Deep residual detection of radio frequency interference for FAST

Radio frequency interference (RFI) detection and excision are key steps in the data-processing pipeline of the Five-hundred-meter Aperture Spherical radio Telescope (FAST). Because of its high sensitivity and large data rate, FAST requires more accurate and efficient RFI flagging methods than its counterparts. In the last decades, approaches based upon artificial intelligence (AI), such as codes using convolutional neural networks (CNNs), have been proposed to identify RFI more reliably and efficiently. However, RFI flagging of FAST data with such methods has often proved to be erroneous, with further manual inspections required. In addition, network construction as well as preparation of training data sets for effective RFI flagging has imposed significant additional workloads. Therefore, rapid deployment and adjustment of AI approaches for different observations is impractical to implement with existing algorithms. To overcome such problems, we propose a model called RFI-Net. With the input of raw data without any processing, RFI-Net can detect RFI automatically, producing corresponding masks without any alteration of the original data. Experiments with RFI-Net using simulated astronomical data show that our model has outperformed existing methods in terms of both precision and recall. Besides, compared with other models, our method can obtain the same relative accuracy with fewer training data, thus reducing the effort and time required to prepare the training data set. Further, the training process of RFI-Net can be accelerated, with overfittings being minimized, compared with other CNN codes. The performance of RFI-Net has also been evaluated with observing data obtained by FAST and the Bleien Observatory. Our results demonstrate the ability of RFI-Net to accurately identify RFI with fine-grained, high-precision masks that required no further modification.

[1]  Kang Ryoung Park,et al.  FRED-Net: Fully residual encoder-decoder network for accurate iris segmentation , 2019, Expert Syst. Appl..

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  Attila Popping,et al.  The standing wave phenomenon in radio telescopes - Frequency modulation of the WSRT primary beam , 2007, 0712.2303.

[4]  Francisco Herrera,et al.  Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation , 2018, Expert Syst. Appl..

[5]  Keeley A. Crockett,et al.  A methodology for the resolution of cashtag collisions on Twitter - A natural language processing & data fusion approach , 2019, Expert Syst. Appl..

[6]  Jian Li,et al.  Learning Gradient Descent: Better Generalization and Longer Horizons , 2017, ICML.

[7]  Robert Meersman,et al.  On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE , 2003, Lecture Notes in Computer Science.

[8]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[9]  G. Desvignes,et al.  SEARCHING FOR PULSARS USING IMAGE PATTERN RECOGNITION , 2013, 1309.0776.

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  A. Kappes,et al.  Detecting radio frequency interference in radio-antenna arrays with the recurrent neural network algorithm , 2018, Astronomische Nachrichten.

[12]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[13]  Carlos Aguirre,et al.  Deep multi-survey classification of variable stars , 2018, Monthly Notices of the Royal Astronomical Society.

[14]  Di Li,et al.  The Five-hundred-meter Aperture Spherical radio Telescope (FAST) project , 2011, 2015 International Topical Meeting on Microwave Photonics (MWP).

[15]  Adam Amara,et al.  HIDE & SEEK: End-to-end packages to simulate and process radio survey data , 2016, Astron. Comput..

[16]  Michael Inggs,et al.  A CNN and LSTM-based approach to classifying transient radio frequency interference , 2018, Astron. Comput..

[17]  Computer-Assisted Intervention,et al.  Medical Image Computing and Computer-Assisted Intervention – MICCAI’99 , 1999, Lecture Notes in Computer Science.

[18]  Willem A. Baan,et al.  Radio Frequency Interference Mitigation at the Westerbork Synthesis Radio Telescope: Algorithms, Test Observations, and System Implementation , 2004 .

[19]  Michael Biehl,et al.  Post‐correlation radio frequency interference classification methods , 2010, 1002.1957.

[20]  Alejandro F. Frangi,et al.  Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015 , 2015, Lecture Notes in Computer Science.

[21]  Chihway Chang,et al.  Radio frequency interference mitigation using deep convolutional neural networks , 2016, Astron. Comput..

[22]  W. van Driel,et al.  Driftscan Surveys in the 21 cm Line with the Arecibo and Nançay Telescopes , 1997, Publications of the Astronomical Society of Australia.

[23]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..