Identification of H 2 and NH 3 gases using calorimetric signals and transient response through machine learning

Abstract Selectivity remains a significant challenge for gas sensors. In contrast to conventional gas sensors that depend solely on conductivity to detect gases, we exploited a single NiO-doped SnO 2 sensor to simultaneously monitor transient changes in both sensor conductivity and temperature. The distinct response profiles of H 2 and NH 3 gases were attributed to differences in their redox rates and enthalpy changes during chemical reactions, which provided an opportunity for gas identification using machine learning (ML) algorithms. The test results indicate that preprocessing the extracted calorimetric and chemi-resistive parameters using the principal component analysis (PCA), followed by the application of ML classifiers for identification, enables a 100% accuracy for both target analytes. This work presents a facile gas identification method that enhances chip-level sensor applications while minimizing the need for complex sensor arrays.