GRO Intern, Oak Ridge National Laboratory
Building graph neural network workflows for composites and polycrystals, including multitask elastic-plastic surrogates and uncertainty-aware fatigue prediction.
About me
I specialize in high-rate dynamics, failure of ceramics & metals, and resonant metamaterials under impact & blast. My expertise is in numerical PDE solvers and scalable HPC workflows. I develop robust graph neural networks for microstructure to property prediction with uncertainty quantification, achieving state-of-the-art accuracy. I am proficient with open-source scientific software and in-house code development.
- Graph neural networks for microstructure-to-property prediction in polycrystalline alloys and fiber composites.
- High-strain-rate dynamics and failure of heterogeneous materials, including metals, ceramics, and composites.
- Design and dynamic response analysis of locally resonant metamaterials under impact and blast loading.
- Uncertainty quantification in machine-learning surrogates for elastic-plastic response and fatigue indicators.
- Multiscale computational mechanics using finite-element, discontinuous Galerkin, and phase-field methods.
- Scalable high-performance computing workflows for large-scale materials simulations.
Graduate Research Assistant, University of Tennessee, Knoxville
Studying resonant metamaterials, high-strain-rate fracture, UMAT and UEL development, and HPC-enabled parametric simulation workflows for impact and blast problems.
Mechanical Engineer, ITUNOVA Technologies
Managed multiphysics CAE workflows for a high-performance turbopump spanning structural, thermal, fatigue, and dynamic analyses.
Intern, Baykar Technologies
Performed structural analysis for composite control surfaces and related aerospace structures.
Intern, Turkish Aerospace Industries - ITU Very Light Aircraft Project
Built global FEM models for composite aircraft structures and carried out sizing, buckling, and stability studies.
Student Organization Member, ITU Facilis Vehicle Team
Led structural analyses for a composite monocoque and related systems, contributed to CFD and manufacturing, and later served as team manager.
Ph.D., Mechanical Engineering, University of Tennessee, Knoxville
Minor in Interdisciplinary Graduate Minor in Computational Science, GPA 4.00/4.00. Thesis: Microstructure as a Graph: Surrogates for Elastic and Failure Responses.
Selected coursework includes Nonlinear FEM, Discontinuous Galerkin Methods, and Machine Learning for Materials.
M.Sc., Solid Mechanics, Istanbul Technical University
GPA 3.56/4.00. Thesis: Mechanical Properties of Boron Nanotubes.
B.Sc., Mechanical Engineering, Istanbul Technical University
Thesis: Design of Composite Monocoque Body for Lightweight Gasoline Vehicles.
- Caliskan, E., Cheney, W., Wang, W., Plaisted, T., Amirkhizi, A. V., and Abedi, R. (2026). Time domain analysis of locally resonant elastic metamaterials under impact. Mechanics of Advanced Materials and Structures, 33(1), 2619034. Link
- Caliskan, E., Abedi, R., and Lupo Pasini, M. (2025). Graph Neural Networks for Mechanical Property Prediction of 2D Fiber Composites. Materials & Design, 114500. Link
- Abedi, R., Furey, C., Pourkamali-Anaraki, F., Huynh, G., Caliskan, E., and Amirkhizi, A. V. (2025). Analyzing fragmentation response of heterogeneous ring using the method of characteristics and machine learning techniques. Computer Methods in Applied Mechanics and Engineering, 436, 117709. Link
- Caliskan, E. and Kirca, M. (2022). Tensile characteristics of boron nanotubes by using reactive molecular dynamics simulations. Computational Materials Science, 209, 111368. Link
- UTK Graduate Student Senate Travel Award: 2023, 2024, and 2025.
- Graduate School Fellowship: Summer 2023.
- 2nd place, 5-Minute Thesis Competition, BASARIM 2022 - 7th High-Performance Computing Conference. Presentation
- Reviewer: Mechanics of Materials.
- HPC resource scholar: UHeM and TRUBA, 2020 - 2022.
Presented 8 times and contributed to 20+ abstracts across SES, IMECE, WCCM, USNCCM, EMI, and related venues. (★) presenter. View all conference entries.
- Erdem Caliskan★, Anik Das Anto, Reza Abedi, and Massimiliano Lupo Pasini. Probabilistic multi-task graph neural network surrogates for elastic-plastic behavior and fatigue indicator prediction in polycrystalline alloys. In SES Conference 2025, Atlanta, Georgia, USA, October 12-15, 2025.
- Erdem Caliskan★, Willoughby Cheney, Weidi Wang, Alireza Amirkhizi, and Reza Abedi. Design and Dynamic Response Analysis of Resonant Microstructured Media. In International Mechanical Engineering Congress and Exposition 2024 (IMECE2024), Portland, Oregon, November 17-21, 2024.
- Erdem Caliskan★, Weidi Wang, Willoughby Cheney, Alireza V. Amirkhizi, and Reza Abedi. Transient nonlinear response of resonant metamaterial arrays under impact loading. In 16th World Congress on Computational Mechanics and 4th Pan American Congress on Computational Mechanics (WCCM / PANACM 2024), Vancouver, British Columbia, Canada, July 21-26, 2024.
- Erdem Caliskan★, Willoughby Cheney, Weidi Wang, Ali Heidari Shirazi, Reza Abedi, and Alireza V. Amirkhizi. Linear time domain analysis of resonant microstructured media and higher order scattering modes. In 17th U.S. National Congress on Computational Mechanics (USNCCM23), Albuquerque, New Mexico, USA, July 23-27, 2023.
- Erdem Caliskan★, Willoughby Cheney, Weidi Wang, Reza Abedi, and Alireza V. Amirkhizi. Time domain analysis of resonant microstructured media under impact loading. In Engineering Mechanics Institute Conference 2023 (EMI 2023), Atlanta, Georgia, USA, June 6-9, 2023.
- Erdem Caliskan★ and Mesut Kirca. Mechanical Properties of Boron Nanotubes In 5 Minute Thesis Competition at 7th High-Performance Computing Conference (BASARIM 2022), Istanbul, Turkiye and Online May 11-13 2022.
- Erdem Caliskan★ and Mesut Kirca. Mechanical Properties of Boron Nanotubes with Triangular Lattice. In 6th International Erciyes Conference on Scientific Research (ERCIYES 2022), online, September 1-2, 2021.
- Tau Beta Pi - The Engineering Honor Society.
- U.S. Association of Computational Mechanics.
- American Society of Mechanical Engineers.
If you would like to discuss research, collaboration, or opportunities in computational mechanics, scientific machine learning, or high-performance computing, email is the fastest way to reach me.