Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles
Abstract Low cloud fractions (LCFs) and meteorological factors (MFs) over an oceanic region containing multiple cloud regimes are examined for three data sets: one Energy Exascale Earth System Model (E3SM) simulation with the default 72‐layer vertical grid (E3SM72), another one with 8‐times vertical...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2021-11-01
|
| Series: | Journal of Advances in Modeling Earth Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2021MS002625 |
| _version_ | 1818925985156825088 |
|---|---|
| author | Yao‐Sheng Chen Takanobu Yamaguchi Peter A. Bogenschutz Graham Feingold |
| author_facet | Yao‐Sheng Chen Takanobu Yamaguchi Peter A. Bogenschutz Graham Feingold |
| author_sort | Yao‐Sheng Chen |
| collection | DOAJ |
| description | Abstract Low cloud fractions (LCFs) and meteorological factors (MFs) over an oceanic region containing multiple cloud regimes are examined for three data sets: one Energy Exascale Earth System Model (E3SM) simulation with the default 72‐layer vertical grid (E3SM72), another one with 8‐times vertical resolution via the Framework for Improvement by Vertical Enhancement (E3SM×8), and one with MFs from ERA5 reanalysis and LCFs from the CERES SSF product (ERA5‐SSF). Neural networks (NNs) are trained to capture the relationship between MFs and LCF and to select the best‐performing MF subsets for predicting LCF. NN ensembles are used to (a) confirm the performance of selected MF subsets, (b) to serve as proxy models for each data set to predict LCFs for MFs from all data sets, and (c) to classify MFs into those in shared and uniquely occupied MF subspaces. Overall, E3SM72 and E3SM×8 have large fractions of MFs in shared MF subspace, but less so near the Californian and Peruvian stratocumulus decks. E3SM×8 and ERA5 have small fractions of MFs in shared MF subspace but greater than E3SM72 and ERA5, especially in the Southeast Pacific. The differences in LCFs between three pairs of data sets are decomposed into those associated with the differences in the LCF‐MF relationship and those involving different MFs. Given the same MFs, LCFs produced by E3SM×8 are greater than those produced by E3SM72 but are still different from those in ERA5‐SSF. In general, the shift in MFs dominates the difference in the LCFs. |
| first_indexed | 2024-12-20T02:49:55Z |
| format | Article |
| id | doaj.art-abfe21993682470981f5f851cc7c2ed6 |
| institution | Directory Open Access Journal |
| issn | 1942-2466 |
| language | English |
| last_indexed | 2024-12-20T02:49:55Z |
| publishDate | 2021-11-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Journal of Advances in Modeling Earth Systems |
| spelling | doaj.art-abfe21993682470981f5f851cc7c2ed62022-12-21T19:56:04ZengAmerican Geophysical Union (AGU)Journal of Advances in Modeling Earth Systems1942-24662021-11-011311n/an/a10.1029/2021MS002625Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network EnsemblesYao‐Sheng Chen0Takanobu Yamaguchi1Peter A. Bogenschutz2Graham Feingold3Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder Boulder CO USACooperative Institute for Research in Environmental Sciences University of Colorado Boulder Boulder CO USALawrence Livermore National Laboratory Livermore CA USANOAA Chemical Sciences Laboratory Boulder CO USAAbstract Low cloud fractions (LCFs) and meteorological factors (MFs) over an oceanic region containing multiple cloud regimes are examined for three data sets: one Energy Exascale Earth System Model (E3SM) simulation with the default 72‐layer vertical grid (E3SM72), another one with 8‐times vertical resolution via the Framework for Improvement by Vertical Enhancement (E3SM×8), and one with MFs from ERA5 reanalysis and LCFs from the CERES SSF product (ERA5‐SSF). Neural networks (NNs) are trained to capture the relationship between MFs and LCF and to select the best‐performing MF subsets for predicting LCF. NN ensembles are used to (a) confirm the performance of selected MF subsets, (b) to serve as proxy models for each data set to predict LCFs for MFs from all data sets, and (c) to classify MFs into those in shared and uniquely occupied MF subspaces. Overall, E3SM72 and E3SM×8 have large fractions of MFs in shared MF subspace, but less so near the Californian and Peruvian stratocumulus decks. E3SM×8 and ERA5 have small fractions of MFs in shared MF subspace but greater than E3SM72 and ERA5, especially in the Southeast Pacific. The differences in LCFs between three pairs of data sets are decomposed into those associated with the differences in the LCF‐MF relationship and those involving different MFs. Given the same MFs, LCFs produced by E3SM×8 are greater than those produced by E3SM72 but are still different from those in ERA5‐SSF. In general, the shift in MFs dominates the difference in the LCFs.https://doi.org/10.1029/2021MS002625cloud controlling factorsE3SMhigh resolution modelingmachine learningshallow clouds |
| spellingShingle | Yao‐Sheng Chen Takanobu Yamaguchi Peter A. Bogenschutz Graham Feingold Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles Journal of Advances in Modeling Earth Systems cloud controlling factors E3SM high resolution modeling machine learning shallow clouds |
| title | Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles |
| title_full | Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles |
| title_fullStr | Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles |
| title_full_unstemmed | Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles |
| title_short | Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles |
| title_sort | model evaluation and intercomparison of marine warm low cloud fractions with neural network ensembles |
| topic | cloud controlling factors E3SM high resolution modeling machine learning shallow clouds |
| url | https://doi.org/10.1029/2021MS002625 |
| work_keys_str_mv | AT yaoshengchen modelevaluationandintercomparisonofmarinewarmlowcloudfractionswithneuralnetworkensembles AT takanobuyamaguchi modelevaluationandintercomparisonofmarinewarmlowcloudfractionswithneuralnetworkensembles AT peterabogenschutz modelevaluationandintercomparisonofmarinewarmlowcloudfractionswithneuralnetworkensembles AT grahamfeingold modelevaluationandintercomparisonofmarinewarmlowcloudfractionswithneuralnetworkensembles |