🔗 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 major tropical system.

Serving as lead forecaster on duty, he predicted that in a single day the weather system would become a severe hurricane and start shifting in the direction of the Jamaican shoreline. Not a single expert had previously made such a bold prediction for rapid strengthening.

But, Papin had an ace up his sleeve: AI technology in the form of Google’s recently introduced 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.

Growing Reliance on Artificial Intelligence Predictions

Forecasters are heavily relying upon the AI system. During 25 October, Papin explained in his official briefing that Google’s model was a primary reason for his certainty: “Approximately 40/50 AI simulation runs show Melissa reaching a most intense hurricane. While I am unprepared to predict that strength yet given track uncertainty, that is still plausible.

“There is a high probability that a phase of quick strengthening is expected as the storm drifts over very warm ocean waters which is the most extreme marine thermal energy in the entire Atlantic basin.”

Surpassing Conventional Models

Google DeepMind is the first artificial intelligence system focused on tropical cyclones, and currently the first to beat traditional meteorological experts at their specialty. Across all 13 Atlantic storms this season, Google’s model is top-performing – even beating human forecasters on path forecasts.

Melissa eventually made landfall in Jamaica at category 5 intensity, one of the strongest coastal impacts ever documented in almost 200 years of record-keeping across the Atlantic basin. Papin’s bold forecast likely gave people in Jamaica extra time to prepare for the disaster, possibly saving people and assets.

How The Model Functions

Google’s model works by identifying trends that traditional time-intensive physics-based weather models may overlook.

“They do it much more quickly than their traditional counterparts, and the processing requirements is less expensive and time consuming,” said Michael Lowry, a ex forecaster.

“What this hurricane season has proven in quick time is that the recent AI weather models are on par with and, in some cases, more accurate than the slower physics-based forecasting tools we’ve relied upon,” Lowry added.

Clarifying Machine Learning

To be sure, Google DeepMind is an example of machine learning – a technique that has been used in research fields like weather science for a long time – and is distinct from creative artificial intelligence like ChatGPT.

AI training processes mounds of data and extracts trends from them in a manner that its system only requires minutes to generate an result, and can do so on a desktop computer – in strong contrast to the primary systems that governments have used for years that can take hours to process and require some of the biggest supercomputers in the world.

Professional Responses and Upcoming Advances

Nevertheless, the fact that the AI could outperform previous gold-standard traditional systems so rapidly is nothing short of amazing to meteorologists who have dedicated their lives trying to predict the world’s strongest weather systems.

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

Franklin noted that while Google DeepMind is beating all other models on predicting the trajectory of storms globally this year, similar to other systems it sometimes errs on extreme strength forecasts inaccurate. It struggled with another storm previously, as it was also undergoing quick strengthening to category 5 above the Caribbean.

During the next break, Franklin stated he plans to discuss with the company about how it can enhance the AI results more useful for forecasters by providing additional internal information they can use to assess the reasons it is producing its conclusions.

“The one thing that troubles me is that while these predictions seem to be highly accurate, the results of the model is kind of a opaque process,” remarked Franklin.

Wider Sector Trends

There has never been a private, for-profit company that has produced a high-performance weather model which allows researchers a peek into its techniques – unlike most other models which are provided at no cost to the public in their full form by the governments that created and operate them.

Google is not alone in adopting AI to address challenging meteorological problems. The authorities are developing their own AI weather models in the development phase – which have also shown improved skill over earlier traditional systems.

The next steps in AI weather forecasts appear to involve new firms tackling previously difficult problems such as sub-seasonal outlooks and improved early alerts of severe weather and flash flooding – and they are receiving US government funding to do so. One company, WindBorne Systems, is also deploying its proprietary weather balloons to fill the gaps in the national monitoring system.