Teen Develops Flood-Detecting CubeSat – IEEE Spectrum

Currently satellites, synthetic aperture radarAnd GPS are used to collect data on flood damage, track the location of victims and communicate with emergency services. But technological failures and slow data transfer According to Merchant, high speed leads to delays in response time. The increase in global floods has increased the need for more accurate and reliable methods.

Last year, Merchant created what she says is a more efficient way to track and collect data during floods: small, inexpensive, standardized CubeSat integrated with artificial intelligence. small satellites use blocks measuring 10x10x10 cm.— which allows manufacturers to develop their batteries, solar panelscomputers and other parts as finished components.

CubeSat takes pictures of the area and uses pattern recognition to detect flooding, assess infrastructure damage and track survivors.

Merchant presented her paper on the device at this year's IEEE. Region 3 annual conference, IEEE SoutheastCon.

“IEEE is a fundamental part of my growth as a young researcher,” she says. “It turned engineering from a dream into a reality.”

Creation of CubeSat WITH

The merchant talks about his interest in disaster response arose after it became known that it could take rescuers several hours to obtain satellite data.

Determined to find a faster method, she began researching technology and discovered that CubeSats I can do it.

“CubeSats are very flexible, scalable, and capable of forming constellations (groups of multiple satellites) that update data in near real time,” she says. “The idea that these small satellites that fit in the palm of your hand could provide life-saving data faster than traditional systems really inspired me to take this concept further.”

Last year, Merchant and three of her classmates were accepted into WITH's Beaver Works Creates CubeSat Challengewhere teams of five American schoolchildren were given eight months to develop a satellite capable of carrying out a space exploration mission.

Merchant team – Satellite Guardians— built a CubeSat based on a convolutional neural network (CNN), which can identify areas heavily affected by flooding and remotely collect data to disaster relief And environmental monitoring. CNNs analyze image data for pattern recognition.

Merchant was the team's payload programmer and led mission design and simulation, which included planning, hardware configuration, and autonomous software development and algorithms to control the payload.

The team began by creating a 3D model of the device to visualize and refine the placement of its parts. Technology used, including Raspberry Piseveral sensors and a camera – housed in a transparent plastic cube.

The medium CubeSat was developed by Merchant and her team during the MIT Beaver Works Build a CubeSat Challenge. On the left is a commercial 1U CubeSat, and on the right is a prototype of Merchant's current design. Abigail Merchant

The device, which cost $310 to manufacture, weighs about 495 grams and was connected remotely to a laptop via Bluetooth during ground tests. The computer contains machine learning algorithm written by the Seller using Python— which analyzes collected images to detect flooding.

The CubeSat takes a high-resolution image of its surroundings every 2 minutes and transmits it to a laptop. The satellite transmits up to 1,500 images daily and stores them on a 16 GB SD card.

The algorithm then analyzes patterns, including changes in water color and image pixel density. When the algorithm detects flooding, the device can alert emergency services.

“While many existing systems operate in multi-hour cycles, CubeSats capture high-resolution images every 2 minutes,” Merchant says. “The system can then trigger alerts that are delivered to first responders via SMS or by email.”

To test their system, Merchant and her team built a model city from Lego blocks in an empty bathtub. They placed a CubeSat above him and he took pictures of the scene. Then they added water and mud to make it look more like a real flood. The CubeSat successfully transmitted images to the laptop and the algorithm detected the flooding.

Out of 30 teams, Satellite Sentinels finished third.

Continuing his work in Accenture

Merchant continues his research into flood prevention technologies in Accenture in Richmond, Virginia, where she works remotely as a payload owner and designer on the company's CubeSat launch team.

After completing the MIT program, Merchant decided to scale her project. She turned to her former mentor Chris Hudsonworld technical leader in space cybersecurity in Accenture. He offered her an internship.

Merchant is working to move from a prototype to a functional product, but she says she needs to overcome the hurdles she faced in her MIT project.

The main one was that the model had difficulty detecting flooding under variable conditions. This is because the CNN model needs context, she said. Without this, the model may misinterpret complex visual signals. To solve this problem, Merchant trained an algorithm to detect flooding by detecting colors in individual pixels.

Transferring images using Bluetooth worked in her bathroom, but that's not so useful when CubeSats orbit 700 kilometers above the earth.

“If you've used a Bluetooth headset before, you know that it turns off the moment you walk away from the device it's connected to,” she says. “It won't work when the CubeSat constellation is in orbit.”

She suggested that the Accenture team migrate to SubMiniature Version A (SMA). antennas. RF antennas are connected to the CubeSat using SMA connector.

“The development process was one of the most important experiences of my career,” says Merchant. “Working on the design and validation of the payload and meeting with these teams was a great experience for me, especially for my age.”

Its payload is expected to launch early next year.

Aerospace internship at MIT.

Merchant is an intern at MIT. Laboratory of Computer Science and Artificial Intelligencethe school's largest interdisciplinary laboratory, with 60 research groups. CSAIL headed by IEEE member Daniel Rus2025 Prize Winner IEEE Edison Medal.

The internship is remote, and Merchant conducts research in the laboratory at University of Central Floridain Orlando.

“IEEE is a fundamental part of my growth as a young researcher. It has transformed engineering from a dream to a reality.”

In this role, Merchant focuses on cognitive cartographya method of structuring complex information into semantic maps that show how ideas and concepts relate to each other. She uses embedding modelsa type of machine learning that converts information into numerical representations. Embeddings allow computers to recognize similarities and relationships between concepts, even if they are described differently. This approach helps the AI ​​product understand how ideas are connected, rather than treating each piece of data as isolated.

“Being one of the youngest people in the lab is challenging,” Merchant says. “However, I am excited to learn from the engineers and researchers who are working at the forefront of this field.”

She says she hopes to go to MIT or Stanford.

The Future of IEEE

Merchant met IEEE Joe Jusayformer financial director IEEE Orlando Section.

Her first personal experience with the organization occurred in 2023 while she was conducting research for a science fair project. She was working on robotic arm who could pick up objects using electroencephalogram and Bluetooth. The project was inspired by her grandmother, who suffers from mobility issues and is wheelchair-bound.

“I kept seeing IEEE mentioned in every regulation and standard I found,” Merchant says. When she learned about the upcoming section meeting in Orlando, she asked her mother to take her with her.

At the meeting, several participants presented their research. The merchant asked Masood Ejaz And Varadraj Gurupur— to the chapter chair and co-chair — if she could discuss her science fair project.

“After presenting my work, IEEE quickly became a community that shaped my understanding of what engineering was capable of,” she says.

She said she felt on top of the world when she presented her CubeSat project at IEEE South EastCon.

“It's one of those experiences that really changes you,” she says.

She said she is excited to become a student member of IEEE when she gets to college. She also hopes to one day be elected its president.

“I met Kathleen Kramer at one of my local IEEE events before she was elected IEEE Presidentand we talked about my work,” she says. “After she was elected, I realized that I would like to someday become president of IEEE.

“I hope that one day I can be in the same situation as her and continue to help IEEE the same way he helped me.”