close
close

Association-anemone

Bite-sized brilliance in every update

New machine learning techniques more accurately measure ocean oxygen loss
asane

New machine learning techniques more accurately measure ocean oxygen loss

Oxygen is essential for living organisms, especially multicellular life, to metabolize organic matter and power all life activities. About half of the oxygen we breathe comes from land plants such as forests and grasslands, while the other half is produced through photosynthesis by marine algae in the ocean’s surface waters.

Oxygen concentrations are declining in many parts of the world’s oceans. Experts believe this drop is related to surface ocean warming and its impact on the physics and chemistry of seawater, although the issue is not fully understood. Temperature plays a crucial role in determining how oxygen dissolves in seawater; as water warms, it loses its ability to hold gas.

“Calculating the amount of oxygen lost from the oceans is challenging because of limited historical measurements and inconsistent timing,” said Taka Ito, an oceanographer and professor in Georgia Tech’s School of Earth and Atmospheric Sciences. “To understand global oxygen levels and their changes, we need to fill many data gaps.”

A group of student researchers attempted to address this issue. Led by Ito, the team developed a new machine learning-based approach to understand and more accurately represent the decline in global ocean oxygen levels. Using the datasets, the team further generated a monthly map of oxygen content that visualizes the decline in ocean oxygen over several decades. Their research was published in Journal of Geophysical Research: Machine Learning and Computation.

“Marine scientists need to understand the distribution of oxygen in the ocean, how much it’s changing, where the changes are happening and why,” said Ahron Cervania, Ph.D. student in Ito’s lab. “Statistical methods have long been used for these estimates, but machine learning techniques can improve the accuracy and resolution of our oxygen assessments.”

The project began three years ago with support from the National Science Foundation, and the team initially focused only on Atlantic Ocean data to test the new method. They used a computational model to generate hypothetical observations, which allowed them to assess how well they could reconstruct the missing information about oxygen levels using just a fraction of the data combined with machine learning. After developing this method, the team expanded to observing the global oceans, involving students and delegating tasks to different ocean basins.

Under Ito’s guidance, Cervania and other student researchers developed algorithms to analyze the relationships between oxygen content and variables such as temperature, salinity and pressure. They used a dataset of historical oxygen observations from ships dating back to the 1960s and recent data from the Argo floats — autonomous floating devices that collect and measure temperature and salinity. Although oxygen data existed before the 1960s, earlier records have accuracy problems, so the team focused on data from the 1960s onwards. They then created a global monthly map of ocean oxygen content from 1965 to the present.

“Using a machine learning approach, we were able to estimate the rate of oxygen loss more precisely at different times and locations,” Cervania said. “Our findings indicate that incorporating buoyant data significantly improves the estimate of oxygen loss while reducing uncertainty.”

The team found that the world’s oceans lost oxygen at a rate of about 0.7% per decade between 1970 and 2010. This estimate suggests a relatively rapid response of the oceans to recent climate change, with potential long-term impacts on the health and sustainability of ecosystems marine. . Their estimate also falls within the range of decline suggested by other studies, indicating the accuracy and effectiveness of their approach.

“We calculated trends in global oxygen levels and ocean inventory, essentially looking at the rate of change over the last five decades,” Cervania said. “It is encouraging to see that our rate aligns with previous estimates from other methods, which gives us confidence. We construct a robust estimate from both our study and other studies.

According to Ito, the team’s new approach addresses an ongoing challenge in the oceanographic community: how to effectively combine different data sources with different accuracies and uncertainties to better understand ocean changes.

“Integrating advanced technologies such as machine learning will be critical to filling in the data gaps and providing a clearer picture of how our oceans are responding to climate change.”