Daniel Echeveste gains new skills in machine learning
Daniel Echeveste was still a plebe — a first-year cadet at West Point — when he understood that he wanted to go into a STEM field.
He was a good student, particularly in mathematics, but wasn’t sure which direction he wanted his career to go. Then, on a short tour of Los Alamos National Laboratory, he crystalized the notion that research and engineering could have concrete, life-altering effects on real people.
“It was my first time visiting a lab and it really opened my eyes to what was possible,” Echeveste says. Soon, he was enrolled in a summer research program at Stanford School of Engineering known as SURF — Stanford Undergraduate Research Fellowship.
At Stanford, Echeveste got to work in the lab of mechanical engineering professor Wendy Gu studying the fine mechanical behavior of nanoscale ceramics, metals and composite materials — materials so small they are hard to describe, but whose impact is large and only just beginning to emerge. Nanomaterials are lightweight, durable and strong and have applications ranging from sophisticated sensors that detect poisons in the water and air to new-age protective materials.
In particular, Echeveste gained his first experiences with artificial intelligence, writing machine learning algorithms to evaluate electron microscope images to determine how effectively these materials “self-assembled” — that is, spontaneously organized themselves depending on the characteristics of a fundamental structural unit called a nanoscale cone. Materials with cones of differing characteristics have different propensities to self-assemble, a quality that engineers describe as “tunability.” Understanding how to tune nanoscale cones is the key to being able to create real-world materials with useful properties.
Echeveste, who is from Tucson, Arizona, returned to West Point after his summer at Stanford as a senior with his eyes set on graduate school. He intends to leverage his new-found mathematical skills to explore other nanomaterials or — intriguingly — to analyze the complex behavior of swarming insects, among the many surprising and exciting opportunities in the ever-evolving world of engineering.
“SURF gave me the confidence to apply to grad school,” Echeveste says. “Machine learning seems to pops up everywhere in applied mathematics.”