Physics-informed learning of aerosol microphysics
Physics-informed learning of aerosol microphysics
复制标题
DOI：
10.1017/eds.2022.22
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
P. Harder;D. Watson‐Parris;P. Stier;Dominik Strassel;N. Gauger;J. Keuper
中科院分区：
文献类型：
--
作者：
P. Harder;D. Watson‐Parris;P. Stier;Dominik Strassel;N. Gauger;J. Keuper
摘要气溶胶粒子通过吸收和散射辐射，影响云的性质，在气候系统中起着重要的作用。它们也是气候建模的最大不确定性来源之一。由于计算的限制，许多气候模式没有包括足够详细的气溶胶。为了代表关键过程，必须考虑气溶胶微物理特性和过程。这是在ECHAM-HAM（欧洲中期天气预报中心-汉堡-汉堡）全球气候气溶胶模式中使用M7微物理学完成的，但高计算成本使得以更高的分辨率或更长的时间运行非常昂贵。我们的目标是使用机器学习以足够的精度模拟微观物理模型，并通过在推理时间快速降低计算成本。原始的M7模型用于生成输入输出对的数据，以在其上训练神经网络（NN）。我们能够学习变量的趋势，平均$ {R}^2 $得分为77.1%。我们进一步探索了用物理知识通知和约束NN的方法，以减少大规模违规并加强大规模积极性。在图形处理单元（GPU）上，与原始模型相比，我们实现了高达64倍以上的速度提升。
Abstract Aerosol particles play an important role in the climate system by absorbing and scattering radiation and influencing cloud properties. They are also one of the biggest sources of uncertainty for climate modeling. Many climate models do not include aerosols in sufficient detail due to computational constraints. To represent key processes, aerosol microphysical properties and processes have to be accounted for. This is done in the ECHAM-HAM (European Center for Medium-Range Weather Forecast-Hamburg-Hamburg) global climate aerosol model using the M7 microphysics, but high computational costs make it very expensive to run with finer resolution or for a longer time. We aim to use machine learning to emulate the microphysics model at sufficient accuracy and reduce the computational cost by being fast at inference time. The original M7 model is used to generate data of input–output pairs to train a neural network (NN) on it. We are able to learn the variables’ tendencies achieving an average $ {R}^2 $ score of 77.1%. We further explore methods to inform and constrain the NN with physical knowledge to reduce mass violation and enforce mass positivity. On a Graphics processing unit (GPU), we achieve a speed-up of up to over 64 times faster when compared to the original model.