Generative Modeling of Atmospheric Convection. Mooers, G., Tuyls, J., Mandt, S., Pritchard, M., & Beucler, T. G In Proceedings of the 10th International Conference on Climate Informatics, of CI2020, pages 98–105, New York, NY, USA, January, 2021. Association for Computing Machinery. ![Generative Modeling of Atmospheric Convection [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.
@inproceedings{mooers_generative_2021,
address = {New York, NY, USA},
series = {{CI2020}},
title = {Generative {Modeling} of {Atmospheric} {Convection}},
isbn = {978-1-4503-8848-1},
url = {https://dl.acm.org/doi/10.1145/3429309.3429324},
doi = {10.1145/3429309.3429324},
abstract = {While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.},
urldate = {2023-04-16},
booktitle = {Proceedings of the 10th {International} {Conference} on {Climate} {Informatics}},
publisher = {Association for Computing Machinery},
author = {Mooers, Griffin and Tuyls, Jens and Mandt, Stephan and Pritchard, Mike and Beucler, Tom G},
month = jan,
year = {2021},
keywords = {climate modeling, subgrid parameterization, variational autoencoders, vertical velocity},
pages = {98--105},
}
Downloads: 0
{"_id":"pwfmvqYAzkipt5TAs","bibbaseid":"mooers-tuyls-mandt-pritchard-beucler-generativemodelingofatmosphericconvection-2021","author_short":["Mooers, G.","Tuyls, J.","Mandt, S.","Pritchard, M.","Beucler, T. G"],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"CI2020","title":"Generative Modeling of Atmospheric Convection","isbn":"978-1-4503-8848-1","url":"https://dl.acm.org/doi/10.1145/3429309.3429324","doi":"10.1145/3429309.3429324","abstract":"While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.","urldate":"2023-04-16","booktitle":"Proceedings of the 10th International Conference on Climate Informatics","publisher":"Association for Computing Machinery","author":[{"propositions":[],"lastnames":["Mooers"],"firstnames":["Griffin"],"suffixes":[]},{"propositions":[],"lastnames":["Tuyls"],"firstnames":["Jens"],"suffixes":[]},{"propositions":[],"lastnames":["Mandt"],"firstnames":["Stephan"],"suffixes":[]},{"propositions":[],"lastnames":["Pritchard"],"firstnames":["Mike"],"suffixes":[]},{"propositions":[],"lastnames":["Beucler"],"firstnames":["Tom","G"],"suffixes":[]}],"month":"January","year":"2021","keywords":"climate modeling, subgrid parameterization, variational autoencoders, vertical velocity","pages":"98–105","bibtex":"@inproceedings{mooers_generative_2021,\n\taddress = {New York, NY, USA},\n\tseries = {{CI2020}},\n\ttitle = {Generative {Modeling} of {Atmospheric} {Convection}},\n\tisbn = {978-1-4503-8848-1},\n\turl = {https://dl.acm.org/doi/10.1145/3429309.3429324},\n\tdoi = {10.1145/3429309.3429324},\n\tabstract = {While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimensionality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, performs unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models.},\n\turldate = {2023-04-16},\n\tbooktitle = {Proceedings of the 10th {International} {Conference} on {Climate} {Informatics}},\n\tpublisher = {Association for Computing Machinery},\n\tauthor = {Mooers, Griffin and Tuyls, Jens and Mandt, Stephan and Pritchard, Mike and Beucler, Tom G},\n\tmonth = jan,\n\tyear = {2021},\n\tkeywords = {climate modeling, subgrid parameterization, variational autoencoders, vertical velocity},\n\tpages = {98--105},\n}\n\n","author_short":["Mooers, G.","Tuyls, J.","Mandt, S.","Pritchard, M.","Beucler, T. G"],"key":"mooers_generative_2021","id":"mooers_generative_2021","bibbaseid":"mooers-tuyls-mandt-pritchard-beucler-generativemodelingofatmosphericconvection-2021","role":"author","urls":{"Paper":"https://dl.acm.org/doi/10.1145/3429309.3429324"},"keyword":["climate modeling","subgrid parameterization","variational autoencoders","vertical velocity"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/iagogv","dataSources":["ovn29uG6Mbp3JWCRR"],"keywords":["climate modeling","subgrid parameterization","variational autoencoders","vertical velocity"],"search_terms":["generative","modeling","atmospheric","convection","mooers","tuyls","mandt","pritchard","beucler"],"title":"Generative Modeling of Atmospheric Convection","year":2021}