Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

In the last few years, the interest in the development of new pervasive or mobile implementations of air quality multisensor devices has significantly grown. New application opportunities appeared together with new challenges due to limitations in dealing with rapid pollutants concentrations transients both for static and mobile deployments. In this work, we propose a Dynamic Neural Network (DNN) approach to the stochastic prediction of air pollutants concentrations by means of chemical multisensor devices. DNN architectures have been devised and tested in order to tackle the cross sensitivities issues and sensors inherent dynamic limitations. Testing have been performed using an on-field recorded dataset from a pervasive deployment in Cambridge (UK), encompassing several weeks. The results obtained with the dynamic model are compared with the response of the static neural network and the performance analysis indicates the capability of the on-field dynamic multivariate calibration to ameliorate the static calibration approach performance in this real world air quality monitoring scenario. Interestingly, results analysis also suggests that the improvements are more significant when pollutants concentration changes more rapidly.