提炼机器学习的附加值:大气应用中的帕累托前沿

Tom Beucler, Arthur Grundner, Sara Shamekh, Peter Ukkonen, Matthew Chantry, Ryan Lagerquist
{"title":"提炼机器学习的附加值:大气应用中的帕累托前沿","authors":"Tom Beucler, Arthur Grundner, Sara Shamekh, Peter Ukkonen, Matthew Chantry, Ryan Lagerquist","doi":"arxiv-2408.02161","DOIUrl":null,"url":null,"abstract":"While the added value of machine learning (ML) for weather and climate\napplications is measurable, explaining it remains challenging, especially for\nlarge deep learning models. Inspired by climate model hierarchies, we propose\nthat a full hierarchy of Pareto-optimal models, defined within an appropriately\ndetermined error-complexity plane, can guide model development and help\nunderstand the models' added value. We demonstrate the use of Pareto fronts in\natmospheric physics through three sample applications, with hierarchies ranging\nfrom semi-empirical models with minimal tunable parameters (simplest) to deep\nlearning algorithms (most complex). First, in cloud cover parameterization, we\nfind that neural networks identify nonlinear relationships between cloud cover\nand its thermodynamic environment, and assimilate previously neglected features\nsuch as vertical gradients in relative humidity that improve the representation\nof low cloud cover. This added value is condensed into a ten-parameter equation\nthat rivals the performance of deep learning models. Second, we establish a ML\nmodel hierarchy for emulating shortwave radiative transfer, distilling the\nimportance of bidirectional vertical connectivity for accurately representing\nabsorption and scattering, especially for multiple cloud layers. Third, we\nemphasize the importance of convective organization information when modeling\nthe relationship between tropical precipitation and its surrounding\nenvironment. We discuss the added value of temporal memory when high-resolution\nspatial information is unavailable, with implications for precipitation\nparameterization. Therefore, by comparing data-driven models directly with\nexisting schemes using Pareto optimality, we promote process understanding by\nhierarchically unveiling system complexity, with the hope of improving the\ntrustworthiness of ML models in atmospheric applications.","PeriodicalId":501369,"journal":{"name":"arXiv - PHYS - Computational Physics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distilling Machine Learning's Added Value: Pareto Fronts in Atmospheric Applications\",\"authors\":\"Tom Beucler, Arthur Grundner, Sara Shamekh, Peter Ukkonen, Matthew Chantry, Ryan Lagerquist\",\"doi\":\"arxiv-2408.02161\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"While the added value of machine learning (ML) for weather and climate\\napplications is measurable, explaining it remains challenging, especially for\\nlarge deep learning models. Inspired by climate model hierarchies, we propose\\nthat a full hierarchy of Pareto-optimal models, defined within an appropriately\\ndetermined error-complexity plane, can guide model development and help\\nunderstand the models' added value. We demonstrate the use of Pareto fronts in\\natmospheric physics through three sample applications, with hierarchies ranging\\nfrom semi-empirical models with minimal tunable parameters (simplest) to deep\\nlearning algorithms (most complex). First, in cloud cover parameterization, we\\nfind that neural networks identify nonlinear relationships between cloud cover\\nand its thermodynamic environment, and assimilate previously neglected features\\nsuch as vertical gradients in relative humidity that improve the representation\\nof low cloud cover. This added value is condensed into a ten-parameter equation\\nthat rivals the performance of deep learning models. Second, we establish a ML\\nmodel hierarchy for emulating shortwave radiative transfer, distilling the\\nimportance of bidirectional vertical connectivity for accurately representing\\nabsorption and scattering, especially for multiple cloud layers. Third, we\\nemphasize the importance of convective organization information when modeling\\nthe relationship between tropical precipitation and its surrounding\\nenvironment. We discuss the added value of temporal memory when high-resolution\\nspatial information is unavailable, with implications for precipitation\\nparameterization. Therefore, by comparing data-driven models directly with\\nexisting schemes using Pareto optimality, we promote process understanding by\\nhierarchically unveiling system complexity, with the hope of improving the\\ntrustworthiness of ML models in atmospheric applications.\",\"PeriodicalId\":501369,\"journal\":{\"name\":\"arXiv - PHYS - Computational Physics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Computational Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.02161\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Computational Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.02161","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

虽然机器学习(ML)为天气和气候应用带来的附加值是可以衡量的,但解释它仍然具有挑战性,尤其是对于大型深度学习模型而言。受气候模型层次结构的启发,我们提出在适当确定的误差-复杂度平面内定义帕累托最优模型的完整层次结构,可以指导模型开发并帮助理解模型的附加值。我们通过三个示例应用展示了帕累托前沿在大气物理学中的应用,其层次结构从具有最小可调参数的半经验模型(最简单)到深度学习算法(最复杂)不等。首先,在云层参数化方面,我们发现神经网络可以识别云层与其热力学环境之间的非线性关系,并吸收以前被忽视的特征,如相对湿度的垂直梯度,从而改善低云层的表示。这一附加值被浓缩为一个十参数方程,其性能可与深度学习模型相媲美。其次,我们建立了模拟短波辐射传输的 ML 模型层次,提炼出双向垂直连通性对于准确表示吸收和散射的重要性,特别是对于多云层。第三,我们强调了对流组织信息在模拟热带降水与其周围环境关系时的重要性。我们讨论了当高分辨率空间信息不可用时,时间记忆的附加价值,以及对降水参数化的影响。因此,通过利用帕累托最优性直接比较数据驱动模型和现有方案,我们通过分层揭示系统的复杂性来促进对过程的理解,希望能提高 ML 模型在大气应用中的可信度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Distilling Machine Learning's Added Value: Pareto Fronts in Atmospheric Applications
While the added value of machine learning (ML) for weather and climate applications is measurable, explaining it remains challenging, especially for large deep learning models. Inspired by climate model hierarchies, we propose that a full hierarchy of Pareto-optimal models, defined within an appropriately determined error-complexity plane, can guide model development and help understand the models' added value. We demonstrate the use of Pareto fronts in atmospheric physics through three sample applications, with hierarchies ranging from semi-empirical models with minimal tunable parameters (simplest) to deep learning algorithms (most complex). First, in cloud cover parameterization, we find that neural networks identify nonlinear relationships between cloud cover and its thermodynamic environment, and assimilate previously neglected features such as vertical gradients in relative humidity that improve the representation of low cloud cover. This added value is condensed into a ten-parameter equation that rivals the performance of deep learning models. Second, we establish a ML model hierarchy for emulating shortwave radiative transfer, distilling the importance of bidirectional vertical connectivity for accurately representing absorption and scattering, especially for multiple cloud layers. Third, we emphasize the importance of convective organization information when modeling the relationship between tropical precipitation and its surrounding environment. We discuss the added value of temporal memory when high-resolution spatial information is unavailable, with implications for precipitation parameterization. Therefore, by comparing data-driven models directly with existing schemes using Pareto optimality, we promote process understanding by hierarchically unveiling system complexity, with the hope of improving the trustworthiness of ML models in atmospheric applications.
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
自引率
0.00%
发文量
0
×
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