Project: #309 Platooning for Improved Safety and Efficiency of Semi-trucks [PISES - III] Progress Report - Reporting Period Ending: March 31, 2021 Principal Investigator: Venkat Viswanathan Status: Active Start Date: July 1, 2020 End Date: June 30, 2021 Research Type: Applied Grant Type: Research Grant Program: FAST Act - Mobility National (2016 - 2022) Grant Cycle: 2020 Mobility21 UTC Progress Report (Last Updated: April 10, 2021, 11:21 a.m.) % Project Completed to Date: 25 % Grant Award Expended: 25 % Match Expended & Document: 25 USDOT Requirements Accomplishments In this reporting period we continued to develop our data-driven convolutional neural ODE models for forecasting fluid dynamics. The model is designed to be much faster than conventional simulations, while retaining the core features of the flow. We have seen significant promise in the results and will be extending the experiments to incorporate more complex flows. We have disseminated this research through the NeurIPS Machine Learning for Physical Sciences Workshop in the form of a paper and presentation. We will also be giving a talk on this work at the upcoming NVIDIA GTC 2021 conference in April. Impacts Through this project we have been able to gain a deeper understanding of how convolutional models affect the physics that drive turbulent flow. This is crucial to developing more complex data-driven techniques to model these difficult fluid dynamics problems. The speed-up from performing rapid predictions will be used to predict many different cases in a fraction of the time as conventional methods. Other We have developed a new framework for constructing convolution-based neural ODEs. Outcomes New Partners N/A Issues No significant issues or changes.