Enabling Weather-Independent Gas Detection through Deep Learning on Light-Activated Sensors.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41144602.
- Also identified by DOI 10.1021/acsnano.5c10308.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
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 In<sub>2</sub>O<sub>3</sub> nanofibers onto micro light-emitting diode (μLED) platforms enables high-performance sensors for simultaneous NO<sub>2</sub> and H<sub>2</sub>O detection. Introducing Bi into In<sub>2</sub>O<sub>3</sub> matrices facilitates the formation of oxygen vacancies and the dissociative adsorption of H<sub>2</sub>O, enhancing the adsorption and reactions with NO<sub>2</sub>. Under blue illumination, this μLED sensor system exhibits high NO<sub>2</sub> sensitivity, with a response value (<i>R</i><sub>g</sub>/<i>R</i><sub>a</sub>) 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 NO<sub>2</sub> 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 NO<sub>2</sub> and H<sub>2</sub>O, thereby demonstrating weather-independent sensing. This integration of Bi-doped In<sub>2</sub>O<sub>3</sub> nanofibers, which are specifically activated by blue illumination, μLEDs, and deep learning analytics, enables highly effective real-time environmental monitoring of NO<sub>2</sub> and humidity under environmentally variable outdoor conditions.