arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.00833astro-ph.COastro-ph.IM
收藏

HIDM:使用基于分数的扩散模型模拟大尺度HI图

HIDM: Emulating Large Scale HI Maps using Score-based Diffusion Models

Sultan Hassan, Sambatra Andrianomena

AI总结:

针对大尺度巡天图分析中高维似然获取与高保真场生成难题,本文提出HIDM,利用CAMELS模拟和基于分数的扩散模型生成与统计量及似然吻合的大尺度HI图。

摘要:

高效分析来自即将开展的大尺度巡天的图,需要直接获取高维似然并高保真生成大尺度场,这两项都是重大挑战。利用CAMELS模拟,我们采用最先进的基于分数的扩散模型同时完成这两项任务。我们表明,我们的模型HIDM能够高效生成高保真的大尺度HI图,并且这些图与CAMELS的功率谱、概率分布以及直到二阶矩的似然高度一致。HIDM代表着迈向最大化未来大尺度巡天科学回报的一步。

英文摘要:

Efficiently analyzing maps from upcoming large-scale surveys requires gaining direct access to a high-dimensional likelihood and generating large-scale fields with high fidelity, which both represent major challenges. Using CAMELS simulations, we employ the state-of-the-art score-based diffusion models to simultaneously achieve both tasks. We show that our model, HIDM, is able to efficiently generate high fidelity large scale HI maps that are in a good agreement with the CAMELS's power spectrum, probability distribution, and likelihood up to second moments. HIDM represents a step forward towards maximizing the scientific return of future large scale surveys.

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。

↑