基于太阳动力学观测数据的多模态基础模型，让太阳研究更高效。
A Foundation Model for the Solar Dynamics Observatory
- 融合三类仪器数据，构建太阳多模态嵌入空间。
- 可生成可微调的模型与嵌入数据，支持跨仪器分析。
- 专为太阳物理学家设计，适合需要数据融合的研究者。
SDO-FM 是一个基于美国国家航空航天局太阳动力学观测卫星（SDO）数据的基础模型，整合了三个独立仪器的数据，将太阳复杂的物理相互作用编码到一个多模态嵌入空间中。该模型能通过提升数据计算可访问性，简化涉及 SDO 的科学调查，并支持需要多仪器融合的研究任务。本文介绍了四个关键部分：用于生成机器学习就绪数据集的数据摄入流程、模型架构与训练方法、生成的嵌入与可微调模型，以及下游微调应用。开发过程中始终纳入领域专家参与，确保模型架构、数据集和训练范式具备科学价值。本文正式发布预训练模型与嵌入数据集，可在 Hugging Face 与 sdofm.org 获取。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。