Research Article: Mobile road weather sensor calibration by sensor fusion and linear mixed models

Date Published: February 7, 2019

Publisher: Public Library of Science

Author(s): Lauri Lovén, Virve Karsisto, Heikki Järvinen, Mikko J. Sillanpää, Teemu Leppänen, Ella Peltonen, Susanna Pirttikangas, Jukka Riekki, Jie Zhang.


Mobile, vehicle-installed road weather sensors are becoming ubiquitous. While mobile sensors are often capable of making observations on a high frequency, their reliability and accuracy may vary. Large-scale road weather observation and forecasting are still mostly based on stationary road weather stations (RWS). Though expensive, sparsely located and making observations on a relatively low frequency, RWS’ reliability and accuracy are well-known and accommodated for in the road weather forecasting models. Statistical analysis revealed that road weather conditions indeed have a great effect on how the observations of mobile and stationary road weather temperature sensors differ from each other. Consequently, we calibrated the observations of mobile sensors with a linear mixed model. The mixed model was fitted fusing ca. 20 000 pairs of mobile and RWS observations of the same location at the same time, following a rendezvous model of sensor calibration. The calibration nearly halved the MSE between the observations of the mobile and the RWS sensor types. Computationally very light, the calibration can be embedded directly in the sensors.

Partial Text

Mobile, vehicle-installed sensors and road weather station (RWS) networks can together provide denser and higher quality information than either alone. They can support optimization of maintenance operations, such as snow clearance and prevention of slipperiness, and generation of real-time warnings for road users. Accurate now-casting and forecasting are keys to safe and economic operations, especially in the northern latitudes where driving conditions can vary a lot in space and time, increasing risk for accidents.

Mobile, vehicle-installed sensors and RWS networks can together provide denser and higher quality information of challenging driving conditions than either alone. First, this study analyzed the observations of mobile (Teconer RCM411, RTS411) and RWS (Vaisala DRS511, DST111, DSC111) road weather sensors and identified conditions and factors that affect how their measurements differ from each other. Second, this study presented a novel calibration method for the mobile sensors. A straightforward linear Eq (5) adjusted the mobile road surface temperature observations to be consistent with the stationary ones, halving the MSE between the mobile and the RWS observations.




Leave a Reply

Your email address will not be published.