English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Flagging of Radio Frequency Interference (RFI) is an increasingly importantchallenge in radio astronomy. We present R-Net, a deep convolutional ResNetarchitecture that significantly outperforms existing algorithms -- includingthe default MeerKAT RFI flagger, and deep U-Net architectures -- across allmetrics including AUC, F1-score and MCC. We demonstrate the robustness of thisimprovement on both single dish and interferometric simulations and, usingtransfer learning, on real data. Our R-Net model's precision is approximately$90\%$ better than the current MeerKAT flagger at $80\%$ recall and has a 35\%higher F1-score with no additional performance cost. We further highlight theeffectiveness of transfer learning from a model initially trained on simulatedMeerKAT data and fine-tuned on real, human-flagged, KAT-7 data. Despite thewide differences in the nature of the two telescope arrays, the model achievesan AUC of 0.91, while the best model without transfer learning only reaches anAUC of 0.67. We consider the use of phase information in our models but findthat without calibration the phase adds almost no extra information relative toamplitude data only. Our results strongly suggest that deep learning onsimulations, boosted by transfer learning on real data, will likely play a keyrole in the future of RFI flagging of radio astronomy data.

Deep Learning improves identification of Radio Frequency Interference