In 2022, Randall Pietersen, US Air Force civil engineer, participated in a training mission to assess the damage on an aerodrome track, practicing the “basic recovery” protocol after a simulated attack. For hours, his team crossed the zone in chemical protection equipment, by geoco-firing radiovization while they were documenting damage and sought threats like unploded ammunition.
The work is standard for all Air Force engineers before their deployment, but it has had a particular meaning for Pietersen, who has spent the last five years developing faster and safer approaches to assess aerodromes as a master's degree and now a doctoral and mathematics candidate. For Pietersen, time work, meticulous and potentially dangerous highlighted the potential of his research to allow remote assessments of the aerodrome.
“This experience was really revealing,” says Pietersen. “We have been told for almost a decade that a new system based on drones is in preparation, but it is always limited by an inability to identify unplodced ammunition; Air, they look too much like rocks or debris.
Pietersen’s objective is to create automated systems based on drones to assess aerodrome damage and detect unploded ammunition. This reduced it a certain number of research paths, from deep learning to small air systems not linked to “hyperspectral” imaging, which captures passive electromagnetic radiation through a wide spectrum of wavelengths. Hyperspectral imaging becomes cheaper, faster and more sustainable, which could make Pietersen research increasingly useful in a range of applications, including agriculture, emergency interventions, mining and buildings assessments.
Find IT and community
Having grown up in a suburb of Sacramento, California, Pietersen gravity towards mathematics and physics at school. But he was also a cross-country athlete and an Eagle Scout, and he wanted a way to bring his interests together.
“I liked the multifaceted challenge that the Air Force Academy presented,” explains Pietersen. “My family has no history of service, but recruiters spoke of holistic education, where academics were a part, but it was the same in physical form and leadership. This well -balanced approach to university experience called me. ”
Pietersen specializes in civil engineering as the first cycle at the Air Force Academy, where he began to learn to conduct university research. This forced him to learn a little computer programming.
“During my last year, Air Force research laboratories had projects related to the roadway which fell into my scope as a civil engineer,” recalls Pietersen. “Although my domain knowledge helped define the initial problems, it was very clear that the development of good solutions would require a deeper understanding of computer vision and remote sensing.”
The projects, which treated evaluations of the aerodrome and threat detection, also led Pietersen to start using hyperspectral imagery and automatic learning, on which he built when he came to pursue his mastery and doctorate in 2020.
“MIT was a clear choice for my research because the school has such a strong history of multidisciplinary research and thinking partnerships that helps you solve these unconventional problems,” explains Pietersen. “There is no better place in the world than put it for advanced work like this.”
As Pietersen arrived at the MIT, he also kissed extreme sports such as ultra-marathons, parachuting and climbing. Some of them come from his participation in infantry competitions as the first cycle. Several days competitions are races focused on the military in which teams around the world cross the mountains and carry out classified activities such as tactical care of combat victims, orientation and shooting.
“The crowd with which I ran to the university was really in this kind of thing, so it was somehow a natural consequence of the establishment of relationships,” explains Pietersen. “These events cover you for 48 or 72 hours, sometimes with a little sleep, and you can compete with your friends and have a good time.”
Since his arrival with his wife and two children, Pietersen has adopted the local race community and even worked as an instructor of indoor parachuting in New Hampshire, although he admits that the winters of the East Coast have been difficult for him and his family.
Pietersen moved from 2022 to 2025, but he did not research the comfort of a home office. The training that showed him the reality of the aerodrome assessments took place in Florida, then it was deployed in Saudi Arabia. He wrote one of his publications as a doctoral journal of a tent in the desert.
Now back to the MIT and approach to the completion of his doctorate this spring, Pietersen is grateful for all the people who supported him throughout his trip.
“It was fun to explore all kinds of different engineering disciplines, trying to understand things with the help of all MIT mentors and the resources available to work on these really niche problems,” explains Pietersen.
Research with a goal
During the summer of 2020, Pietersen did an internship with the Halo Trust, a humanitarian organization working to free up terrestrial mines and other explosives from the areas affected by the war. Experience has demonstrated another powerful application for his work.
“We have post-conflict regions in the world where children are trying to play and there are terrestrial mines and unploded ammunition in their backyards,” explains Pietersen. “Ukraine is a good example in the news today. There are always leftovers. At the moment, people have to go to these potentially dangerous areas and erase them, but new remote control detection techniques could speed up this process and make much safer. ”
Although the work of the master of Pietersen spoke mainly around the evaluation of the normal wear of the road structures, its doctorate focused on the means of detecting unploded ammunition and more serious damage.
“If the track is attacked, there would be bombs and craters everywhere,” explains Pietersen. “This allows an environment difficult to assess. Different types of sensors extract different types of information and each has its advantages and disadvantages. There is still a lot of work to do both on the hardware side and software, but so far, hyperspectral data seem to be a promising discriminator for deep object detectors. ”
After obtaining the diploma, Pietersen will be stationed in Guam, where Air Force engineers regularly carry out the same evaluation simulations of the aerodrome which he participated in Florida. He soon hopes that these evaluations will not be carried out by humans in protective equipment, but by drones.
“Right now, we are counting on visible site lines,” explains Pietersen. “If we can move on to spectral imaging and in -depth learning solutions, we can finally perform remote assessments that make everyone safer.”
