Low-cost gas sensors detect pollutants gas at part per billion level and may be installed in small devices to densify air quality monitoring networks and to analyze the spread of pollutants around an emissive source. However, these sensors suffer from several issues such as environmental factors impact and cross-interfering gases. For instance, ozone (O₃) electrochemical sensor senses nitrogen dioxide (NO₂) and O₃ simultaneously without discrimination. Alphasense proposes the use of pair of sensors, the first one is equipped with filter dedicated to measure NO₂. The second one is sensitive to both NO₂ and O₃. Thus, O₃ concentration can be obtained by subtracting the concentration of NO₂ from the sum of the two concentrations. This technic is not practical and requires calibrating each sensor individually leading to biased concentration estimation. In this paper we propose partial least square regression (PLS) to build a calibration model including both of sensors responses and temperature and humidity variations. The results obtained from data collected on field for two months show that PLS regression provides better gases concentrations estimation in terms of accuracy than calibrating each sensor individually.