AirNet: A Deep Learning-Driven Auto Baseline Correction Algorithm Balancing Global Smoothness and Local Fidelity

2026/06/11 by S Wang, Hao-ping Wu, Si-Heng Luo +12 · 1 voice
Biochemistry, Genetics and Molecular Biology · Physics and Astronomy · Engineering · #Spectroscopy Techniques in Biomedical and Chemical Research #Spectroscopy and Quantum Chemical Studies #Optical Polarization and Ellipsometry

paper · doi:10.1021/acs.analchem.6c01550

openalex publication_date 2026/06/11 · openalex created_date 2026/06/12 · openalex updated_date 2026/07/22

Abstract

quares (Dr-airPLS) under optimized smoothness. On both simulated and experimental Raman spectra, AirNet outperforms algorithms like airPLS, OP-airPLS, and DIRAS in both accuracy and generalizability, with a speed of 0.3 s per spectrum. Furthermore, the Homologous Model of AirNet ensures consistent baseline correction across homologous spectra. The segmented fitting strategy applies a region-specific smoothing parameter, facing a Raman spectrum with drastically changed background gradients. AirNet extracts high-fidelity Raman spectral information, providing a solid basis for reliable spectrum-structure correlation.

Citations

• Baseline correction using a deep-learning model combining ResNet and UNet

Discussions

• AirNet: A Deep Learning-Driven Auto Baseline Correction Algorithm Balancing Global Smoothness and Local Fidelity Anal. Chem. 2026 doi.org/10.1021/acs.... #raman [bsky, 1 points, 0 comments]

Related

• Baseline correction using a deep-learning model combining ResNet and UNet
• Refinement of spectra using a deep neural network: Fully automated removal of noise and background
• Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy
• RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics
• RamanNet: A generalized neural network architecture for Raman Spectrum Analysis