arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.02530astro-ph.SRcs.CV
收藏

太阳动力学观测站的基础模型

A Foundation Model for the Solar Dynamics Observatory

University of Cambridge(剑桥大学);University of Central Lancashire(中央兰开夏大学);Universidad Industrial de Santander(桑坦德工业大学);Dublin Institute for Advanced Studies(都柏林高等研究院);Pure Storage(Pure Storage公司);AE Studio(AE工作室);University of Tokyo(东京大学);Trillium Technologies Inc(Trillium技术公司);University of Oxford(牛津大学)

James Walsh, Daniel G. Gass, Raul Ramos Pollan, Paul J. Wright, Richard Galvez, Noah Kasmanoff, Jason Naradowsky, Anne Spalding, James Parr, Atılım Güneş Baydin

AI总结:

本文提出SDO-FM基础模型,融合NASA太阳动力学观测站三个仪器的数据构建多模态嵌入空间,并发布预训练模型与嵌入数据集以促进日球层物理学研究。

摘要:

SDO-FM 是一个基础模型,使用来自 NASA 太阳动力学观测站(SDO)航天器的数据;它整合了三个独立的仪器,将太阳复杂的物理相互作用封装到一个多模态嵌入空间中。该模型可用于简化涉及 SDO 的科学研究,使海量数据集在计算上更易于日球层物理学研究访问,并支持需要仪器融合的研究。我们讨论了四个关键组成部分:一个用于创建机器学习就绪数据集的摄取管道、模型架构与训练方法、生成的嵌入和可微调模型,以及最终的下游微调应用。这项工作的一个关键组成部分是在开发的每个阶段都纳入领域专家;他们审查科学价值,并为模型架构、数据集和训练范式决策提供指导。本文标志着我们预训练模型和嵌入数据集的发布,这些资源已通过 Hugging Face 和 sdofm.org 向社区开放。

英文摘要:

SDO-FM is a foundation model using data from NASA's Solar Dynamics Observatory (SDO) spacecraft; integrating three separate instruments to encapsulate the Sun's complex physical interactions into a multi-modal embedding space. This model can be used to streamline scientific investigations involving SDO by making the enormous datasets more computationally accessible for heliophysics research and enable investigations that require instrument fusion. We discuss four key components: an ingestion pipeline to create machine learning ready datasets, the model architecture and training approach, resultant embeddings and fine-tunable models, and finally downstream fine-tuned applications. A key component of this effort has been to include subject matter specialists at each stage of development; reviewing the scientific value and providing guidance for model architecture, dataset, and training paradigm decisions. This paper marks release of our pretrained models and embedding datasets, available to the community on Hugging Face and sdofm.org.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑