The Plastics Pollution In The Ocean: How a Low-Cost Machine Learning & Infrared Spectroscopy Equipped ROV Can Change It

I have been working on this project alone, coming up with the ideas by myself.

Photo of Anna Du
2 2

Written by

Additional categories (optional)

  • Technology

Are you employed by T-Mobile or related to an employee of T-Mobile?

  • No

Eligibility: Date of Birth

10/25/2005

Help us stay in touch!

phone number: 716-226-6238 mailing address: 16 Evergreen LN MA: Andover (01810)

Website or social media url(s) (optional):

https://www.annadu.org

Date You Started Your Project Started

July/2017

Project Stage: Select the description below that best applies to your approach.

  • Growth (have moved past the very first activities; working towards the next level of expansion)

1. The Problem: What problem are you helping to solve?

Microplastics, which are plastics smaller than 5 millimeters, are posing a great danger to our environment. An estimated 8 million metric tons of plastics were dumped in the ocean in the year 2017 alone. Through the food chain, and ocean movements in general, microplastics can spread across the entire ocean floor, being found everywhere from fish to humans, in multiple brands of salt, and even the Mariana Trench.

2. Your Solution: How are you planning to solve this problem? Share your specific approach.

Currently, there already are many different organizations working on the cleanup of microplastics. However, they are focused on the larger pieces of plastics on the surface of the ocean -- microplastics on the ocean floor haven’t really been touched yet. microplastics is just the beginning. To clean up microplastics in the most efficient way possible, I’m planning on first identifying the patterns of aggregation so we can target the known areas, rather than blindly search the ocean. In the beginning, I planned to use infrared spectroscopy, which is commonly found in waste management industries as a non-intrusive method to identify plastics. Now, I’ve also added an unnatural color detection system, and a morphology color, to find the colors and shapes common in microplastics. These methods can reinforce each other to get a higher accuracy. To improve the system, I’ve added artificial intelligence to increase the accuracy and to make the entire process more efficient. Now, I’m able to get over 90% accuracy in the identification of microplastics. I will use this system to try and spatially map where they are located.

3. Personal Journey: What’s the story behind why you decided to start this project?

I first got inspired two years ago, when I was collecting sea glass at the beach. I was distracted by the number of plastics that were surrounding me. I began to realize the implications of plastics getting everywhere. I started to research this process more and more, and I learned a lot about this problem. I learned about how quickly this issue is growing, and I learned about microplastics. I was horrified, and I wanted to do something immediately. In the beginning, I had some ideas on how to clean up microplastics, but I soon realized that it would be futile to try to clean up the entire ocean from scratch -- I thought it would make more sense, if I first knew where the microplastics were, and then target those areas with a high risk for contamination. I thought that this would be much more efficient than cleaning up every inch of the ocean.

4. Selfie Elevator Pitch: Include 1-minute video that answers the following “I am stepping up to make change because...”

Microplastics are an imminent problem that the world is facing. It has already spread its reaches all around the world -- even to humans. I have created an ROV, which is able to identify microplastics under the ocean utilizing three different systems, an infrared color mapping system, which can analyze the patterns between the absorption and reflection of different objects, an unnatural color identification system, and a morphology classifier, in conjunction with artificial intelligence.

5. Example: Please walk us through a specific example of what happens when a person or group gets involved with your project.

During the process of creating my project, I had to have guidance for every single step. I was unsure of myself, and not confident in the decisions I made for my own project. That changed, when I did a presentation in front of my own school. In the beginning, I was extremely nervous -- but soon, I was able to break out of my shell. Not only did many of my friends and their families compliment me, they also started asking me for help in making the world a better place. I learned that it doesn’t matter where we start this process, what matters is if we start it in the first place. As an ancient Chinese philosopher, Lao-tzu, once said,”Even the greatest journeys must begin with a single step.”

6. The X Factor: What is different about your project compared to other programs or solutions already out there?

My project is differs in three main ways: 1) Using machine learning to assist the data coming from my infrared spectroscopy, UCDS, and morphology identification systems allows the process of locating the microplastics become more accurate and efficient. 2) This is a very low-cost method to identify objects which are difficult to find, making it scalable, which is what we need for a problem of this scale. 3) To clean up the microplastics in the most efficient way possible, we need to first find them. This way, we are spending money and resources on places where we know microplastics are.

7. Impact: How has your project made a difference so far?

Since my project started in 2017, I have received many positive feedback from neighbors, to people all around the world. I’ve been invited to talk with people locally, and to people all the way in Russia! I’ve convinced my friends and family to not use single-use plastic products. When I started to write a book, funding came from people all around the world! I hope that more people, especially children, can be aware of this growing problem, and participate in the fight against plastic pollution.

8. What’s Next: What are your ideas for taking your project to the next level?

My next step is to make my current ROV more scalable. So far, I've been able to achieve my initial goals: make an ROV that can move on the ocean floor, use infrared spectroscopy to identify microplastics in cost efficient way, increase the accuracy through supplemental systems, and use machine learning to identify the plastics quickly and efficiently. The next step would be to apply this on a global scale. By creating a swarm of ROVs, I can tackle the growing problem of plastic pollution across the entire ocean.

How did you hear about this challenge?

  • Email

2 comments

Join the conversation:

Comment
Spam
Photo of Ashka S
Team

I love your idea and think it will make a great impact on the environment! Keep it up!

View all comments