Will AI Disprove The Much Touted Climate Change-Extreme Weather Link?
h/t potentilla, commenter at Cliscep.com
This Guardian article has come to my attention:
What really piqued my interest was this passage:
Traditional physics-based weather forecasts solve vast numbers of equations to produce their predictions, but GenCast learned how global weather evolves by training on 40 years of historic data generated between 1979 and 2018. This included wind speed, temperature, pressure, humidity and dozens more variables at different altitudes.
For a start, this period doesn’t include the last 6 years of global warming, and in particular the last 18 months of ‘global boiling’. If GenCast, going forward, continues to make accurate weather predictions (particularly extreme weather predictions) based on historical data, and does not get any more accurate when its weather database is updated, then this would be a good test of the validity of the alleged climate change-extreme weather link.
Just as a start, Gencast could be tasked with making weather predictions based on synoptic data covering the periods 1979-2018 and 1985-2024 to analyse if there is any significant difference between the two.
Of course, it will require a lot of electricity to power DeepMind AI to do this, so we might have to abandon wind and solar power - which allegedly will make the weather better - in order to better understand if climate change is in fact making the weather worse!
I don’t see how anyone could trust an AI analysis of climate change. Would it use raw data rather than dishonestly adjusted data? Would it use UHI-corrupted data? Would it take into account all climate variables (which the UN IPCC doesn’t): solar variations, planetary orbital and gravitational variations, solar/ocean-driven ENSO, PDO and AMO cycles and much more including the data which shows that an increase in atmospheric CO2 follows the rise in global temperature rather than coming before it and causing it?
In other words, would it be programmed by the same corrupt deep state professional liars who are pushing the fake climate change so-called emergency?
If the past proves to be a good guide to the future, then it might suggest (I put it no higher than that) that climate change isn't so extreme as is suggested. It's certainly interesting that AI analysis of past weather produces more accurate weather forecasts than fancy computer models