AI in weather and climate science: not the revolution you might think

It feels like there's no escaping AI right now, whether you’re trying to type a sentence without being interrupted by a digital “assistant” or struggling to find a new refrigerator that doesn’t require a Wi-Fi connection for some reason. You’d be forgiven for wondering if we’re in the midst of a quantum leap in tech or whether people are just hyping up a heap of slop. So what should we make of the growing use of AI in weather and climate modeling?

The conversation didn't get off to a great start earlier this year when a National Weather Service office posted a forecast map featuring nonexistent cities in Idaho with names like “Whata Bod” and “Orangeotild.” Thankfully, that was just an AI-generated image produced for social media, not the actual forecast model. Meteorologists and climate scientists are not yet being replaced by large language model prompt engineers. Despite the hype surrounding AI, its role in weather and climate science appears to be more evolutionary than revolutionary.

The technology is being used to augment and improve existing models, rather than replace them entirely. The use of AI in weather and climate modeling does show promise, but its limitations and potential biases must be carefully considered. As the technology continues to develop, it will be important to monitor its progress and assess its impact on the field.

Why this matters: The integration of AI in weather and climate science has significant implications for the broader industry. While AI may not be a panacea for the complex challenges facing meteorologists and climate scientists, it has the potential to improve forecasting accuracy and enhance our understanding of the climate. For developers, this means investing in AI research and development that prioritizes transparency, accountability, and collaboration with domain experts.

For businesses and consumers, this could mean more accurate and reliable weather forecasts, which can inform decision-making and mitigate the impacts of extreme weather events. However, there are also open questions about the potential risks and limitations of AI in weather and climate science, including issues related to data quality, model interpretability, and the need for ongoing evaluation and validation.