Experts: How are climate scientists using artificial intelligence?

According to Carbon Brief, from weather forecasting to analysing satellite images, climate scientists are using various types of AI to develop faster and more efficient ways to study the warming planet.[1]The outlet also reports that the technology comes with no shortage of risks and challenges, including overreliance on unverified results, intensive energy use and exacerbating existing inequalities in climate science.[1]Dr Amirpasha Mozaffari of the Barcelona Supercomputing Centre told Carbon Brief that AI forecast models "underperform physics-based models on record-breaking and unprecedented extremes"[1]. He called solving that "the central open problem for the field."[1]One expert quoted by Carbon Brief said that for the IPCC's seventh assessment report, "for the very first time, there's a model intercomparison project just for models using AI"[1], and called it "a real milestone"[1].Another contributor said that new machine-learning methods used to take two or three years to reach climate work, but "today it is a matter of months"[1].Prof Detlef van Vuuren of the PBL Netherlands Environmental Assessment Agency told Carbon Brief that "there are now many more proposals being submitted than in the past, as people can use AI tools."[1]A further expert warned in the piece that "the first and foremost risk is AI diverging attention from other forms of climate action. AI is not a silver bullet."[1]