🔗 Share this article

As Tropical Storm Melissa was churning off the coast of Haiti, meteorologist Philippe Papin had confidence it would soon grow into a monster hurricane.

As the primary meteorologist on duty, he predicted that in just 24 hours the weather system would intensify into a severe hurricane and start shifting towards the coast of Jamaica. No forecaster had ever issued this confident forecast for rapid strengthening.

But, Papin possessed a secret advantage: AI technology in the guise of the tech giant’s recently introduced DeepMind cyclone prediction system – released for the initial occasion in June. And, as predicted, Melissa evolved into a storm of astonishing strength that tore through Jamaica.

Increasing Dependence on AI Forecasting

Forecasters are increasingly leaning hard on Google DeepMind. On the morning of 25 October, Papin clarified in his official briefing that the AI tool was a primary reason for his certainty: “Roughly 40/50 Google DeepMind simulation runs show Melissa becoming a Category 5 hurricane. Although I am unprepared to forecast that intensity at this time given track uncertainty, that remains a possibility.

“There is a high probability that a phase of quick strengthening is expected as the storm drifts over very warm sea temperatures which represent the most extreme oceanic heat content in the entire Atlantic basin.”

Surpassing Traditional Systems

The AI model is the first artificial intelligence system focused on hurricanes, and currently the first to outperform traditional weather forecasters at their specialty. Through all tropical systems so far this year, the AI is top-performing – surpassing experts on track predictions.

Melissa ultimately struck in Jamaica at category 5 intensity, one of the strongest coastal impacts recorded in nearly two centuries of data collection across the region. The confident prediction likely gave residents additional preparation time to prepare for the disaster, possibly saving lives and property.

How Google’s Model Works

The AI system operates through identifying trends that traditional time-intensive physics-based prediction systems may overlook.

“The AI performs far faster than their traditional counterparts, and the computing power is more affordable and demanding,” said Michael Lowry, a former meteorologist.

“This season’s events has proven in quick time is that the recent artificial intelligence systems are competitive with and, in some cases, more accurate than the less rapid physics-based forecasting tools we’ve relied upon,” he said.

Understanding Machine Learning

To be sure, the system is an example of AI training – a method that has been used in data-heavy sciences like weather science for a long time – and is distinct from creative artificial intelligence like ChatGPT.

AI training processes large datasets and pulls out patterns from them in a such a way that its system only takes a few minutes to generate an result, and can do so on a desktop computer – in sharp difference to the primary systems that authorities have utilized for years that can require many hours to process and require the largest high-performance systems in the world.

Expert Reactions and Upcoming Developments

Still, the fact that Google’s model could outperform earlier gold-standard legacy models so quickly is truly remarkable to meteorologists who have spent their careers trying to forecast the most intense weather systems.

“It’s astonishing,” said James Franklin, a former forecaster. “The data is sufficient that it’s pretty clear this is not just beginner’s luck.”

Franklin noted that although Google DeepMind is beating all competing systems on forecasting the future path of storms worldwide this year, like many AI models it sometimes errs on extreme strength predictions wrong. It struggled with Hurricane Erin earlier this year, as it was similarly experiencing quick strengthening to maximum intensity north of the Caribbean.

In the coming offseason, he stated he plans to talk with the company about how it can make the DeepMind output even more helpful for forecasters by offering extra internal information they can utilize to assess the reasons it is producing its answers.

“A key concern that nags at me is that while these predictions seem to be really, really good, the output of the model is kind of a black box,” said Franklin.

Broader Sector Developments

There has never been a commercial entity that has produced a top-level weather model which grants experts a view of its methods – unlike most other models which are offered free to the general audience in their entirety by the governments that created and operate them.

The company is not the only one in starting to use AI to address challenging weather forecasting problems. The US and European governments also have their respective AI weather models in the development phase – which have demonstrated improved skill over previous non-AI versions.

Future developments in AI weather forecasts seem to be new firms taking swings at formerly difficult problems such as sub-seasonal outlooks and improved advance warnings of tornado outbreaks and flash flooding – and they have secured federal support to do so. One company, WindBorne Systems, is also deploying its proprietary atmospheric sensors to fill the gaps in the national monitoring system.