FinalKAN: A Dual-Stream KAN Network Integrating Multisource Features for Radio Telescope Pointing Correction
文献类型：期刊论文
| 作者 | He, Yao2; Hao LF(郝龙飞)1; Dai, Wei2 |
| 刊名 | ADVANCES IN ASTRONOMY
 |
| 出版日期 | 2026 |
| 卷号 | 2026期号:1 |
| 关键词 | dual-stream architecture Kolmogorov-Arnold network machine learning pointing error correction radio telescope |
| ISSN号 | 1687-7969 |
| DOI | 10.1155/aa/7212588 |
| 产权排序 | 第2完成单位 |
| 文献子类 | Article |
| 英文摘要 | This paper investigates the degradation of pointing accuracy in the Kunming 40-m radio telescope due to long-term equipment aging and environmental disturbances. Conventional linear pointing models are constrained by their linear modeling framework, making it difficult to accurately represent the nonlinear errors induced by temperature, wind speed, and gear backlash, thereby limiting high-frequency, high-resolution observations. We propose a dual-stream Kolmogorov-Arnold network (FinalKAN) that integrates multisource environmental dynamics. Guided by the Kolmogorov-Arnold representation theorem, our heterogeneous dual-stream architecture employs stream-specific feature selection for angular and environmental inputs, a cross-stream attention mechanism, and a multistrategy fusion module to jointly model and compensate for errors from multiple disturbance sources. Experiments on a historical dataset from the Kunming 40-m telescope (6,734 samples, 74 radio sources, and 8 feature variables) demonstrate that FinalKAN achieves a root mean square error (RMSE) of 28. 26('') in azimuth and 14. 89('') in elevation under five-fold cross-validation, improving over least-squares modeling by 21.6% and 20.9%, respectively, and outperforming baselines including extreme gradient boosting (XGBoost) and multilayer perceptron (MLP). Ablation studies confirm the contributions of the dual-stream design, cross-stream attention, and directional encoding. The method provides a data-driven, interpretable solution for high-precision pointing control in radio telescopes, with practical implications for enhancing observational performance. |
| 学科主题 | 天文学 ; 射电天文学 |
| URL标识 | 查看原文 |
| 出版地 | 111 RIVER ST, HOBOKEN 07030-5774, NJ USA |
| WOS关键词 | ERROR |
| 资助项目 | National Natural Science Foundation of China[12063003]; National Natural Science Foundation of China[12073076] |
| WOS研究方向 | Astronomy & Astrophysics |
| 语种 | 英语 |
| WOS记录号 | WOS:001699022900001 |
| 出版者 | WILEY |
| 资助机构 | National Natural Science Foundation of China[12063003, 12073076] |
| 版本 | 出版稿 |
| 源URL | [http://ir.ynao.ac.cn/handle/114a53/28990]  |
| 专题 | 云南天文台_射电天文研究组 |
| 通讯作者 | Dai, Wei |
| 作者单位 | 1.YunnanObservatories, Chinese Academy of Sciences, Kunming 650000, Yunnan, China 2.Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China; |
| 推荐引用方式 GB/T 7714 | He, Yao,Hao LF,Dai, Wei. FinalKAN: A Dual-Stream KAN Network Integrating Multisource Features for Radio Telescope Pointing Correction[J]. ADVANCES IN ASTRONOMY,2026,2026(1). |
| APA | He, Yao,郝龙飞,&Dai, Wei.(2026).FinalKAN: A Dual-Stream KAN Network Integrating Multisource Features for Radio Telescope Pointing Correction.ADVANCES IN ASTRONOMY,2026(1). |
| MLA | He, Yao,et al."FinalKAN: A Dual-Stream KAN Network Integrating Multisource Features for Radio Telescope Pointing Correction".ADVANCES IN ASTRONOMY 2026.1(2026). |
入库方式： OAI收割
来源：云南天文台
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。