Dual-gas sensing via SnO2-TiO2 heterojunction on MXene: Machine learning-enhanced selectivity and sensitivity for hydrogen and ammonia detection

Abstract

This study presents a novel strategy for the rapid detection of hydrogen and ammonia gases through the synthesis of a composite material that integrates SnO₂ and TiO₂ into an n-n heterostructure on the surface of two-dimensional layered Ti₃C₂Tx MXene. The incorporation of Pd nanoparticles significantly enhances the sensor's adsorption and sensing capabilities, particularly for hydrogen. The resulting dual-gas sensor demonstrates a pronounced linear response to hydrogen with a low detection limit of 200 ppb, along with rapid response times, excellent repeatability and long-term stability. Leveraging MXene's superior ammonia adsorption properties, the sensor also exhibits commendable linearity and robustness in detecting ammonia, with strong resistance to humidity-induced interference. To further improve the sensor's performance, machine learning techniques such as support vector machine (SVM) and artificial neural network (ANN) are incorporated, substantially enhancing the sensor's selectivity and sensitivity of the detection. These advancement enables the precise identification and quantification of complex gas mixtures containing hydrogen and ammonia. The sensor’s meticulously designed circuitry operates in real-time sensing mode, ensuring accurate differentiation between the two gases. This research establishes a robust foundation for the development of advanced gas sensing technology, showcasing its potential for multi-gas detection and analysis across diverse industrial and environmental applications.