Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Estimation of Doppler Velocity from Incoherent Scatter Spectra Using Context-Aware Transformers
Yanlin Liand Qihou Zhou
Abstract. We present a context-aware transformer model for estimating Doppler velocity from incoherent scatter radar (ISR) spectra. The model is based on the standard transformer encoder with adaptations from the Vision Transformer. Trained entirely on theoretical spectra, the AI model generalizes well for Arecibo ISR data and outperforms the traditional fitting methods significantly. Simulations show that the velocity error of the conventional least-squares fitting (LSF) is 1.5 to 3.5 times that of the AI model using 5 input heights. An inference from the AI model is approximately 100 times faster than the LSF method and requires minimal hardware, making it practical for large-scale or real-time processing. The AI approach applies to all situations where the spectrum can be parameterized.
Received: 10 Oct 2025 – Discussion started: 30 Oct 2025
Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
We introduce a transformer-based AI model for estimating Doppler velocity from incoherent scatter radar (ISR) spectra. Inspired by Vision Transformers, the model uses a standard transformer encoder adapted for radar data. Trained solely on simulated spectra, it performs well on real data from the Arecibo radar and significantly outperforms traditional least-squares fitting (LSF) methods. This approach is broadly applicable wherever spectral data can be parameterized.
We introduce a transformer-based AI model for estimating Doppler velocity from incoherent...
