Embedded Files
Joshua R. Tempelman
Joshua R. Tempelman
I am currently a Director’s Postdoctoral Fellow at Los Alamos National Laboratory. My research sits at the intersection of nonlinear dynamics, wave propagation, and scientific machine learning, with the goal of developing wave- and vibration-based tools for diagnosing, monitoring, and designing complex mechanical and material systems.
My work is guided by a central question: How is information encoded, transported, transformed, and lost in wave-bearing mechanical systems, and how can that information be exploited for diagnostics, digital twins, and material design? To address this question, my research combines advanced dynamics, wave mechanics, sensing, and AI to develop next-generation tools for structural diagnostics, manufacturing qualification, and AI-assisted metamaterial design.
Starting in January 2027, I will join the George W. Woodruff School of Mechanical Engineering at the Georgia Institute of Technology as an Assistant Professor. I am recruiting Ph.D. students to begin in 2027. Interested students are encouraged to contact me directly by email with a CV and a brief description of their background and research interests.
What I do
What I do
News
News
February 2026 — Ultrasonic Weld Inspection Paper accepted to Computer Methods in Applied Mechanics (CMAME).
Our paper on using simulation, generative AI, and laser sensing for weld characterization has been accepted to Computer Methods in Applied Mechanics. This work advances ultrasonic wave modeling and ML-enabled inversion.
February 2026 — Spectral Scattering paper accepted to Journal of Sound and Vibration (JSV).
Our paper on spectral characterization of wave scattering at granular–elastic interfaces has been accepted to Journal of Sound and Vibration. This work advances reduced-order and spectral perspectives on nonlinear wave transport and interface dynamics.
January 2026 — Hyperspectral inverse modeling paper accepted to IEEE TGRS.
Our work on probabilistic emissivity retrieval using physics-guided variational inference has been accepted to IEEE Transactions on Geoscience and Remote Sensing (TGRS). The paper develops a generative, uncertainty-aware framework for hyperspectral inversion under model–measurement mismatch.
January 2026 — Invited Talk at AMS Joint Mathematics Meeting.
Presented “Conditional Generative Modeling for Hyperspectral Emissivity Retrieval” at the AMS Joint Mathematics Meeting, highlighting physics-informed generative modeling for data-limited inverse problems.
December 2025 — Presented at Acoustical Society Joint Meeting (Honolulu, HI).
Delivered a talk on ultrasonic weld inspection using low-order Lamb wave models and diffusion-based signal enhancement, integrating hierarchical modeling and ML-driven inversion.
August 2025 — Invited Talk at Sandia National Laboratories.
Presented “Generative Modeling for Data-Limited Inverse Problems in Acoustic and Spectral Imaging,” discussing physics-regularized AI for nondestructive evaluation and remote sensing.
May 2025 — Invited Seminar at University of Illinois Urbana-Champaign.
Presented “Scientific Machine Learning for Acoustic and Spectral Sensing,” covering reduced-order modeling, generative alignment, and uncertainty-aware inversion.
2024 — Awarded Director’s Postdoctoral Fellowship, Los Alamos National Laboratory.
Selected as a Director’s Postdoctoral Fellow at LANL, supporting research on interpretable AI for structural diagnostics, inverse modeling, and digital twin development.
2024 — Received Stanley I. Weiss Outstanding Thesis Award (UIUC).
Recognized for doctoral research on passive energy management in acoustic and nonlinear dynamical systems.
2022 — Los Alamos Distinguished Student Award.
Honored for contributions to multimodal sensing and machine learning for advanced manufacturing.
Page updated
Google Sites
Report abuse