The SMARTHEP project comprises 12 Early Stage Researchers (ESRs) from 10 countries who began their PhDs in October 2022, selected from 199 applicants representing 55 nationalities. Working across the four main Large Hadron Collider (LHC) experiments (ALICE, ATLAS, CMS, and LHCb), their focus is on real-time analysis systems known as "trigger systems." These systems perform first-pass analyses on massive data delivered by the LHC in milliseconds, selecting data for further analysis and ultimately contributing to fundamental particle measurements and new particle searches.
The project tackled a fundamental challenge of our data-rich age: how to make fast, intelligent decisions when faced with enormous streams of information. SMARTHEP's goal is to accelerate decision-making using machine learning and hybrid computing architectures, while ensuring high-quality data despite the constrained environment in which first-pass analysis is performed. Since these goals are common to industry and science, cross-talk between academia and industry is integral to the PhD projects. To reach these goals, SMARTHEP brought together universities, research institutions and industry partners, organising specialised schools covering machine learning, scientific writing, data visualisation and science communication. These were complemented by hands-on secondments at IBM, Verizon Connect and CERN, giving researchers direct experience of how cutting-edge techniques translate between academic research and commercial applications.
The researchers made substantial contributions to the trigger systems at CERN, which must filter 40 million particle collision events per second down to a manageable few thousand. Their work improved how these systems select interesting physics events in real time, directly enabling more efficient data collection. Several researchers developed novel machine learning algorithms—including graph neural networks and transformer models—that operate within extremely tight time constraints while maintaining high accuracy.
Beyond fundamental physics, ESRs developed bird's eye view perception systems for autonomous driving requiring no expensive sensor-based training data, created open-source tools for detecting financial fraud using realistic synthetic transaction data, and built traffic prediction models. These applications demonstrate how techniques from particle physics can address real-world challenges in transport safety and financial security.
The network produced over 20 open-access publications, including three major review papers on LHC triggers, machine learning for real-time analysis, and hybrid computing architectures, mostly in peer-reviewed journals and presented at major international conferences. Five researchers have completed their PhDs, with the remainder on track to finish by early 2027. Graduates have secured positions ranging from postdoctoral research to applied scientist roles in finance and technology, reflecting the programme's success in preparing versatile professionals for both academia and industry.
