Abstract: Systems, methods, and other embodiments described relate to estimating a traffic pattern using learning models that process data from road sensors that are sparse. In one embodiment, a method includes forming multi-channel data from partial data and timing data about traffic on a road, the partial data acquired from road sensors. The method also includes generating an adjacency matrix from the partial data and geometry about the road. The method also includes training a graph model using temporal patterns for graph nodes from the multi-channel data and the adjacency matrix to complete the partial data and output a traffic pattern estimate.

Abstract: The systems and methods of the present disclosure provide accurate traffic volume estimates at intersections using data available from a subset of the total vehicles and can effectively resolve the issue with a low penetration rate of connected vehicles and can be used to optimize traffic lights at intersections. The systems and methods of the present disclosure use vehicle trajectory data to calculate arrival times at intersections and, from this data, use a statistical method to estimate the traffic volume. Traffic arriving at the intersection can be modeled by a distribution and then, using an algorithm, the likelihood of the observed data (limited approaching vehicles data) can be maximized. The parameters from the optimized model can be used to estimate the real traffic volume. The systems and methods of the present disclosure use a Gaussian Mixture Model (GMM) distribution to model incoming vehicles.