An Interpretable AI Framework to Disentangle Self-interacting and Cold Dark Matter in Galaxy Clusters: The CKAN Approach
文献类型：期刊论文
| 作者 | Huang, Zhenyang1,4; Shi, Haihao1,4; Liu, Zhiyong2,3,4; Wang, Na2,3,4 |
| 刊名 | ASTRONOMICAL JOURNAL
 |
| 出版日期 | 2025-11-03 |
| 卷号 | 170期号:5页码:10 |
| ISSN号 | 0004-6256 |
| DOI | 10.3847/1538-3881/ae0476 |
| 通讯作者 | Liu, Zhiyong(liuzhy@xao.ac.cn) |
| 英文摘要 | Convolutional neural networks have shown their ability to differentiate between self-interacting dark matter (SIDM) and cold dark matter on galaxy cluster scales. However, their large parameter counts and "black-box" nature make it difficult to assess whether their decisions adhere to physical principles. To address this issue, we have built a convolutional Kolmogorov-Arnold network (CKAN) that reduces parameter count and enhances interpretability, and propose a novel analytical framework to understand the network's decision-making process. With this framework, we leverage our network to qualitatively assess the offset between the dark matter distribution center and the galaxy cluster center, as well as the size of heating regions in different models. These findings are consistent with current theoretical predictions and show the reliability and interpretability of our network. By combining network interpretability with unseen test results, we also estimate that for SIDM in galaxy clusters, the minimum cross section (sigma/m)th required to reliably identify its collisional nature falls between 0.1 and 0.3 cm2 g-1. Moreover, CKAN maintains robust performance under simulated JWST and Euclid noise, highlighting its promise for application to forthcoming observational surveys. |
| WOS关键词 | INTERACTION CROSS-SECTION ; PROBE WMAP OBSERVATIONS ; LARGE-SCALE STRUCTURE ; COSMOLOGICAL SIMULATIONS ; OBSERVABLE TESTS ; BLACK-HOLES ; CONSTRAINTS ; EVOLUTION ; PROFILES ; SHAPES |
| 资助项目 | MOST divided by National Key Research and Development Program of China (NKPs)https://doi.org/10.13039/501100012166[2021YFC2203501] ; National Key R&D Program of China ; Operation, Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments ; Ministry of Finance of China[PTYQ2022YZZD01] ; Scientific Instrument Developing Project of the Chinese Academy of Sciences |
| WOS研究方向 | Astronomy & Astrophysics |
| 语种 | 英语 |
| WOS记录号 | WOS:001590797800001 |
| 出版者 | IOP Publishing Ltd |
| 资助机构 | MOST divided by National Key Research and Development Program of China (NKPs)https://doi.org/10.13039/501100012166 ; National Key R&D Program of China ; Operation, Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments ; Ministry of Finance of China ; Scientific Instrument Developing Project of the Chinese Academy of Sciences |
| 源URL | [http://ir.xao.ac.cn/handle/45760611-7/8244]  |
| 专题 | 脉冲星研究团组 |
| 通讯作者 | Liu, Zhiyong |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Astron & Space Sci, Beijing 101408, Peoples R China 2.Key Lab Xinjiang Radio Astrophys, Urumqi 830011, Peoples R China 3.Chinese Acad Sci, Key Lab Radio Astron & Technol, A20 Datun Rd, Beijing 100101, Peoples R China 4.Chinese Acad Sci, Xinjiang Astron Observ, Urumqi 830011, Peoples R China |
| 推荐引用方式 GB/T 7714 | Huang, Zhenyang,Shi, Haihao,Liu, Zhiyong,et al. An Interpretable AI Framework to Disentangle Self-interacting and Cold Dark Matter in Galaxy Clusters: The CKAN Approach[J]. ASTRONOMICAL JOURNAL,2025,170(5):10. |
| APA | Huang, Zhenyang,Shi, Haihao,Liu, Zhiyong,&Wang, Na.(2025).An Interpretable AI Framework to Disentangle Self-interacting and Cold Dark Matter in Galaxy Clusters: The CKAN Approach.ASTRONOMICAL JOURNAL,170(5),10. |
| MLA | Huang, Zhenyang,et al."An Interpretable AI Framework to Disentangle Self-interacting and Cold Dark Matter in Galaxy Clusters: The CKAN Approach".ASTRONOMICAL JOURNAL 170.5(2025):10. |
入库方式： OAI收割
来源：新疆天文台
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。