The researchers argue, convincingly, that the climate models need to be improved so they more accurately predict the locations that are likely to see more extreme weather, so locals can learn and plan accordingly. They make a couple of suggestions for how the models can be improved. One is to make them higher-resolution, so that the small local hotspots can be more clearly identified — though, unfortunately, we can’t go back in time to make the last 75 years of data collection more granular, so, at least in the short term, this might be difficult. They also argue that new AI technologies might help generate more accurate models, but they note that machine-learning algorithms don’t explain the reasoning behind the model, so we might get better predictions without understanding the “why” behind them.