Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy.
A methodology is proposed, which addresses the caveat that line-of-sight emission spectroscopy presents in that it cannot provide spatially resolved temperature measurements in non-homogeneous temperature fields. The aim of this research is to explore the use of data-driven models in measuring tempe...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0317703 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849314253554581504 |
|---|---|
| author | Ruiyuan Kang Dimitrios C Kyritsis Panos Liatsis |
| author_facet | Ruiyuan Kang Dimitrios C Kyritsis Panos Liatsis |
| author_sort | Ruiyuan Kang |
| collection | DOAJ |
| description | A methodology is proposed, which addresses the caveat that line-of-sight emission spectroscopy presents in that it cannot provide spatially resolved temperature measurements in non-homogeneous temperature fields. The aim of this research is to explore the use of data-driven models in measuring temperature distributions in a spatially resolved manner using emission spectroscopy data. Two categories of data-driven methods are analyzed: (i) Feature engineering and classical machine learning algorithms, and (ii) end-to-end convolutional neural networks (CNN). In total, combinations of fifteen feature groups and fifteen classical machine learning models, and eleven CNN models are considered and their performances explored. The results indicate that the combination of feature engineering and machine learning provides better performance than the direct use of CNN. Notably, feature engineering, which is comprised of physics-guided transformation, signal representation-based feature extraction and Principal Component Analysis is found to be the most effective. Moreover, it is shown that when using the extracted features, the ensemble-based, light blender learning model offers the best performance with RMSE, RE, RRMSE and R values of 64.3, 0.017, 0.025 and 0.994, respectively. The proposed method, based on feature engineering and the light blender model, is capable of measuring nonuniform temperature distributions from low-resolution spectra, even when the species concentration distribution in the gas mixtures is unknown. |
| format | Article |
| id | doaj-art-a2f2e253dfe848e092d7270036413d66 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-a2f2e253dfe848e092d7270036413d662025-08-20T03:52:29ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031770310.1371/journal.pone.0317703Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy.Ruiyuan KangDimitrios C KyritsisPanos LiatsisA methodology is proposed, which addresses the caveat that line-of-sight emission spectroscopy presents in that it cannot provide spatially resolved temperature measurements in non-homogeneous temperature fields. The aim of this research is to explore the use of data-driven models in measuring temperature distributions in a spatially resolved manner using emission spectroscopy data. Two categories of data-driven methods are analyzed: (i) Feature engineering and classical machine learning algorithms, and (ii) end-to-end convolutional neural networks (CNN). In total, combinations of fifteen feature groups and fifteen classical machine learning models, and eleven CNN models are considered and their performances explored. The results indicate that the combination of feature engineering and machine learning provides better performance than the direct use of CNN. Notably, feature engineering, which is comprised of physics-guided transformation, signal representation-based feature extraction and Principal Component Analysis is found to be the most effective. Moreover, it is shown that when using the extracted features, the ensemble-based, light blender learning model offers the best performance with RMSE, RE, RRMSE and R values of 64.3, 0.017, 0.025 and 0.994, respectively. The proposed method, based on feature engineering and the light blender model, is capable of measuring nonuniform temperature distributions from low-resolution spectra, even when the species concentration distribution in the gas mixtures is unknown.https://doi.org/10.1371/journal.pone.0317703 |
| spellingShingle | Ruiyuan Kang Dimitrios C Kyritsis Panos Liatsis Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. PLoS ONE |
| title | Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. |
| title_full | Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. |
| title_fullStr | Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. |
| title_full_unstemmed | Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. |
| title_short | Comparative analysis of data-driven models for spatially resolved thermometry using emission spectroscopy. |
| title_sort | comparative analysis of data driven models for spatially resolved thermometry using emission spectroscopy |
| url | https://doi.org/10.1371/journal.pone.0317703 |
| work_keys_str_mv | AT ruiyuankang comparativeanalysisofdatadrivenmodelsforspatiallyresolvedthermometryusingemissionspectroscopy AT dimitriosckyritsis comparativeanalysisofdatadrivenmodelsforspatiallyresolvedthermometryusingemissionspectroscopy AT panosliatsis comparativeanalysisofdatadrivenmodelsforspatiallyresolvedthermometryusingemissionspectroscopy |