Accelerating Exploration of Marine Cloud Brightening Impacts on Tipping Points Using an AI Implementation of Fluctuation-Dissipation Theorem.

Haruki Hirasawa, Soo Kyung Kim, Peetak Mitra, Subhashis Hazarika, Salva Rühling Cachay, Dipti Swapnil Hingmire, Kalai Ramea, Hansi Singh, philip Rasch

Keywords: climate intervention, climate change, fluctuation dissipation theorem

Abstract:

Marine cloud brightening (MCB) is a proposed climate intervention
technology to partially offset greenhouse gas warming
and possibly avoid crossing climate tipping points. The
climate impacts of MCB are typically estimated using computationally
expensive Earth System Model (ESM) simulations,
preventing a thorough assessment of the large possibility
space of MCB intervention patterns. Here, we describe
an AI model, named AiBEDO, that can be used to
rapidly project climate responses via a novel application of
the Fluctuation-Dissipation Theorem (FDT). AiBEDO is a
Multilayer Perceptron (MLP) model that maps from monthlymean
radiation anomalies to surface climate anomalies at a
range of time lags. By leveraging a internal climate noise
from a large existing dataset of ESM simulations, we use
AiBEDO to construct an FDT operator that successfully
projects the pattern of MCB climate responses when evaluated
against ESM simulations. We propose that AiBEDO
could be used to identify MCB forcing patterns to that reduce
tipping point risks while minimizing negative side effects in
other parts of the climate.