Thursday, September 4, 2025  |  9:00 - 10:00 AM ET

Join us for a technical webinar exploring how synthetic thermal infrared imagery can dramatically improve deep learning performance for detecting and recognizing unmanned aerial vehicles (UAVs). In the thermal IR wavebands (MWIR and LWIR), acquiring large, high-quality datasets—especially of adversarial targets—can be difficult. This session will highlight how physics-based simulation tools like MuSES and CoTherm are used to generate realistic, diverse datasets of commercial and military UAVs under varying weather conditions, times of day, and sensor perspectives.

We’ll discuss the automated generation of these synthetic datasets and demonstrate their impact on training a YOLO (“You Only Look Once”) deep learning model. Performance will be analyzed across real and synthetic imagery, examining how variables like background conditions and resolution affect detection and recognition accuracy.

What You’ll Learn:

• Challenges of training deep learning models in thermal IR
• How to simulate realistic UAV thermal signatures with MuSES
• Automation of dataset generation and image processing with CoTherm
• Comparative performance of YOLO on real vs. synthetic IR imagery

Who Should Attend:
Engineers, data scientists, researchers, and defense technologists working with thermal imaging, machine learning, or UAV detection.

Don't miss this opportunity to see how simulation and AI combine to solve real-world sensing challenges.

Logan Canull

Thermal/CFD Engineer

Logan Canull is a Thermal/CFD Engineer at ThermoAnalytics, Inc. His primary focus is on supporting the research and expansion of features in TAITherm, MuSES, and CoTherm, including the simulation of thermal runaway propagation, laser heating, and satellites. He joined ThermoAnalytics in 2022 and completed his M.S. in Mechanical Engineering in 2023.

J. Weston Early

Thermal/CFD Engineer

J. Weston Early is a Thermal/CFD Engineer at ThermoAnalytics, Inc., where he applies his background in simulation, heat transfer, computer vision, and algorithm design to support research and modeling efforts. With dual bachelor’s degrees in Mechanical Engineering / Engineering Mechanics and Computer Engineering from Michigan Technological University, Weston brings a multidisciplinary perspective to thermal analysis, image processing, and data-driven simulation. His skill set spans software development, statistical analysis,  3D modeling, and closed loop control systems, making him well-suited to support work involving synthetic data generation and AI-driven thermal modeling.