Distinguishing methane from other hydrocarbons using machine learning and atmospheric pressure plasma optical emission spectroscopy

Tahereh Shah Mansouri, Hui Wang, Davide Mariotti, Paul Maguire

Research output: Contribution to journalArticlepeer-review

5 Downloads (Pure)


The ability to detect gas molecule and assign a concentration offers an inventive solution in the field of plasma integrated with machine learning. The most important finding of this work is firstly, to develop an algorithm for gas-molecule identification using three different hydrocarbons (CH4, C2H2, C2H6) and secondly, organize a model for detecting gas concentration (classification). For this reason, initially eight different gases evaluated. The study confirms the present of the unique emission lines as a gas indicator, i.e., a wavelength peak related to hydrocarbons identified via increasing in C x H y concentration. By means of unique variable important in projection, hydrocarbons can be distinguished. Our proposed Chemometric analysis strategy examined on >1000 samples and results development of suitable techniques that are sufficiently rapid, accurate and innovative. This demonstrates the potential for real-time, portable, and continuous monitoring of trace gases with potential applications in medical, environmental, and industrial gas sensing.
Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalJournal of Physics D: Applied Physics
Issue number34
Early online date4 Jun 2024
Publication statusPublished online - 4 Jun 2024

Data Access Statement

The data cannot be made publicly available upon publication because they are not available in a format that is sufficiently accessible or reusable by other researchers. The data that support the findings of this study are available upon reasonable request from the authors.


  • methane identification
  • optical emission spectroscopy (OES)
  • variable importance in projection (VIP)
  • unique VIP
  • partial least square discriminant analysis
  • hydrocarbons
  • classification


Dive into the research topics of 'Distinguishing methane from other hydrocarbons using machine learning and atmospheric pressure plasma optical emission spectroscopy'. Together they form a unique fingerprint.

Cite this