RADAR: Raman Spectral Analysis Using Deep Learning for Artifact Removal

Abstract Raman spectroscopy is a non‐destructive analytical technique that reveals molecular vibrations, enabling precise identification of chemical compounds and material properties. Its spatial resolution and compatibility with microscopic imaging allow for high‐resolution chemical mapping of heterogeneous samples. However, spectral artifacts such as baseline drift, cosmic rays, and instrumental noise complicate data interpretation, necessitating correction. RADAR is introduced, two lightweight deep learning models for artifact removal, capable of simultaneous denoising and correction of Raman spectra, significantly accelerating high‐quality data acquisition. The models help reduce the data acquisition time by 90% while preserving signal integrity, as demonstrated on noisy spectra from a diversity of samples, biological and non‐biological. These models are versatile and can be readily applied to novel Raman datasets, offering an order‐of‐magnitude improvement in acquisition efficiency. This work advances Raman spectroscopy as a faster, more reliable tool for chemical analysis, with broad applications in materials science, biomedical research, and beyond.