A Neural Network‐Based Scale‐Adaptive Cloud‐Fraction Scheme for GCMs

Chen, Guoxing; Wang, Wei‐Chyung; Yang, Shixi; Wang, Yixin; Zhang, Feng; Wu, Kun

doi:10.1029/2022ms003415

Cited by 7 publications

(5 citation statements)

References 78 publications

(102 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recognizing the importance of cloud dynamics for SIP, training RaFSIP using outputs from higher‐resolution km‐scale grids or even Large Eddy Simulation models would be imperative. In the context of growing convective clouds, where the HM process may surpass BR in efficiency (Waman et al., 2022), and DS may be more active due to the presence of larger raindrops, potential adaptations for a scale‐adaptive RaFSIP scheme (Chen et al., 2023) could be more urgent than in stratiform clouds. This is because of the scale dependence of LWC, which can be an important input for predicting the effect of HM.…”

Section: Discussionmentioning

confidence: 99%

RaFSIP: Parameterizing Ice Multiplication in Models Using a Machine Learning Approach

Georgakaki,

Nenes

2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

Accurately representing mixed‐phase clouds (MPCs) in global climate models (GCMs) is critical for capturing climate sensitivity and Arctic amplification. Secondary ice production (SIP), can significantly increase ice crystal number concentration (ICNC) in MPCs, affecting cloud properties and processes. Here, we introduce a machine‐learning (ML) approach, called Random Forest SIP (RaFSIP), to parameterize SIP in stratiform MPCs. RaFSIP is trained on 16 grid points with 10‐km horizontal spacing derived from a 2‐year simulation with the Weather Research and Forecasting (WRF) model, including explicit SIP microphysics. Designed for a temperature range of 0 to −25°C, RaFSIP simplifies the description of rime splintering, ice‐ice collisional break‐up, and droplet‐shattering using only a limited set of inputs. RaFSIP was evaluated offline before being integrated into WRF, demonstrating its stable online performance in a 1‐year simulation keeping the same model setup as during training. Even when coupled with the 50‐km grid spacing domain of WRF, RaFSIP reproduces ICNC predictions within a factor of 3 when compared to simulations with explicit SIP microphysics. The coupled WRF‐RaFSIP scheme replicates regions of enhanced SIP and accurately maps ICNCs and liquid water content, particularly at temperatures above −10°C. Uncertainties in RaFSIP minimally impact surface cloud radiative forcing in the Arctic, resulting in radiative biases under 3 Wm−2 compared to simulations with detailed microphysics. Although the performance of RaFSIP in convective clouds remains untested, its adaptable nature allows for data set augmentation to address this aspect. This framework opens possibilities for GCM simplification and process description through physics‐guided ML algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

RaFSIP: Parameterizing Ice Multiplication in Models Using a Machine Learning Approach

Georgakaki,

Nenes

2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

show abstract

“…The rise of machine learning (ML, i.e., data-driven models) capabilities has fostered new approaches to improving parameterizations (Gentine et al, 2018). Examples include replacing computationally intensive physical parameterizations with ML emulation (Keller & Evans, 2019;Krasnopolsky et al, 2005Krasnopolsky et al, , 2010Lagerquist et al, 2021;O'Gorman & Dwyer, 2018;Perkins et al, 2023) and training ML against observations (Chen et al, 2023;McGibbon & Bretherton, 2019;Watt-Meyer et al, 2021) or more accurate and computationally intensive parameterizations (Chantry et al, 2021). ML parameterizations for coarse-grid models have been trained on coarsened (coarse-grained) outputs of fine-grid or super-parameterized reference simulations, for example, to predict the effect of the full physics parameterization (Brenowitz & Bretherton, 2019;Han et al, 2020;Rasp et al, 2018;Watt-Meyer et al, 2024;Yuval et al, 2021), or a column-wise correction to the coarse-grid model physics (Bretherton et al, 2022;Clark et al, 2022;Kwa et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

“…This motivated us to use ML to also improve the simulated cloud distributions. Grundner et al (2022Grundner et al ( , 2023 and Chen et al (2023) have developed ML parameterizations of fractional cloud cover trained on coarsened fine-grid output and observations, and they showed that these parameterizations can improve upon the skill of existing physically based parameterizations. We extend such work here by demonstrating that ML-predicted cloud statistics, including fractional cloud cover and ice and liquid cloud condensate mixing ratios, can improve the offline simulation of coarse model radiative fluxes, given careful attention to the vertical overlap of fractional cloud cover within grid columns.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Parameterization of Clouds in a Coarse‐Resolution Climate Model for Unbiased Radiation

Henn,

Jauregui,

Clark

et al. 2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

Coarse‐grid weather and climate models rely particularly on parameterizations of cloud fields, and coarse‐grained cloud fields from a fine‐grid reference model are a natural target for a machine‐learned parameterization. We machine‐learn the coarsened‐fine cloud properties as a function of coarse‐grid model state in each grid cell of NOAA's FV3GFS global atmosphere model with 200 km grid spacing, trained using a 3 km fine‐grid reference simulation with a modified version of FV3GFS. The ML outputs are coarsened‐fine fractional cloud cover and liquid and ice cloud condensate mixing ratios, and the inputs are coarse model temperature, pressure, relative humidity, and ice cloud condensate. The predicted fields are skillful and unbiased, but somewhat under‐dispersed, resulting in too many partially cloudy model columns. When the predicted fields are applied diagnostically (offline) in FV3GFS's radiation scheme, they lead to small biases in global‐mean top‐of‐atmosphere (TOA) and surface radiative fluxes. An unbiased global‐mean TOA net radiative flux is obtained by setting to zero any predicted cloud with grid‐cell mean cloud fraction less than a threshold of 6.5%; this does not significantly degrade the ML prediction of cloud properties. The diagnostic, ML‐derived radiative fluxes are far more accurate than those obtained with the existing cloud parameterization in the nudged coarse‐grid model, as they leverage the accuracy of the fine‐grid reference simulation's cloud properties.

show abstract

“…For example, Zhang et al (2021) proposed a ML trigger function for a deep convection parameterization by learning from field observations, demonstrating its superior accuracy compared to traditional CAPE-based trigger functions. Chen et al (2023) developed a neural network-based cloud fraction parameterization, better predicting both spatial distribution and vertical structure of cloud fraction when compared to the traditional Xu-Randall scheme (Xu & Randall, 1996). Krasnopolsky et al (2013) prototyped a system using a neural network to learn the convective temperature and moisture tendencies from cloud-resolving model (CRM) simulations.…”

Section: Introductionmentioning

confidence: 99%

A Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models

Zhang,

Morcrette,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex problems has spawned immense interests in climate science applications. Specifically, ML-based parameterizations have been developed to represent convection, radiation and microphysics processes in ESMs by learning from observations or high-resolution simulations, which have the potential to improve the accuracies and alleviate the uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to be coupled with the dynamical core of ESMs to investigate the effectiveness and their performance in a coupled system. In this study, we present a novel Fortran-Python interface designed to seamlessly integrate ML parameterizations into ESMs. This interface showcases high versatility by supporting popular ML frameworks like PyTorch, TensorFlow, and Scikit-learn. We demonstrate the interface's modularity and reusability through two cases: a ML trigger function for convection parameterization and a ML wildfire model. We conduct a comprehensive evaluation of memory usage and computational overhead resulting from the integration of Python codes into the Fortran ESMs. By leveraging this flexible interface, ML parameterizations can be effectively developed, tested, and integrated into ESMs.

show abstract

A Neural Network‐Based Scale‐Adaptive Cloud‐Fraction Scheme for GCMs

Cited by 7 publications

References 78 publications

RaFSIP: Parameterizing Ice Multiplication in Models Using a Machine Learning Approach

RaFSIP: Parameterizing Ice Multiplication in Models Using a Machine Learning Approach

A Machine Learning Parameterization of Clouds in a Coarse‐Resolution Climate Model for Unbiased Radiation

A Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models

Contact Info

Product

Resources

About