Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data

Abstract

Infrared absorption spectroscopy is a widely used tool to quantify and monitor compositions of gases. The concentration information is often retrieved by fitting absorption profiles to the acquired spectra, utilizing spectroscopic databases. In complex gas matrices an expanded parameter space leads to long computation times of the fitting routines due to the increased number of spectral features that need to be computed for each iteration during the fit. This hinders the capability of real-time analysis of the gas matrix. Here, an artificial neural network (ANN) is employed for rapid prediction of gas concentrations in complex infrared absorption spectra composed of mixtures of CO and N2O. Experimental data is acquired with a mid-infrared dual frequency comb spectrometer. To circumvent the experimental collection of huge amounts of training data, the network is trained on synthetically generated spectra. The spectra are based on simulated absorption profiles making use of the HITRAN database. In addition, the spectrometer’s influence on the measured spectra is characterized and included in the synthetic training data generation. The ANN was tested on measured spectra and compared to a non-linear least squares fitting algorithm. An average evaluation time of 303 µs for a single measured spectrum was achieved. Coefficients of determination were 0.99997 for the predictions of N2O concentrations and 0.99987 for the predictions of CO concentrations, with uncertainties on the predicted concentrations between 0.04 and 0.18 ppm for 0 to 100 ppm N2O and between 0.05 and 0.18 ppm for 0 to 60 ppm CO.

A sub-ppbv-level Acetone and Ethanol Quantum Cascade Laser Based Photoacoustic Sensor – Characterization and Multi-Component Spectra Recording in Synthetic Breath

“…Synthetic spectra are very desirable in spectroscopy as they allow a low-cost data generation, which can be used to train and develop machine learning based algorithms. The feasibility of a gas detection system trained solely on synthetic data was shown by Goldschmidt et al [52] for dual-comb spectroscopy of N 2 O and CO. Zifarelli et al [53] use a measured dataset enriched with synthetic data to detect N 2 O and CO with an addition of C 2 H 2 using a quartz-enhanced PAS (QEPAS) system. They apply a linear combination of their wavelength modulated measurements to augment their dataset as their spectra do not suffer from a strong background.…”

Analysis of Gas Mixtures with Broadband Dual Frequency Comb Spectroscopy and Unsupervised Learning Neural Network

“…Although DCS decreases the measurement time and thus reduces the impact of long timescale drifts or fluctuations, such as of the output laser power or temperature on the overall data collection, the challenges of baseline variations, due for instance, to unknown absorbers and background noise can still degrade the accuracy of simultaneous detection of multiple molecules over a broad spectral range. [ 15 ]…”

“…Although DCS decreases the measurement time and thus reduces the impact of long timescale drifts or fluctuations, such as of the output laser power or temperature on the overall data collection, the challenges of baseline variations, due for instance, to unknown absorbers and background noise can still degrade the accuracy of simultaneous detection of multiple molecules over a broad spectral range. [15] Modeling and fitting of the blended spectra is a feasible way to overcome such challenges. To determine the concentrations of gases of interest, fitting algorithms based on nonlinear least squares, such as partial least squares (PLS), are often employed, [16,17] relying on absorption profiles provided by spectroscopic databases such as HITRAN [18] or PNNL.…”

Online Monitoring of Seawater Carbon Dioxide Based on an Infrared Rear Beam Splitter

“…Schroder et al in 2022 proposed a new multispectral NDIR gas sensor capable of achieving a 90% decrease in signal intensity in ten seconds when the concentration was changed and set up for the direct conversion of values to ppm units [ 16 ]. In fact, most of the carbon dioxide detection is focused on air, using optical paths with multiple reflective devices [ 17 , 18 , 19 ]. It is well known that carbon dioxide molecules are polar and interact with other molecules, which affects the sensitivity and accuracy of the sensor.…”