RUSTON, La. — National Science Foundation awarded Louisiana Tech University assistant professor Abdur Rahman a two-year, $185,000 grant to develop artificial intelligence systems designed to detect problems in critical infrastructure, including power grids, water networks, manufacturing facilities and transportation systems.
The project, titled “ERI: Flexible, Adaptive, and Explainable Anomaly Detection under Distribution Shift in Multivariate Time Series,” will focus on creating AI models that can adapt to changing real-world conditions while providing explanations for how they make decisions in complex sensor-based environments.
Rahman, who recently completed his first year as an assistant professor in Louisiana Tech’s College of Engineering and Science Industrial Engineering program, said the research addresses a longstanding challenge in AI systems known as “distribution shift,” where models trained under one set of conditions lose accuracy as environments evolve.
“AI models often perform very well in controlled environments, but real-world systems constantly change,” Rahman said. “Equipment ages, operating conditions shift, and environmental factors vary. Our goal is to develop AI systems that can adapt to those changes while remaining reliable and transparent for the people who depend on them.”
Anomaly detection systems are used to identify unusual patterns that may indicate equipment failures, operational problems, cyberattacks or safety risks. Early detection can help organizations reduce downtime, lower safety risks and prevent larger system failures.
Rahman said explainability is a central component of the project because operators need to understand why AI systems trigger alerts.
“Explainability is essential when AI is being used in systems people rely on every day,” Rahman said. “Operators need to understand not only that an alert was triggered but also why it was triggered, so they can make informed decisions quickly and confidently.”
Collin Wick, dean of the College of Engineering and Science, said the project supports both infrastructure resilience and workforce development.
“Dr. Rahman’s research addresses challenges that directly affect the safety, reliability, and resilience of critical infrastructure while creating meaningful opportunities for student involvement and workforce development,” Wick said.
The funding will support graduate and undergraduate researchers at Louisiana Tech, providing hands-on experience in machine learning, reinforcement learning, explainable AI, industrial analytics and time-series analysis. Students involved in the project will contribute to software development, publications and applied research initiatives.
Wick said the grant marks the second research award received this month by a first-year faculty member in the college, reflecting broader efforts to expand Louisiana Tech’s research operations and recruit faculty focused on applied research.
The project also aligns with the university’s investment in AI infrastructure, including a new AI laboratory under construction in Nethken Hall. The lab is expected to open in fall 2026 and will provide students and faculty access to 15 NVIDIA Spark workstations for research, instruction and collaboration.