Improving Prediction of Marine Low Clouds Using Cloud Droplet Number Concentration in a Convolutional Neural Network DOI Creative Commons
Yang Cao, Yannian Zhu, Minghuai Wang

et al.

Journal of Geophysical Research Machine Learning and Computation, Journal Year: 2024, Volume and Issue: 1(4)

Published: Nov. 30, 2024

Abstract Marine low clouds play a crucial role in cooling the climate, but accurately predicting them remains challenging due to their highly non‐linear response various factors. Previous studies usually overlook effects of cloud droplet number concentration (N d ) and non‐local information target grids. To address these challenges, we introduce convolutional neural network model (CNN Met‐Nd that uses both local includes N as cloud‐controlling factor enhance predictive ability daily cover, albedo, radiative (CRE) for global marine clouds. CNN demonstrates superior performance, explaining over 70% variance three variables scenes 1° × 1°, notable improvement past efforts. also replicates geographical patterns trends from 2003 2022. In contrast, similar without Met struggles predict long‐term properties effectively. Permutation importance analysis further highlights critical Met‐N 's success. Further comparisons with an artificial (ANN model, which same inputs considering spatial dependence, show performance R 2 values CRE being 0.16, 0.12, 0.18 higher, respectively. This incorporating information, at least on scale, into predictions climate parameterizations.

Language: Английский

Aerosol trends dominate over global warming-induced cloud feedback in driving recent changes in marine low clouds DOI Creative Commons
Yang Cao, Hao Wang, Yannian Zhu

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 13, 2025

Abstract Over the past two decades, anthropogenic emission reductions and global warming have impacted marine low clouds through aerosol-cloud interactions (ACI) cloud feedback, yet their quantitative contributions remain unclear. This study employs a deep learning model (CNNMet−Nd) Community Earth System Model version 2 (CESM2) to disentangle these effects. CNNMet−Nd reveals that aerosol-driven changes in droplet number concentration dominate near-global shortwave radiative effect (ΔCRE), contributing 0.42 ± 0.08 Wm⁻² per 20 years, compared 0.05 0.37 from feedback. CESM2 effectively reproduces predominant influence of aerosol on ΔCRE by CNNMet−Nd, lending us confidence for stronger estimate effective forcing due ACI (ERFaci) -1.29 since preindustrial era. These findings highlight critical role shaping trends its broader climate implications, especially under ongoing reduction efforts.

Language: Английский

Citations

0
Improving Prediction of Marine Low Clouds Using Cloud Droplet Number Concentration in a Convolutional Neural Network DOI Creative Commons
Yang Cao, Yannian Zhu, Minghuai Wang

et al.

Journal of Geophysical Research Machine Learning and Computation, Journal Year: 2024, Volume and Issue: 1(4)

Published: Nov. 30, 2024

Abstract Marine low clouds play a crucial role in cooling the climate, but accurately predicting them remains challenging due to their highly non‐linear response various factors. Previous studies usually overlook effects of cloud droplet number concentration (N d ) and non‐local information target grids. To address these challenges, we introduce convolutional neural network model (CNN Met‐Nd that uses both local includes N as cloud‐controlling factor enhance predictive ability daily cover, albedo, radiative (CRE) for global marine clouds. CNN demonstrates superior performance, explaining over 70% variance three variables scenes 1° × 1°, notable improvement past efforts. also replicates geographical patterns trends from 2003 2022. In contrast, similar without Met struggles predict long‐term properties effectively. Permutation importance analysis further highlights critical Met‐N 's success. Further comparisons with an artificial (ANN model, which same inputs considering spatial dependence, show performance R 2 values CRE being 0.16, 0.12, 0.18 higher, respectively. This incorporating information, at least on scale, into predictions climate parameterizations.

Language: Английский

Citations

0