TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Christian Gaarde Nielsen, - PowerPoint PPT Presentation

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Christian Gaarde Nielsen, Stanislav Borysov, Mads Gaml, Tina Hjøllund, Vignesh Krishnamoorthy 1

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Background • Provide more knowledge about air pollution • Improve quality of life (clean air) while securing traffic accessibility 2

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Purpose • Overall: Understand connections between congestion and air pollution with an ability to control traffic • Pilot experiment: Understand local air pollution in intersections 3

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Design • Data gathered from: • Dec 2017 - Mar 2018 • Two intersections in CPH • Data sources: • Traffic signal regimes • INRIX traffic data sets • Micro radar • Air quality sensors • Weather data (Wunderground) 4

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Explaining the data Power supply issues: Reduced battery capacity due to low temperatures • Particle (PM 1, 2.5, 10) measurements: Optical sensors are affected by weather conditions • Precipitation (m/h) 3 100 No missing values % of non-missing observations 0 16 Visibility (km) 0 400 PM 1 (c) All values are missing 0 0 2018-02-19 … 2018-04-16 Time of day 5

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Explaining the data • Data aggregated by time of day 120 120 NO2, weekday NO2, weekend 0 0 500 500 CO, weekday CO, weekend 0 0 Time of day Time of day 6

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Explaining the data • Plain correlation between traffic and air pollution NO2, Micro-radar counts NO2, INRIX travel time CO, Micro-radar counts CO, INRIX travel time corr (raw) = 0.05 corr (raw) = 0.05 corr (raw) = 0.33 corr (raw) = 0.36 corr (MA10) = 0.12 corr (MA10) = 0.14 corr (MA10) = 0.47 corr (MA10) = 0.50 corr (LK clean) = 0.58 corr (LK clean) = 0.61 corr (LK clean) = 0.28 corr (LK clean) = 0.40 • Machine learning modeling Predicting NO2 Predicting CO 7

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Explaining the data Increase for yellow lights for one intersection – NO2 • 100 Signal regime, Sensor 1 Sensor 2 NO2, sensor 1 NO2, sensor 2 Signal direction [% increase] [% increase] Standard Standard 80 Mean Mean Deviation Deviation Red/Yellow, Average 60 Vigerslev Allé both 9 8 7 55 directions Yellow, 40 4 80 1 -10 In direction of Lykkebovej Yellow, 4 28 5 32 In direction of parking lot 20 0 8

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Explaining the data Increase for yellow lights for one intersection – CO • 250 Signal regime, Sensor 1 Sensor 2 CO, sensor 1 CO, sensor 2 Signal direction [% increase] [% increase] 200 Standard Standard Mean Mean Deviation Deviation Red/Yellow, 150 Vigerslev Allé both 113 78 90 111 directions Yellow, Average 100 14 -22 4 -44 In direction of Lykkebovej Yellow, 41 28 45 41 In direction of parking lot 50 0 9

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Evaluation • Know the administrative processes • Advanced data processing is important • Get what you need 10

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Main points of conclusion • Plain correlation between air pollution and traffic counts were up to: • 61 % for NO2 • 50 % for CO • Reliable correlations achieved through real-life data gathering • Mean air pollution level reached during red/yellow and yellow: • 9 % for NO2 • 113 % for CO • Accelerating cars starting from standstill or “catching” yellow light 11

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Future experiments • Scaling the project • Use of traffic corridor • Collect data 24/7 • Identify traffic optimization • Find "triggers" for management scenarios • Lots of other factors • Other experiments: • System provided with data can trigger certain protocols • Data could be noise pollution, cloudbursts and city events 12

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Partner group • City of Copenhagen • Technical University of Denmark • University of Copenhagen • Leapcraft • Citelum • PTV Group and TNO 13

TRAFFIC-FLOW & AIR QUALITY EXPERIMENT Thank you for your attention! 14