Search for Cosmic-Ray Events Using Radio Signals and CNNs in Data from the IceTop Enhancement Prototype Station

Abstract

Cosmic-ray air showers emit radio waves that can be used to measure the properties of cosmic-ray primary particles. The radio detection technique presents several advantages, such as low cost and year-round duty cycle as well as the ability to provide high sensitivity to X max and energy estimation with minimal theoretical uncertainties, making it a promising tool for studying cosmic rays at the highest energies. However, the primary limitation of radio detection is the irreducible background from various sources that obscure the impulsive signals generated by air showers. To address this issue, we investigated the use of Convolutional Neural Networks (CNNs), trained on CoREAS simulations and radio backgrounds measured by a prototype station at the South Pole. We developed two different CNNs: a Classifier that distinguishes between cosmic ray event radio signals and pure background waveforms, and a Denoiser that mitigates background noise to recover the underlying cosmic-ray signal. After training the networks we apply them to the air-shower data to search for radio events. With two months data, we were able to identify 51 candidate events. The event's arrival direction reconstructed using CNN denoised radio waveforms is found to be in good agreement with the IceTop reconstruction. Finally, our approach demonstrated improved directional reconstruction compared to traditional methods.

New IceTop trigger in the context of the planned IceCube surface detector enhancement at the South Pole

“…So, there is an improvement in trigger efficiency for inclined events above 10 PeV with the IceTop7HG trigger. In the future, when there will be several surface array enhancement stations with radio antennas, it is expected that with the implementation of the IceTop7HG trigger in IceTop, coincident detection of air showers with radio and IceTop tanks can be done for energies > 10 PeV where radio antennas start to get sensitive to air showers at the South Pole [7].…”

Cosmic ray detection with the IceTop Enhancement

“…A second approach uses CNN to identify radio pulses in high background [10]. A Classifier was used for identifying signal from background and a Denoiser was used to clean the traces from the background RFI.…”

“…A Classifier was used for identifying signal from background and a Denoiser was used to clean the traces from the background RFI. [10] where the raw waveforms are represented in blue, waveforms after using the Denoiser in orange and after the use of a spike filter with black dashed lines.…”

“…Figure 4: Figure from Ref [10]. where the raw waveforms are represented in blue, waveforms after using the Denoiser in orange and after the use of a spike filter with black dashed lines.…”