Engineering topics
Cohn, Nicholas
Publications and source records attributed to Cohn, Nicholas.
The Impact of Inherited Morphology on Sandbar Migration During Mild Wave Seasons
Sandbars are ubiquitous morphologic features found in the nearshore environment throughout the world, yet predictive capabilities of their evolution remain limited. In order to provide new insights on the relevant processes controlling sandbar morphodynamics, this study uses a 41-year record of 637 monthly cross-shore profiles from Duck, North Carolina, USA, to derive complex empirical orthogonal functions representative of the two dominant modes of sandbar migrations: offshore and onshore propagation. Interference of these two modes produces commonly observed sandbar states. While mild wave energies are traditionally assumed to drive onshore sandbar migration, the offshore mode is repeatedly seen to dominate sandbar migration in mild wave seasons following anomalously high late-winter wave energy and when the inherited morphology is composed of a single bar or terrace, as opposed to a more common two-bar state. A data-derived conceptual model is presented synthesizing the effect of antecedent morphology and wave climate chronology on interannual trends in net offshore sandbar migration.
Network-Scale Ubiquitous Volume Estimation Using Tree-Based Ensemble Learning Methods
Currently ubiquitous volume data for roadway networks remains the key missing dimension in traffic operations. Most volume data are average annual daily traffic (AADT) measures derived from the Highway Performance Monitoring System (HPMS). Although methods to factor the AADT to hourly averages for typical day of week exist, actual volume data is limited to a sparse collection of locations in which volumes are continuously recorded. This paper/poster explores the use of state-of-art machine learning techniques to estimate accurate volume measures that span the highway network providing ubiquitous coverage in space, and point-in-time measures for a specific date and time. Three tree-based ensemble learning models, random forest (RF), gradient boost machine (GBM), and extreme gradient boost (XGBoost), were tested for volume estimation by learning from combined dataset of commercial probe data provided by TomTom, the FHWA's Travel Monitoring Analysis System (TMAS) data, and other infrastructure attributes such as number of lanes, speed limit, and weather. The methods were tested on major corridors and freeways in the metropolitan area of Denver. All three machine learning methods were able to provide hourly volume estimates 24 hours a day, 7 days a week, and 365 days a year with around 18% mean absolute error to true volume and about 5% of error with respect to roadway capacity. The low error measures allow the potential application by transportation agencies.