Issue link: http://uwashington.uberflip.com/i/1047596
16 Pacifi c Northwest Transportation Consortium An Airborne Lidar Scanning and Deep Learning System for Real-Time Event Extraction Control Policies in Urban Transportation Networks • PI: Christopher Parrish (OSU) • Co-Investigators: Sameh Sorour (UI), Ahmed Abdel-Rahim (UI), David Hurwitz (OSU) The project team is currently investigating the capability to provide transportation and mobility solutions driven by real-time data generated from UAS using lidar and event identifi cation through deep learning. Specifi c project tasks include: 1) developing optimal UAS-based lidar acquisition methodologies (payloads, sensor settings, and processing strategies) for transportation network scanning; 2) designing, implementing, and testing a deep learning algorithm that can extract features from the UAS lidar data, and 3) developing guidelines for state DOTs and other transportation agencies on the technical and operational requirements for UAS-based lidar data integration. The OSU project team recently integrated a Velodyne Puck lidar system and OxTS xNAV direct georeferencing system on a DJI S1000 remote aircraft and have conducted test fl ights under an FAA-issued Certifi cate of Authorization (COA). Next steps will include working with ODOT to identify project sites to scan with the UAS-based lidar and transmitting the data to the UI project partners for implementing and testing the deep learning algorithms. Measuring the Impact of Landslide on Transportation Infrastructure to Improve Mobility and Safety • PI: Margaret Darrow (UAF) The collision of FDL-A with the abandoned Dalton Highway embankment represents a unique opportunity; it is not often that engineers can observe a landslide impacting a roadway in a safe and controlled way and on a predictable schedule. This work will be done in multiple phases to accommodate ADOT&PF's construction schedule. Future phases will include: 1) measuring deformation of the embankment and subsurface; 2) measuring earth pressure during the collision of FDL-A with the embankment; and 3) documenting and visualizing the collision through repeat LiDAR scans and repeat photography. For this fi rst phase, we will install sensors to measure pore water pressure and temperature changes in the subsurface as FDL-A approaches and covers the instrumentation locations. Additionally, we will use a back-pack mounted LiDAR system to measure surface deformation of the FDL and estimate volume change. Through all phases of this research, we will learn more about the earth pressure a landslide imparts to an engineered structure, how the landslide deforms the embankment, and how FDLs modify the permafrost ahead of them. These results can be used to develop successful mitigation strategies for the FDLs, which will improve longterm mobility and safety along this stretch of the Dalton Highway. Additionally, the results can be incorporated into or used to check existing models for earth pressure on retaining walls or piles. Measuring Dispersal and Tracking of Anti Icing and Deicing Chemicals using In Situ Hyperspectral Data • PI: Nathan Belz (UAF) The use and application of salt, sand and related mixtures, and derivatives have proven to be highly effective for controlling or removing the development of ice on the roadway surface. Ample research exists indicating the way in which application method, application rate and effi cacy of mix contents can vary depending on temperature and surface conditions. There is also substantial research on the environmental impacts of anti-icing and deicing applications on factors such as soil and groundwater as well as the corrosive properties of different types of chlorides. However, there is little if any research to suggest the longevity and dispersal of anti-