Research Projects

The Large Hadron Collider (LHC) and future high-energy physics (HEP) experiments generate un- precedented volumes of data, necessitating advanced real-time data processing at the trigger level to identify rare physics events, such as those involving Higgs boson decays, dark matter candidates, or Beyond-Standard-Model (BSM) phenomena. Traditional trigger systems struggle to balance effi- ciency, latency, and computational constraints in this high-rate environment. This project proposes the development and optimization of Topological Neural Network (TNN) algorithms tailored for heterogeneous computing platforms, e.g. Central-Processing-Unit (CPU), Graphics-Processing- Unit (GPU), Field-Programmable-Gate-Array (FPGA), and Application-Specific-Integrated-Circuit (ASIC) to enhance trigger level decision making. By leveraging the geometric and topological properties of particle collision data, TNNs will improve the identification of rare physics signatures while meeting the stringent latency and resource requirements of trigger systems. The project aims to deliver scalable, robust, and energy-efficient algorithms, validated through simulations and hardware implementations, to support the LHC’s High-Luminosity phase (HL-LHC) and future HEP experiments