Kendal Merry

Graduate Student | PhD

Email:: kemerry@iu.edu

Bio

As a graduate research student at Indiana University’s CREATE program, Kendal Merry explores the interdisciplinary challenges of space and high-radiation environments, where systems must endure harsh, often imperceptible conditions. A key challenge in advancing this field is the ability to accurately replicate such environments through physical experimentation or simulation. Her research investigates the potential of Physics-Informed Machine Learning (PiML) and Physics-Informed Neural Networks (PiNNs) to develop predictive models that improve the resilience and performance of microelectronic devices, particularly microchips, in space and other high-radiation settings.

Drawing on her background in Intelligent Systems Engineering, Kendal integrates artificial intelligence and machine learning to enhance the accuracy and predictability of radiation facility models and to analyze variations in radiation effects. Her additional training in chemistry enables a deeper understanding of device behavior at the atomic and material levels, while advanced mathematical knowledge supports algorithm development and interpretation of physics-based models. Complementing her technical expertise, Kendal’s strong creative aptitude (shaped by a long-standing passion for visual arts) allows her to conceptualize complex systems and communicate intricate ideas through effective visual representations, a skill consistently recognized as one of her notable strengths by educators and mentors.

Research

Phsyics-Informed Neural Networks (PiNNs)

Leveraging her background in mathematics, machine learning, and semiconductor physics, Kendal is advancing her research with a focus on Physics-Informed Neural Networks (PiNNs):

Applies PiNNs, which integrate data-driven learning with governing physical laws, to model complex physical systems
Focuses on radiation effects on semiconductor devices, aiming to improve predictive modeling and interpretability
Develops usable outputs (including validated datasets, models, diagrams, and graphical analyses) to support radiation-aware device research

Physics-Informed Neural Network (PiNN) Diagram Model

Seimens Internship (Summer 2025)

During a summer internship with Siemens, Kendal received comprehensive training and badges in Siemens EDA software:

IC Design
Design Verification
PCB Design
Design-for-test (DFT) methodologies

This experience combined self-paced technical training with collaborative group projects and applied design challenges.

PCB Layout on Siemens Schematic Challenge

REU Internship (Summer 2024)

During the REU internship, Kendal was assigned a Technology Computer-Aided Design (TCAD) project focused on transistor modeling and simulation:

Independently learned and operated TCAD software in the absence of a standardized training pathway, while also supporting and teaching others to use the program
Self-studied fundamental device physics to effectively configure and interpret simulations
Performed physical testing simulations to calibrate Id-Vg curves and identify key doping parameters influencing device behavior