A research team from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences Chinese Academy of Sciences, has developed a comprehensive algorithm framework that dramatically improves the accuracy, robustness and dynamic range performance of Fourier transform infrared spectroscopy (FTIR) for gas analysis.

This advancement delivers improvements in four key areas: mixture identification, baseline reconstruction, concentration inversion, and adaptive band selection.

FTIR spectroscopy is widely used in environmental monitoring, industrial emission analysis and national security. However, real-world measurements are often limited by overlapping absorption features, instrument differences, nonlinear responses at high concentrations and baseline drift. The researchers designed their methods to directly address these long-standing challenges.

A notable outcome of the research is a deep-learning model that significantly improves mixture identification across different instruments. Trained on data from one instrument, it maintained over 91% accuracy on nine unseen line shapes, demonstrating its potential for cross-device deployment.

To correct hidden baseline distortions in mixed-gas spectra, the team introduced a relative-absorbance independent component analysis (ICA) method that reconstructs baselines with greater accuracy than commonly used techniques while preserving the fine baseline structure that is important for multi-component detection.

For gas quantification, the researchers developed a "Suppression–Adaptation–Optimization" model that integrates noise reduction, residual modeling and adaptive loss optimization. Tests showed that it improves concentration inversion accuracy for carbon dioxide (CO₂), nitrous oxide (N₂O) and carbon monoxide (CO) by about 15% under noisy conditions.

Finally, their information density-based adaptive band selection method allows FTIR systems to automatically select the optimal spectral regions. When validated using methane, the method demonstrated a wide linear dynamic range, greatly extending the capability of FTIR in high-concentration scenarios.

These advances provide a stronger foundation for using FTIR in complex environments and for improving its performance in gas analysis.

Deep learning network based on an attention mechanism for mixture identification (Image by XU Tairan)