Automatic Detection of VLF Tweek Signals Based on the YOLO Model

Abstract

Tweek signals are a special type of VLF (very low frequency) pulse, originally produced by lightning discharge, which becomes dispersive after repetitive bounces within the waveguide between the Earth’s surface and lower ionosphere. As such, tweek signals carry critical information about the region near the reflection height of the VLF waves, namely the D-region ionosphere. Although tweek measurements have been widely utilized in studies of the D-region ionosphere and lightning discharge, few statistical studies have been conducted, mainly due to the difficulty of manually identifying tweek signals from the enormous amount of VLF data with heavy noise. Considering the importance of tweek signals and the lack of a high-precision detection model, in this study, we propose a method to automatically and accurately pick out tweek signals from VLF measurements. This method is explicitly developed based on the you only look once (YOLO) model and a post-tracing process. Using a total of 2495 randomly selected VLF spectrogram images as the testing set, we evaluated the performance of this method. The precision and recall are found to be 92.0% and 89.2% for the first-order mode, and 97.5% and 86.7% for the first-two-order mode tweek, respectively. The time needed to process 10-s VLF measurements with a cadence of 4 μs is only 6.5 s, allowing for identifying the tweek signals from continuous VLF measurements in real time. Therefore, this method represents a reliable means to automatically detect tweek signals and enables the opportunity to statistically investigate the D-region ionosphere and lightning discharge via these signals.

Intelligent Detection Method for Satellite TT&C Signals under Restricted Conditions Based on TATR

“…Li et al [29] divide the entire signal frequency band into broadband segments, obtain time-frequency maps using short-time Fourier transform, and propose a CNN-based broadband signal detection method, successfully detecting and recognizing six types of signals. Additionally, Xu [34] introduces a deep learning method based on YOLO to automatically and accurately pick out tweek signals from VLF measurements. The aforementioned deep-learning-based methods typically require time-domain IQ sequences or their transformed counterparts, such as time-frequency spectrograms, as inputs to deep neural networks.…”

Optimizing Geo-Hazard Response: LBE-YOLO’s Innovative Lightweight Framework for Enhanced Real-Time Landslide Detection and Risk Mitigation

“…The mean average precision (mAP) represents the average of precision computed at various recall levels, serving as a comprehensive metric for model evaluation. The F1, the harmonic mean of precision and recall, is employed to holistically assess the model's accuracy and stability, providing a balanced view of the model performance [55,56].…”