RADAR: Raman Spectral Analysis Using Deep Learning for Artifact Removal (Advanced Optical Materials 25/2025)
Raman Spectroscopy In article 10.1002/adom.202500736, Ion Petre and co-workers introduce RADAR, two lightweight deep learning models that simultaneously denoise and correct Raman spectra, reducing data acquisition time by up to 90% while preserving signal integrity. By streamlining artifact removal, RADAR enhances the speed, accuracy, and usability of Raman spectroscopy across diverse applications in materials science, biomedical research, and beyond.
Authors
- Andrei Păun (ORCID: https://orcid.org/0000-0002-1644-8198)
- Mioara Larion (ORCID: https://orcid.org/0000-0002-7016-9587)
- Joel Sjöberg
- Ion Petre (ORCID: https://orcid.org/0000-0002-5014-5529)
- Nicoleta Siminea (ORCID: https://orcid.org/0000-0002-9956-1718)
- Adrian Lita (ORCID: https://orcid.org/0000-0003-0115-6077)
Institutions
- National Institutes of Health (US)
- University of Bucharest (RO)
- University of Turku (FI)
- Turku University of Applied Sciences (FI)
- Academia Oamenilor de Știință din România (RO)
- National Institute for Research and Development in Informatics - ICI Bucharest (RO)
- National Institute of Research and Development for Biological Sciences (RO)
- National Cancer Institute (US)
- Romanian Academy (RO)
Publication Details
- Journal
- Advanced Optical Materials
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1002/adom.70254
- Primary Topic
- Industrial Vision Systems and Defect Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00