利用人工智能驱动的图像识别/分类表征HD 209458b类热木星的大气动力学

IF 4.8 2区 物理与天体物理 Q1 ASTRONOMY & ASTROPHYSICS
F. Sainsbury-Martinez, P. Tremblin, M. Mancip, S. Donfack, E. Honore, M. Bourenane
{"title":"利用人工智能驱动的图像识别/分类表征HD 209458b类热木星的大气动力学","authors":"F. Sainsbury-Martinez, P. Tremblin, M. Mancip, S. Donfack, E. Honore, M. Bourenane","doi":"10.3847/1538-4357/acf9ed","DOIUrl":null,"url":null,"abstract":"Abstract In order to understand the results of recent observations of exoplanets, models have become increasingly complex. Unfortunately, this increases both the computational cost and output size of said models. We intend to explore if AI image recognition can alleviate this burden. We used DYNAMICO to run a series of HD 209458-like models with different orbital radii. Training data for a number of features of interest was selected from the initial outputs of these models. This was used to train a pair of multi-categorization convolutional neural networks (CNNs), which we applied to our outer-atmosphere-equilibrated models. The features detected by our CNNs revealed that our models fall into two regimes: models with shorter orbital radii exhibit significant global mixing that shapes the dynamics of the entire atmosphere, whereas models with longer orbital-radii exhibit negligible mixing except at mid-pressures. Here the initial nondetection of any trained features revealed a surprise: a nightside hot spot. Analysis suggests that this occurs when rotational influence is sufficiently weak that divergent flows from the dayside to the nightside dominate over rotational-driven transport, such as the equatorial jet. We suggest that image classification may play an important role in future, computational, atmospheric studies. However special care must be paid to the data feed into the model, from the color map, to training the CNN on features with enough breadth and complexity that the CNN can learn to detect them. However, by using preliminary studies and prior models, this should be more than achievable for future exascale calculations, allowing for a significant reduction in future workloads and computational resources.","PeriodicalId":50735,"journal":{"name":"Astrophysical Journal","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Characterizing the Atmospheric Dynamics of HD 209458b-like Hot Jupiters Using AI-driven Image Recognition/Categorization\",\"authors\":\"F. Sainsbury-Martinez, P. Tremblin, M. Mancip, S. Donfack, E. Honore, M. Bourenane\",\"doi\":\"10.3847/1538-4357/acf9ed\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract In order to understand the results of recent observations of exoplanets, models have become increasingly complex. Unfortunately, this increases both the computational cost and output size of said models. We intend to explore if AI image recognition can alleviate this burden. We used DYNAMICO to run a series of HD 209458-like models with different orbital radii. Training data for a number of features of interest was selected from the initial outputs of these models. This was used to train a pair of multi-categorization convolutional neural networks (CNNs), which we applied to our outer-atmosphere-equilibrated models. The features detected by our CNNs revealed that our models fall into two regimes: models with shorter orbital radii exhibit significant global mixing that shapes the dynamics of the entire atmosphere, whereas models with longer orbital-radii exhibit negligible mixing except at mid-pressures. Here the initial nondetection of any trained features revealed a surprise: a nightside hot spot. Analysis suggests that this occurs when rotational influence is sufficiently weak that divergent flows from the dayside to the nightside dominate over rotational-driven transport, such as the equatorial jet. We suggest that image classification may play an important role in future, computational, atmospheric studies. However special care must be paid to the data feed into the model, from the color map, to training the CNN on features with enough breadth and complexity that the CNN can learn to detect them. However, by using preliminary studies and prior models, this should be more than achievable for future exascale calculations, allowing for a significant reduction in future workloads and computational resources.\",\"PeriodicalId\":50735,\"journal\":{\"name\":\"Astrophysical Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2023-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Astrophysical Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3847/1538-4357/acf9ed\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ASTRONOMY & ASTROPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Astrophysical Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3847/1538-4357/acf9ed","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0

摘要

为了理解最近对系外行星的观测结果,模型变得越来越复杂。不幸的是,这增加了所述模型的计算成本和输出大小。我们打算探索人工智能图像识别是否可以减轻这种负担。我们使用DYNAMICO运行了一系列具有不同轨道半径的HD 209458模型。从这些模型的初始输出中选择一些感兴趣的特征的训练数据。这被用来训练一对多分类卷积神经网络(cnn),我们将其应用于我们的外部大气平衡模型。我们的cnn检测到的特征表明,我们的模型分为两种模式:轨道半径较短的模型显示出显著的全球混合,形成了整个大气的动力学,而轨道半径较长的模型显示出除了中压外的可忽略不计的混合。在这里,最初没有检测到任何经过训练的特征揭示了一个惊喜:一个夜间热点。分析表明,当旋转影响足够弱时,这种情况就会发生,从昼侧到夜侧的发散气流占主导地位,而不是旋转驱动的输送,如赤道喷流。我们认为图像分类可能在未来的计算大气研究中发挥重要作用。然而,必须特别注意输入到模型中的数据,从颜色图到训练CNN的特征,这些特征具有足够的广度和复杂性,使CNN能够学会检测它们。然而,通过使用初步研究和先前的模型,这对于未来的百亿亿次计算来说应该是可以实现的,从而可以显著减少未来的工作负载和计算资源。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Characterizing the Atmospheric Dynamics of HD 209458b-like Hot Jupiters Using AI-driven Image Recognition/Categorization
Abstract In order to understand the results of recent observations of exoplanets, models have become increasingly complex. Unfortunately, this increases both the computational cost and output size of said models. We intend to explore if AI image recognition can alleviate this burden. We used DYNAMICO to run a series of HD 209458-like models with different orbital radii. Training data for a number of features of interest was selected from the initial outputs of these models. This was used to train a pair of multi-categorization convolutional neural networks (CNNs), which we applied to our outer-atmosphere-equilibrated models. The features detected by our CNNs revealed that our models fall into two regimes: models with shorter orbital radii exhibit significant global mixing that shapes the dynamics of the entire atmosphere, whereas models with longer orbital-radii exhibit negligible mixing except at mid-pressures. Here the initial nondetection of any trained features revealed a surprise: a nightside hot spot. Analysis suggests that this occurs when rotational influence is sufficiently weak that divergent flows from the dayside to the nightside dominate over rotational-driven transport, such as the equatorial jet. We suggest that image classification may play an important role in future, computational, atmospheric studies. However special care must be paid to the data feed into the model, from the color map, to training the CNN on features with enough breadth and complexity that the CNN can learn to detect them. However, by using preliminary studies and prior models, this should be more than achievable for future exascale calculations, allowing for a significant reduction in future workloads and computational resources.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Astrophysical Journal
Astrophysical Journal 地学天文-天文与天体物理
CiteScore
8.40
自引率
30.60%
发文量
2854
审稿时长
1 months
期刊介绍: The Astrophysical Journal is the foremost research journal in the world devoted to recent developments, discoveries, and theories in astronomy and astrophysics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信