🔗 Share this article

When Tropical Storm Melissa swirled south of Haiti, meteorologist Philippe Papin felt certain it would soon escalate to a major tropical system.

As the primary meteorologist on duty, he predicted that in a single day the storm would become a severe hurricane and start shifting towards the Jamaican shoreline. Not a single expert had previously made such a bold forecast for rapid strengthening.

However, Papin had an ace up his sleeve: AI technology in the guise of the tech giant’s recently introduced DeepMind cyclone prediction system – released for the initial occasion in June. True to the forecast, Melissa did become a system of remarkable power that tore through Jamaica.

Increasing Dependence on AI Forecasting

Forecasters are heavily relying upon Google DeepMind. On the morning of 25 October, Papin explained in his public discussion that Google’s model was a primary reason for his certainty: “Roughly 40/50 AI simulation runs indicate Melissa becoming a Category 5 storm. Although I am not ready to forecast that strength at this time due to path variability, that is still plausible.

“There is a high probability that a phase of rapid intensification is expected as the system moves slowly over very warm sea temperatures which represent the highest oceanic heat content in the whole Atlantic basin.”

Outperforming Conventional Systems

Google DeepMind is the first AI model dedicated to tropical cyclones, and now the first to beat standard weather forecasters at their own game. Through all 13 Atlantic storms this season, the AI is top-performing – even beating experts on track predictions.

The hurricane eventually made landfall in Jamaica at category 5 intensity, among the most powerful landfalls ever documented in almost 200 years of data collection across the region. Papin’s bold forecast probably provided residents extra time to get ready for the disaster, possibly saving people and assets.

How Google’s System Functions

The AI system operates through identifying trends that conventional time-intensive physics-based weather models may overlook.

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

“What this hurricane season has demonstrated in short order is that the recent AI weather models are competitive with and, in some cases, superior than the less rapid traditional weather models we’ve relied upon,” he added.

Clarifying AI Technology

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

Machine learning takes large datasets and pulls out patterns 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 desktop computer – in strong contrast to the primary systems that governments have used for decades that can take hours to process and require the largest high-performance systems in the world.

Expert Reactions and Upcoming Advances

Still, the reality that the AI could exceed earlier top-tier legacy models so rapidly is nothing short of amazing to weather scientists who have dedicated their lives trying to predict the most intense storms.

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

Franklin said that although Google DeepMind is outperforming all competing systems on forecasting the trajectory of storms worldwide this year, similar to other systems it sometimes errs on extreme strength forecasts wrong. It had difficulty with another storm previously, as it was also undergoing quick strengthening to category 5 north of the Caribbean.

In the coming offseason, he stated he plans to discuss with the company about how it can enhance the DeepMind output even more helpful for experts by providing extra internal information they can utilize to evaluate exactly why it is coming up with its conclusions.

“A key concern that nags at me is that while these predictions appear highly accurate, the output of the model is essentially a black box,” remarked Franklin.

Wider Industry Developments

There has never been a commercial entity that has developed a top-level forecasting system which allows researchers a peek into its techniques – in contrast to nearly all other models which are provided free to the public in their full form by the authorities that designed and maintain them.

The company is not the only one in starting to use AI to address difficult weather forecasting problems. The authorities are developing their respective AI weather models in the development phase – which have also shown better performance over earlier traditional systems.

The next steps in AI weather forecasts appear to involve new firms taking swings at formerly tough-to-solve problems such as long-range forecasts and better advance warnings of severe weather and flash flooding – and they have secured US government funding to pursue this. One company, WindBorne Systems, is also deploying its proprietary atmospheric sensors to fill the gaps in the US weather-observing network.