TY - JOUR
T1 - Gradient-Guided Attentional Network for Radio Transient Localization With the Cluster-Feed Telescope
AU - Cao, Hailin
AU - Peng, Junhui
AU - Fan, Jin
AU - Yong, Wai Yan
AU - Wu, Decheng
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 51877015, Grant U1831117, Grant U1931129, Grant U20A20157, Grant 11403054, and Grant 11611130023; in part by the Natural Science Foundation of Chongqing under Grant cstc2021jcyj-bsh0198; and in part by the Fundamental Research Funds for the Central Universities under Project 106112017CDJXSYY0002
Publisher Copyright:
© 1980-2012 IEEE.
PY - 2022/4/18
Y1 - 2022/4/18
N2 - Large, single-dish radio telescopes with high sensitivities are ideal for detecting faint radio transients (RTs). However, single-dish radio telescopes possess a limited angular resolution, which limits their accuracy in localizing objects. In this article, we propose to improve the localization accuracy of the RT by exploring the 3-D focal field distributions (3DFFDs) of the dish reflector with a gradient-guided attentional network (GGAN). The LSTM-based attention block of the GGAN achieves the task-oriented adaptive recalibration of 3DFFD features by exploring the significant properties and spatial dependencies of 3DFFD. In addition, a gradient-guided approach is being developed to improve the attention block performance under varying incident angles. The proposed attention mechanism is applied to the convolutional neural network in order to reconstruct 3DFFDs and perceive RT positions based on the reconstructed results. Simulation results indicate that the technique can enable the precise localization of RTs. Moreover, the proposed solution improves the telescope's instantaneous field of view (FOV) compared to a sky survey with the traditional cluster feed telescope.
AB - Large, single-dish radio telescopes with high sensitivities are ideal for detecting faint radio transients (RTs). However, single-dish radio telescopes possess a limited angular resolution, which limits their accuracy in localizing objects. In this article, we propose to improve the localization accuracy of the RT by exploring the 3-D focal field distributions (3DFFDs) of the dish reflector with a gradient-guided attentional network (GGAN). The LSTM-based attention block of the GGAN achieves the task-oriented adaptive recalibration of 3DFFD features by exploring the significant properties and spatial dependencies of 3DFFD. In addition, a gradient-guided approach is being developed to improve the attention block performance under varying incident angles. The proposed attention mechanism is applied to the convolutional neural network in order to reconstruct 3DFFDs and perceive RT positions based on the reconstructed results. Simulation results indicate that the technique can enable the precise localization of RTs. Moreover, the proposed solution improves the telescope's instantaneous field of view (FOV) compared to a sky survey with the traditional cluster feed telescope.
KW - 3-D focal field distribution (3DFFD)
KW - attentional network
KW - localization of radio transients (RTs)
KW - single-dish radio telescope
KW - wide field of view (FoV)
KW - 2023 OA procedure
UR - http://www.scopus.com/inward/record.url?scp=85128594544&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2022.3167762
DO - 10.1109/TGRS.2022.3167762
M3 - Article
AN - SCOPUS:85128594544
SN - 0196-2892
VL - 60
JO - IEEE transactions on geoscience and remote sensing
JF - IEEE transactions on geoscience and remote sensing
M1 - 4601511
ER -