This paper discusses the utilization of Commercial Microwave Links (CMLs) for opportunistic air temperature measurement. This opportunistic sensing method uses the existing dense infrastructure of microwave telecommunication devices without the additional cost of extending the meteorological network. This method provides extensive spatial coverage, especially in areas with low meteorological density. The research presented here investigates the factors influencing temperature of the devices, analyzes their correlation with reference meteorological station data, and evaluates the capability of a neural network model to accurately predict ambient temperature using this opportunistic sensing method.