Robust gas species and concentration monitoring via cross-talk transformer with snapshot infrared spectral imager

Abstract

With the rising industrialization, monitoring of chemical gases such as carbon dioxide, methane, and sulfur dioxide has become critical due to their profound impact on the global environment, human health, and industrial development. Recently, the Uncooled Snapshot Infrared Spectrometer (USIRS) has been employed for rapid, long-distance identification and concentration sensing of various gases. However, these uncooled instruments face limitations in gas detection accuracy due to weak signals and a low signal-to-noise ratio. To address these issues, we introduce the Cross-talk Transformer, which leverages the attention mechanism to learn deep correlations between the target gas and the gas spectral library. Furthermore, we have developed a comprehensive radiation transfer model for USIRS to generate substantial data, thereby adequately training the Cross-talk Transformer. Upon validation, our method achieves a recognition accuracy of 98.63% on experimental data for 11 types of chemical gases. In terms of concentration prediction, our approach attains a mean error of 330 ppm for chemical gases with concentrations up to 30,000 ppm. These results highlight the high accuracy and robustness of our method in monitoring gas types and concentrations, demonstrating its potential for industrial monitoring and other applications.