Machine Learning‐Assisted Research and Development of Chemiresistive Gas Sensors

Abstract

The traditional trial‐and‐error testing to develop high‐performance chemiresistive gas sensors is inefficient and fails to meet the high demand for sensors in various industries. Machine learning (ML) can address the limitations of trial‐and‐error testing and can be effectively utilized for enhancing, developing, and designing sensors. This review first discusses the prediction of critical mechanism parameters of gas‐sensitive materials by ML, including adsorption energy, bandgap, thermal conductivity, and dielectric constant. Second, it proposes that ML can improve five performance indexes: selectivity, response/recovery time, stability, sensitivity, and accuracy. ML also facilitates the development and structural design of gas‐sensitive new materials. In addition, the potential of ML to optimize the sensor arrays is investigated, including reducing the number of sensors, identifying the best array combination, and improving recognition and detection capabilities. Finally, this article discusses the challenges and limitations of machine‐learning assisted chemiresistive gas sensors in practical applications and envisions their future development.