of severe weather and flash flooding – and they are receiving federal support to pursue this. One company, WindBorne Systems, is even launching its own atmospheric sensors to address deficiencies in the US weather-observing network.