Enabling Weather-Independent Gas Detection through Deep Learning on Light-Activated Sensors

Light-activated gas sensors offer a low-temperature, low-power approach for detecting target species, and their high-performance capabilities make them ideal for practical applications. The direct integration of Bi-doped In₂O₃ nanofibers onto micro light-emitting diode (μLED) platforms enables high-performance sensors for simultaneous NO₂ and H₂O detection. Introducing Bi into In₂O₃ matrices facilitates the formation of oxygen vacancies and the dissociative adsorption of H₂O, enhancing the adsorption and reactions with NO₂. Under blue illumination, this μLED sensor system exhibits high NO₂ sensitivity, with a response value (<i>R</i>_g/<i>R</i>_a) of 264.9 at 1 ppm and 60% relative humidity and response and recovery times of less than 30 s. The use of μLEDs enhances light activation with a high energy transfer efficiency, resulting in outstanding NO₂ sensing characteristics. A convolutional neural network-based algorithm is employed to analyze transient sensing signals, accurately predicting with 99% classification accuracy and 10% regression error for both NO₂ and H₂O, thereby demonstrating weather-independent sensing. This integration of Bi-doped In₂O₃ nanofibers, which are specifically activated by blue illumination, μLEDs, and deep learning analytics, enables highly effective real-time environmental monitoring of NO₂ and humidity under environmentally variable outdoor conditions.