Prediction of the SnO2-based sensor response for hydrogen detection by artificial intelligence techniques.

SnO 2 -based nanocomposites are reliable sensors to detect hydrogen leakage and satisfy safety protocols. Although the hydrogen detection response (HDR) of these sensors has been deeply studied in the laboratory, there are no models to estimate this parameter. Consequently, this study uses three machine learning classes (i.e., gene expression programming, support vector regression, and artificial neural network) to calculate the HDR of pure and Ag-, Co-, Pd-, Pt-, and Ru-decorated SnO 2 nanostructures. These models only need nanocomposite chemistry and operating conditions to estimate the HDR of SnO 2 -based sensors. Comparing these models' performance by the ranking analysis and spider-graph indicates the multilayer perceptron neural network is superior to the other models. This model shows the highest accuracy (regression coefficient = 0.9882, average absolute deviation = 2.74, and root mean squared errors = 8.05) for estimating the HDR of SnO 2 -based sensors. This model also anticipates that Pd and Ru are the best and worst dopants to decorate the SnO 2 -based sensors. • A reliable approach is built to estimate H 2 detection ability of SnO 2 -based sensors. • This ANN-based model accurately estimate H 2 sensing ability of five nanostructures. • Palladium and Ruthenium are the best and worst metals to decorate SnO 2 sensors. • Dopant dosage and temperature have complex effects on H 2 sensing ability of sensors. • Statistical, trend, and leverage analyses approved reliability of the built model. [ABSTRACT FROM AUTHOR]