Semiquantitative Classification of Two Oxidizing Gases with Graphene-Based Gas Sensors

• Published in: Chemosensors 2022-02, Vol.10 (2), p.68
• Main Authors: Lind, Martin, Kiisk, Valter, Kodu, Margus, Kahro, Tauno, Renge, Indrek, Avarmaa, Tea, Makaram, Prashanth, Zurutuza, Amaia, Jaaniso, Raivo
• Format: Article
• Language: English
• Subjects: Accuracy; Air pollution; Algorithms; Amplitudes; Chemical vapor deposition; Classification; Copper oxides; Discriminant analysis; Electronic noses; gas sensor; Gas sensors; Gases; Graphene; Indium oxides; Internet of Things; Laser beam heating; Lasers; Learning algorithms; Machine learning; Manganese dioxide; Metal oxides; Nanomaterials; Nitrogen dioxide; NO2; Oxidation; Oxide coatings; Pollution monitoring; Pulsed laser deposition; Pulsed lasers; Recovery; Relative humidity; Scandium oxides; Sensors; Silicon nitride; Silicon substrates; VOCs; Volatile organic compounds
• ISSN: 2227-9040; 2227-9040
• DOI: 10.3390/chemosensors10020068

Miniature and low-power gas sensing elements are urgently needed for a portable electronic nose, especially for outdoor pollution monitoring. Hereby we prepared chemiresistive sensors based on wide-area graphene (grown by chemical vapor deposition) placed on Si/Si3N4 substrates with interdigitated electrodes and built-in microheaters. Graphene of each sensor was individually functionalized with ultrathin oxide coating (CuO-MnO2, In2O3 or Sc2O3) by pulsed laser deposition. Over the course of 72 h, the heated sensors were exposed to randomly generated concentration cycles of 30 ppb NO2, 30 ppb O3, 60 ppb NO2, 60 ppb O3 and 30 ppb NO2 + 30 ppb O3 in synthetic air (21% O2, 50% relative humidity). While O3 completely dominated the response of sensors with CuO-MnO2 coating, the other sensors had comparable sensitivity to NO2 as well. Various response features (amplitude, response rate, and recovery rate) were considered as machine learning inputs. Using just the response amplitudes of two complementary sensors allowed us to distinguish these five gas environments with an accuracy of ~ 85%. Misclassification was mostly due to an overlap in the case of the 30 ppb O3, and 30 ppb O3 + 30 ppb NO2 responses, and was largely caused by the temporal drift of these responses. The addition of recovery rates to machine learning input variables enabled us to very clearly distinguish different gases and increase the overall accuracy to ~94%.