🔗 Share this article

As Tropical Storm Melissa was churning off the coast of Haiti, weather expert Philippe Papin had confidence it was about to grow into a monster hurricane.

Serving as lead forecaster on duty, he forecasted that in just 24 hours the storm would intensify into a category 4 hurricane and start shifting in the direction of the Jamaican shoreline. No forecaster had previously made such a bold prediction for quick intensification.

But, Papin had an ace up his sleeve: artificial intelligence in the guise of the tech giant’s new DeepMind cyclone prediction system – released for the first time in June. True to the forecast, Melissa did become a storm of remarkable power that ravaged Jamaica.

Growing Dependence on Artificial Intelligence Forecasting

Meteorologists are increasingly leaning hard on Google DeepMind. On the morning of 25 October, Papin explained in his public discussion that Google’s model was a primary reason for his confidence: “Approximately 40/50 AI ensemble members show Melissa reaching a Category 5 hurricane. While I am unprepared to predict that strength yet due to path variability, that is still plausible.

“It appears likely that a phase of quick strengthening is expected as the storm drifts over exceptionally hot ocean waters which is the most extreme oceanic heat content in the whole Atlantic basin.”

Outperforming Traditional Models

Google DeepMind is the pioneer artificial intelligence system focused on hurricanes, and now the first to outperform standard meteorological experts at their own game. Across all tropical systems this season, the AI is top-performing – even beating human forecasters on track predictions.

Melissa eventually made landfall in Jamaica at category 5 strength, among the most powerful landfalls ever documented in almost 200 years of record-keeping across the Atlantic basin. The confident prediction probably provided people in Jamaica additional preparation time to prepare for the disaster, possibly saving people and assets.

The Way Google’s System Functions

Google’s model operates through identifying trends that conventional lengthy physics-based prediction systems may overlook.

“The AI performs much more quickly than their traditional counterparts, and the computing power is less expensive and demanding,” stated Michael Lowry, a former meteorologist.

“This season’s events has demonstrated in quick time is that the newcomer AI weather models are competitive with and, in some cases, superior than the slower physics-based weather models we’ve relied upon,” Lowry said.

Understanding Machine Learning

To be sure, Google DeepMind is an example of AI training – a technique that has been used in research fields like meteorology for a long time – and is distinct from generative AI like ChatGPT.

Machine learning processes mounds of data and pulls out patterns from them in a manner that its model only takes a few minutes to come up with an result, and can operate on a standard PC – in strong contrast to the primary systems that authorities have used for years that can take hours to process and need the largest high-performance systems in the world.

Expert Responses and Future Developments

Still, the fact that Google’s model could outperform previous gold-standard traditional systems so quickly is nothing short of amazing to weather scientists who have spent their careers trying to forecast the most intense weather systems.

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

Franklin noted that while Google DeepMind is beating all competing systems on forecasting the trajectory of hurricanes globally this year, like many AI models it sometimes errs on high-end intensity predictions wrong. It had difficulty with Hurricane Erin earlier this year, as it was similarly experiencing quick strengthening to category 5 above the Caribbean.

In the coming offseason, he said he intends to talk with Google about how it can make the DeepMind output more useful for forecasters by providing additional under-the-hood data they can use to evaluate exactly why it is producing its answers.

“The one thing that nags at me is that although these forecasts appear highly accurate, the output of the model is essentially a opaque process,” remarked Franklin.

Wider Sector Trends

Historically, no a private, for-profit company that has produced a top-level forecasting system which allows researchers a view of its techniques – in contrast to most systems which are provided at no cost to the public in their full form by the governments that created and operate them.

The company is not alone in starting to use AI to solve difficult weather forecasting problems. The authorities are developing their respective artificial intelligence systems in the development phase – which have demonstrated better performance over earlier non-AI versions.

Future developments in artificial intelligence predictions appear to involve startup companies taking swings at previously tough-to-solve problems such as sub-seasonal outlooks and improved advance warnings of tornado outbreaks and sudden deluges – and they have secured US government funding to pursue this. A particular firm, WindBorne Systems, is also launching its own atmospheric sensors to fill the gaps in the US weather-observing network.