Looking to the future: Advice for scholars

Sara Vanaki shares advice for future scholars and describes her project using computer vision to identify creatures in sea floor photos.

NOAA has collected millions of images of the seafloor to learn about the organisms that live there. But how do you look at millions of photos and identify what is in them? Sara Vanaki, a 2021 Hollings scholar, spent her summer internship with NOAA Fisheries taking on this challenge. She created a machine learning program that can analyze the images and identify sand dollars and sea stars. 

Two images are side-by-side. Each image of the sea floor looks like sand with shell fragments and some darker circles that are identifiable as sand dollars if you zoom in. In the first photo, there are squares around some of the dark circles, but many were not "seen" and identified by the computer. The confidence numbers are almost all under .10. In the right photo, all of the dark circles are identified as sand dollars and the confidence values are much higher.

These images showcase the improvement in Sara’s machine learning program. The image on the left is from her team’s first time running the program. The squares indicate an identified sand dollar and the number next to the square indicates how confident it is in the identification. After going through several hundred such images and checking machine annotations, they were able to improve the machine learning program. The image on the right shows how accurate the machine was after improvements. (Image credit: Sara Vanaki)

Though computer vision may help sort through countless photos, there was no such tool to help Sara choose from the overwhelming number of internship opportunities open to Hollings scholars. She found that learning about several internships of interest helped her make a decision. “I recommend future scholars take advantage of this unique opportunity and ask for as many informational interviews with potential mentors as possible in order to see if you are a good match for that mentor and project,” says Sara.

Sara also advises scholars to use the resources at their fingertips such as networking with others during the summer of the internship to not only learn more about their project, but also to build their social network. She says that the opportunity helped her connect with professors at graduate schools she is interested in, such as the MIT-WHOI program offsite link, Dartmouth College offsite link, and more. After her planned 2023 graduation, Sara looks forward to applying the skills she gained in Computer Vision to pursue a Ph.D. in Computer Science. 

 

Headshot of Sara
Sara Vanaki, 2021 Hollings scholar

Sara Vanaki is double majoring in computer science and mathematics at the University of San Diego offsite link. She credits her professors and advisors, such as Dr. Pruski and Emily Baxt, for helping her become a NOAA Hollings scholar.