This paper introduces PIRC, a lightweight physics-informed reservoir computing framework that embeds degradation priors into a closed-form ridge regression readout for battery state-of-health prediction, validated on the NASA PCoE dataset and chaotic benchmark systems.
Received the MECC 2026 DSCD & AACC Student Travel Award to present our paper on Lightweight Physics-Informed Reservoir Computing (PIRC) for Battery Health Prediction at MECC 2026 in Phoenix, Arizona.
Presented PIRC framework for accurate and energy-efficient State of Health (SOH) prediction of lithium-ion batteries using physics-informed reservoir computing at ACC 2026.
Presented our work on Energy-Efficient Solar Forecasting with a Neuromorphic–Bayesian State Estimation Approach at the Energy Consequences of Information (ECI) Workshop 2026, held in Santa Fe, NM, USA.
This paper introduces RCUKF, a framework combining Reservoir Computing and Unscented Kalman Filtering to achieve accurate state estimation in complex systems, validated on benchmark problems and real-time vehicle simulations.
Presented the RCUKF framework, integrating Reservoir Computing and Unscented Kalman Filter for accurate state estimation of nonlinear systems, at MECC 2025 in an invited session on sustainable transportation solutions.
Received the Student Grant Award at MECC 2025 for the paper ‘RCUKF: Data-Driven Modeling Meets Bayesian Estimation’, selected from over 120 global applicants for promising research in modeling, estimation, and control.