Adam Coscia, a fourth-year doctoral student at Georgia Tech, has transformed oceanographic research with his interactive data visualization tool, DeepSee, which allows scientists to predict and analyze sediment sample hotspots in deep-sea environments.
A groundbreaking data visualization tool is offering oceanographers and microbial ecologists an unprecedented look at the deep-sea ecosystems they study. Designed by Adam Coscia, a fourth-year doctoral student at Georgia Tech, the tool, called DeepSee, is transforming how researchers predict and analyze sediment sample hotspots.
Initially started as an internship project at NASA, Coscia’s work has evolved into a critical resource under the guidance of an interdisciplinary team from Caltech, the Jet Propulsion Laboratory (JPL) managed by Caltech for NASA and the ArtCenter College of Design.
Victoria Orphan, the leader of the research team at Caltech, is a renowned microbial ecologist with a focus on studying deep-sea microbial communities and their interactions within seafloor sediments. Having faced organizational challenges with historical data sets, Orphan and her team needed a more consolidated approach.
“Historically, our data sets have been discrete and have lived in separate Excel spreadsheets. Maybe at the end, we’ll do some statistical analysis to find correlations in that data. Then we compare those to our maps,” Orphan said in a news release. “We didn’t have a way of consolidating everything under one umbrella that allows us to learn more about these ecosystems.”
To optimize their research expeditions, Orphan’s team annually embarks on voyages off the California coast, using remotely operated vehicles (ROVs) to collect crucial sediment samples. The introduction of DeepSee has revolutionized these expeditions.
“The idea is once you have the samples, and you’re interested in a specific area with prior samples, you can go in and annotate on the map where to collect samples next with our drawing tool,” Coscia said in the news release.
DeepSee integrates topographic and photographic data into a user-friendly, interactive web browser that can generate 3D visualization models. This innovative tool not only enhances data organization but also facilitates real-time interaction and note-taking.
“We focused on the exploration and notetaking process with maps and data and having new ways of visualizing it,” Coscia added. “Scientists can draw and map out all their samples in real time. They can reference specific data much easier and determine where the team should go to get the best samples.”
Implemented during two recent expeditions, DeepSee has already demonstrated increased efficiency in strategic planning for the Orphan Lab.
“The infrastructure put in place by Adam will make this an enabling tool not only for my group but for other oceanographers and scientists in other fields — anywhere there is a spatial distribution of information you want to connect to other metadata,” Orphan said.
DeepSee is also proving invaluable for training new researchers, making the onboarding process more seamless and intuitive.
“We can onboard them much easier and give them a sense of what data is available and where we’ve collected information in a way that’s much clearer than having them refer to an Excel spreadsheet,” Orphan added.
The tool’s capabilities extend beyond surface-level data visualization, as it can create 3D models under the sea floor, estimating data quality in adjacent locations based on known data points.
“You would never see anything visually below the sea floor. You’d have to go dig. But our 3D models show you that you might have data suggesting a hotspot just a few feet below the floor. That tells you where to sample next,” Coscia said.
Looking ahead, Coscia aims to integrate machine learning models into DeepSee to further enhance its predictive capabilities, contingent on the accumulation of more data.
DeepSee stands as a beacon of innovation in oceanographic research, heralding a new era of data visualization and efficiency in the field.