Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/3/857 |
| _version_ | 1797484805245370368 |
|---|---|
| author | Jens Goldschmidt Leonard Nitzsche Sebastian Wolf Armin Lambrecht Jürgen Wöllenstein |
| author_facet | Jens Goldschmidt Leonard Nitzsche Sebastian Wolf Armin Lambrecht Jürgen Wöllenstein |
| author_sort | Jens Goldschmidt |
| collection | DOAJ |
| description | 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 N<sub>2</sub>O. 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 N<sub>2</sub>O 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 N<sub>2</sub>O and between 0.05 and 0.18 ppm for 0 to 60 ppm CO. |
| first_indexed | 2024-03-09T23:09:45Z |
| format | Article |
| id | doaj.art-6893007e679e447cac54bbfa1ae63bed |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T23:09:45Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6893007e679e447cac54bbfa1ae63bed2023-11-23T17:46:31ZengMDPI AGSensors1424-82202022-01-0122385710.3390/s22030857Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic DataJens Goldschmidt0Leonard Nitzsche1Sebastian Wolf2Armin Lambrecht3Jürgen Wöllenstein4Laboratory for Gas Sensors, Department of Microsystems Engineering-IMTEK, University of Freiburg, Georges-Köhler-Allee 102, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, Georges-Köhler-Allee 301, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, Georges-Köhler-Allee 301, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, Georges-Köhler-Allee 301, 79110 Freiburg, GermanyLaboratory for Gas Sensors, Department of Microsystems Engineering-IMTEK, University of Freiburg, Georges-Köhler-Allee 102, 79110 Freiburg, GermanyInfrared 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 N<sub>2</sub>O. 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 N<sub>2</sub>O 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 N<sub>2</sub>O and between 0.05 and 0.18 ppm for 0 to 60 ppm CO.https://www.mdpi.com/1424-8220/22/3/857spectral analysisquantitative gas analysismachine learningartificial neural networksdual comb spectroscopybroadband spectroscopy |
| spellingShingle | Jens Goldschmidt Leonard Nitzsche Sebastian Wolf Armin Lambrecht Jürgen Wöllenstein Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data Sensors spectral analysis quantitative gas analysis machine learning artificial neural networks dual comb spectroscopy broadband spectroscopy |
| title | Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data |
| title_full | Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data |
| title_fullStr | Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data |
| title_full_unstemmed | Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data |
| title_short | Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data |
| title_sort | rapid quantitative analysis of ir absorption spectra for trace gas detection by artificial neural networks trained with synthetic data |
| topic | spectral analysis quantitative gas analysis machine learning artificial neural networks dual comb spectroscopy broadband spectroscopy |
| url | https://www.mdpi.com/1424-8220/22/3/857 |
| work_keys_str_mv | AT jensgoldschmidt rapidquantitativeanalysisofirabsorptionspectrafortracegasdetectionbyartificialneuralnetworkstrainedwithsyntheticdata AT leonardnitzsche rapidquantitativeanalysisofirabsorptionspectrafortracegasdetectionbyartificialneuralnetworkstrainedwithsyntheticdata AT sebastianwolf rapidquantitativeanalysisofirabsorptionspectrafortracegasdetectionbyartificialneuralnetworkstrainedwithsyntheticdata AT arminlambrecht rapidquantitativeanalysisofirabsorptionspectrafortracegasdetectionbyartificialneuralnetworkstrainedwithsyntheticdata AT jurgenwollenstein rapidquantitativeanalysisofirabsorptionspectrafortracegasdetectionbyartificialneuralnetworkstrainedwithsyntheticdata |