*This item and others will be in the monthly “Solar Geoengineering Updates Substack” newsletter:* https://solargeoengineeringupdates.substack.com/ -----------------------------------------------------------------
https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2023GL106137 *Authors* Antonios Mamalakis, Elizabeth A. Barnes, James W. Hurrell *First published: 12 October 2023* https://doi.org/10.1029/2023GL106137 *Abstract* Stratospheric aerosol injection (SAI) has been proposed as a possible response option to limit global warming and its societal consequences. However, the climate impacts of such intervention are unclear. Here, an explainable artificial intelligence (XAI) framework is introduced to quantify how distinguishable an SAI climate might be from a pre-deployment climate. A suite of neural networks is trained on Earth system model data to learn to distinguish between pre- and post-deployment periods across a variety of climate variables. The network accuracy is analogous to the “climate distinguishability” between the periods, and the corresponding distinctive patterns are identified using XAI methods. For many variables, the two periods are less distinguishable under SAI than under a no-SAI scenario, suggesting that the specific intervention modeled decelerates future climatic changes and leads to a less novel climate than the no-SAI scenario. Other climate variables for which the intervention has negligible effect are also highlighted. *Key Points* An explainable artificial intelligence framework is introduced to quantify the “climate distinguishability” after a climate intervention The distinctive patterns between the pre- and post-intervention climates are not predefined but are learned directly from the data For the climate simulations analyzed, stratospheric aerosol injection is shown to reduce distinguishability for some climate variables *Plain Language Summary* We use Earth system model predictions for two scenarios of the future: one policy-relevant climate change scenario where global temperatures continue rising in the coming decades, and that same scenario but with humans intervening in the climate system to limit warming to 1.5°C. We then train a machine to learn to classify annual maps of climate variables based on whether they originate from the period before or after the intervention. The more successful the machine is at this task, the more distinguishable the pre- and post-intervention periods are with respect to the variable analyzed. Our results show that for many climate variables, the two periods are less distinguishable under the climate intervention scenario than the no-intervention scenario. In those cases, the intervention ends up decelerating future climate change. However, we also show that there are important climate variables for which the intervention has a negligible effect. *Source: AGU* -- You received this message because you are subscribed to the Google Groups "geoengineering" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/geoengineering/CAHJsh99ahxBoTC%3DEQUV1RU%3D9vC8%3DE9UYs52KE6fFKkF9UWurrQ%40mail.gmail.com.
