🔗 Share this article

When Tropical Storm Melissa swirled south of Haiti, meteorologist Philippe Papin had confidence it was about to escalate to a monster hurricane.

As the lead forecaster on duty, he predicted that in just 24 hours the weather system would become a severe hurricane and begin a turn towards the coast of Jamaica. No forecaster had ever issued this confident prediction for rapid strengthening.

But, Papin had an ace up his sleeve: artificial intelligence in the form of Google’s new DeepMind cyclone prediction system – released for the initial occasion in June. True to the forecast, Melissa did become a system of astonishing strength that tore through Jamaica.

Increasing Reliance on Artificial Intelligence Predictions

Forecasters are increasingly leaning hard on the AI system. On the morning of 25 October, Papin clarified in his official briefing that Google’s model was a primary reason for his confidence: “Approximately 40/50 Google DeepMind ensemble members indicate Melissa reaching a most intense storm. While I am not ready to forecast that intensity at this time given track uncertainty, that is still plausible.

“It appears likely that a period of quick strengthening is expected as the system drifts over very warm ocean waters which is the highest marine thermal energy in the whole Atlantic basin.”

Outperforming Traditional Systems

The AI model is the first AI model dedicated to hurricanes, and currently the first to outperform traditional weather forecasters at their own game. Through all tropical systems this season, the AI is top-performing – surpassing experts on track predictions.

The hurricane ultimately struck in Jamaica at maximum strength, one of the strongest landfalls recorded in almost 200 years of data collection across the region. Papin’s bold forecast probably provided people in Jamaica additional preparation time to prepare for the disaster, potentially preserving lives and property.

The Way Google’s System Functions

The AI system works by spotting patterns that traditional time-intensive physics-based prediction systems may overlook.

“The AI performs far faster than their physics-based cousins, and the computing power is more affordable and time consuming,” stated Michael Lowry, a former forecaster.

“This season’s events has demonstrated in short order is that the recent AI weather models are competitive with and, in some cases, superior than the less rapid physics-based forecasting tools we’ve traditionally leaned on,” he said.

Understanding Machine Learning

It’s important to note, Google DeepMind is an instance of machine learning – a technique that has been employed in research fields like meteorology for years – and is not generative AI like ChatGPT.

Machine learning processes large datasets and extracts trends from them in a such a way that its system only takes a few minutes to generate an answer, and can do so on a desktop computer – in sharp difference to the flagship models that governments have utilized for years that can take hours to run and need some of the biggest supercomputers in the world.

Professional Reactions and Upcoming Developments

Nevertheless, the fact that the AI could outperform previous gold-standard legacy models so quickly is truly remarkable to meteorologists who have dedicated their lives trying to predict the most intense storms.

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

He noted that although Google DeepMind is outperforming all competing systems on forecasting the future path of storms worldwide this year, like many AI models it sometimes errs on high-end intensity predictions inaccurate. It had difficulty with another storm earlier this year, as it was similarly experiencing quick strengthening to category 5 north of the Caribbean.

During the next break, Franklin said he intends to discuss with Google about how it can enhance the AI results even more helpful for forecasters by providing extra under-the-hood data they can use to assess the reasons it is coming up with its conclusions.

“A key concern that nags at me is that while these predictions appear really, really good, the results of the model is essentially a opaque process,” remarked Franklin.

Wider Industry Developments

Historically, no a private, for-profit company that has produced a top-level forecasting system which grants experts a peek into its methods – in contrast to most other models which are provided at no cost to the general audience in their full form by the authorities that designed and maintain them.

The company is not alone in adopting AI to address difficult weather forecasting problems. The authorities also have their respective artificial intelligence systems in the development phase – which have also shown better performance over previous non-AI versions.

Future developments in AI weather forecasts seem to be new firms tackling formerly tough-to-solve problems such as long-range forecasts and improved advance warnings of severe weather and flash flooding – and they are receiving federal support to pursue this. A particular firm, WindBorne Systems, is even deploying its proprietary weather balloons to address deficiencies in the US weather-observing network.