AiBEDO: A hybrid AI model to capture the effects of cloud properties on global circulation and regional climate patterns

Kalai Ramea, Sookyung Kim, Peetak Mitra, Subhashis Hazarika, Haruki Hirasawa, Dipti Hingmire, Philip John Rasch, Hansi Singh

Preprint · 17 January 2023

Paper PDF

In one sentence. Hybrid AI surrogate links cloud radiative effects to large-scale circulation and regional climate, enabling low-cost scenario runs for cloud-based climate intervention.

Abstract

Clouds play a vital role both in modulating Earth's radiation budget and shaping the coupled circulation of the atmosphere and ocean, driving regional changes in temperature and precipitation. However, the climate response to changing clouds is one of the largest uncertainties in Earth System Models (ESM) when producing decadal (and longer) climate projections. This limitation becomes apparent especially when analyzing scenarios with large changes in cloud properties, e.g., the presence of greenhouse gases (leading to loss of clouds or engineered interventions (leading to higher cloud reflectivity. Data-driven and hybrid physics-informed surrogate models have the potential to accelerate ESM simulations, with many recent investigations focusing on using deep learning to improve sub-grid scale processes in ESMs. There has not been any effort thus far to develop a hybrid AI model to characterize the complex, multi-timescale relationships between the radiative effects of clouds and the large-scale climate response, particularly in the context of optimizing cloud radiative forcing (intervention) strategies to avoid climate tipping points. AiBEDO is the pioneering effort that addresses the weaknesses of ESMs and provides a framework that enables the modeler to run scenarios at extremely low computational cost.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.