A surrogate-assisted measurement correction method for accurate and low-cost monitoring of particulate matter pollutants

Air pollution involves multiple health and economic challenges. Its accurate low-cost monitoring is important for developing services dedicated to reduce the exposure of living beings pollution. Particulate matter (PM) measurement sensors belong key components that support operation these systems. In this work, a modular, mobile Internet Things sensor PM measurements has been proposed. Due limited accuracy detector, data are refined using two-stage procedure elimination non-physical signal spikes followed by non-linear correction responses multiplicative surrogate model. The layer derived from sparse non-uniform calibration data, i.e., combination station obtained in same location over specified (relatively short) interval. device method have both demonstrated based on during three campaigns. proposed scheme improves fidelity around two orders magnitude w.r.t. which post-processing not considered. Performance surrogate-assisted technique favorably compared against benchmark approaches literature.