Zero-shot learning of aerosol optical properties with graph neural networks.

Zero-shot learning of aerosol optical properties with graph neural networks.
复制标题

DOI:
10.1038/s41598-023-45235-8
复制
发表时间:
2023-10-31
期刊:
影响因子:
4.6
通讯作者:
Gentine, P.
Gentine, P.
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Lamb, K. D.;Gentine, P.

文献摘要

参考文献

相似文献

炭黑是一种强吸附性气溶胶,是一种重要的短期气候因子。BC的复杂形态导致了其直接气候辐射效应的不确定性,因为目前精确计算这些气溶胶光学特性的方法计算成本太高,无法用于在线模式或用于观测检索。在这里,我们证明了用于预测数值生成的BC分形聚集体光学性质的图神经网络(GNN)可以准确地推广到任意形状的粒子,包括比训练数据集中更大的聚集体。这种零射击学习方法可用于估计真实形状的气溶胶和云粒子的单粒子光学特性,以便纳入大气模型和遥感反演的辐射传输代码。此外,GNN可以用来获得关于小尺度相互作用(这里是球体的位置和相互作用)和大尺度性质(这里是气溶胶的辐射性质)之间关系的物理直觉。
Black carbon (BC), a strongly absorbing aerosol sourced from combustion, is an important short-lived climate forcer. BC’s complex morphology contributes to uncertainty in its direct climate radiative effects, as current methods to accurately calculate the optical properties of these aerosols are too computationally expensive to be used online in models or for observational retrievals. Here we demonstrate that a Graph Neural Network (GNN) trained to predict the optical properties of numerically-generated BC fractal aggregates can accurately generalize to arbitrarily shaped particles, including much larger () aggregates than in the training dataset. This zero-shot learning approach could be used to estimate single particle optical properties of realistically-shaped aerosol and cloud particles for inclusion in radiative transfer codes for atmospheric models and remote sensing inversions. In addition, GNN’s can be used to gain physical intuition on the relationship between small-scale interactions (here of the spheres’ positions and interactions) and large-scale properties (here of the radiative properties of aerosols).
DOI: 10.1080/02786826.2011.568022
发表时间: 2011-01-01
影响因子: 5.2
作者:
Chakrabarty, Rajan K.;Garro, Mark A.;Herald, Christopher M.
通讯作者: Herald, Christopher M.
黑碳聚集体:光学特性数据库
DOI: 10.1016/j.jqsrt.2018.10.021
发表时间: 2019-01-01
影响因子: 2.3
作者:
Liu, Chao;Xu, Xiaofeng;Yung, Yuk L.
通讯作者: Yung, Yuk L.
DOI: 10.1016/j.jqsrt.2018.05.002
发表时间: 2018-08-01
影响因子: 2.3
作者:
Luo, Jie;Zhang, Yongming;Zhang, Qixing
通讯作者: Zhang, Qixing
DOI: 10.1029/2018gl078202
发表时间: 2018-06-16
影响因子: 5.2
作者:
Gentine, P.;Pritchard, M.;Yacalis, G.
通讯作者: Yacalis, G.
DOI: 10.1029/2006jd008296
发表时间: 2007-07-19
影响因子: 4.4
作者:
Adachi, Kouji;Chung, Serena H.;Buseck, Peter R.
通讯作者: Buseck, Peter R.