Mohammad G. Abdo is Technical R&D Distinguished Staff Member at Idaho National Laboratory, where he develops, applies, and deploys data science and machine learning across a broad spectrum of applications, significantly advancing the lab's research capabilities. he is the technical lead and work package manager of the Plant reload optimization team under the Risk-Informed Systems Analysis (RISA) Pathway under the Light Water Reactor Sustainability (LWRS) which aims to achieve optimal fuel utilization, longer cycles, and better safty limits utilizing AI-based metaheuristic optimization.

With 25 years of experience in mechanical engineering and 10 years extensive experiance in aplying machine learning to nuclear applications, Mohammad Abdo possesses expertise in reduced order modeling, uncertainty quantification and characterization, sensitivity analysis, design optimization, sparse sensing, and digital twinning. His academic background includes a bachelor degree in mechanical engineering from Alexandria University, Egypt, and a PhD in nuclear engineering from North Carolina State University, Raleigh NC. He has held positions as a postdoctoral researcher , a modeling and simulation specialist, and a Technical R&D Distinguished Staff Member at Idaho National Laboratory.

Before joining INL, Mohammad Abdo came from Kansas State University in Manhattan KS, where he served during 2018-2019 as an instructor in the mechanical and nuclear engineering department. In 2017-2018 he conducted research as a postdoctoral research associate and participated in constructing a time-dependent surrogate model for the TRIGA II reactor, a first step to propagate uncertainties over 70 years of reactor operations. Prior to that, Dr. Abdo earned his Ph.D. form North Carolina State University and spent a year as a postdoctoral researcher. He has been recognized among the RAVEN development team with R&D100 award in 2023. His work includes
• Metamodeling for predicting effective properties of advanced materials (porous and additively manufactured materials). (PI)
• VVUQ and relevance of prototype models to full target models. (PI)
• Promoting sparse sensing and sparse learning in nuclear digital twins. (PI)
• A Causal Approach to Model Validation and Calibration (Co-PI)
• LWRS-RISA pathway: Fuel reload optimization using metaheuristic algorithms. (Technical Lead and work package manager)
• LWRS-RISE pathway: Power uprate for current fleet LWRS.
• IES: Multiresolution analysis for Integrated energy systems.
• FPOG: Capacity expansion optimization for Integrated Energy Systems.
• Modeling, scaling, and calibration of high density particle fluidization TH & CFD behaviours in conical sprouted beds.
• Lithology identification and well correlation: Deploying ML/AI in industrial Uranium Mining applications.
• State-aware anomaly detection to support state changes, sensor calibrations, and other process accepted changes.

Mohammad Abdo holds a Ph.D. in Nuclear Engineering from NCSU. He has 20 scientific publications and reports.

Machine learning, deep learning, reduced order modeling, uncertainty quantification, sensitivity analysis, Digital Twinning, I4.0, IIOT, time series analysis, time-delayed embeddings, Koopman theory, dynamic mode decomposition, sparsity promoting algorithms, optimal sensor placement for physics recovery, Metaheuristic optimization such as: simulated annealing and genetic algorithms.