{"678242":{"#nid":"678242","#data":{"type":"news","title":"Novel Machine Learning Techniques Measure Ocean Oxygen Loss More Accurately","body":[{"value":"\u003Cp\u003EOxygen is essential for living organisms, particularly multicellular life, to metabolize organic matter and energize all life activities. About half of the oxygen we breathe comes from terrestrial plant life, such as forests and grasslands, while the other half is produced through photosynthesis by marine algae in the ocean\u0027s surface waters.\u003C\/p\u003E\u003Cp\u003EOxygen concentrations are declining in many parts of the world\u2019s oceans. Experts believe this drop is linked to the ocean\u2019s surface warming and its impacts on the physics and chemistry of seawater, though the problem 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.\u003C\/p\u003E\u003Cp\u003E\u201cCalculating the amount of oxygen lost from the oceans is challenging due to limited historical measurements and inconsistent timing,\u201d said \u003Ca href=\u0022https:\/\/eas.gatech.edu\/people\/ito-dr-taka\u0022\u003ETaka Ito\u003C\/a\u003E, oceanographer and professor in the \u003Ca href=\u0022https:\/\/eas.gatech.edu\/\u0022\u003ESchool of Earth and Atmospheric Sciences\u003C\/a\u003E at Georgia Tech. \u201cTo understand global oxygen levels and their changes, we need to fill in many data gaps.\u201d\u003C\/p\u003E\u003Cp\u003EA group of student researchers sought to address this issue. Led by Ito, the team developed a new machine learning-based approach to more accurately understand and represent the decline in global ocean oxygen levels. Using datasets, the team further generated a monthly map of oxygen content visualizing the ocean\u2019s oxygen decline over several decades. Their research was \u003Ca href=\u0022https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/full\/10.1029\/2024JH000272\u0022\u003Epublished\u003C\/a\u003E in the \u003Cem\u003EJournal of Geophysical Research: Machine Learning and Computation\u003C\/em\u003E.\u003C\/p\u003E\u003Cp\u003E\u201cMarine scientists need to understand the distribution of oxygen in the ocean, how much it\u0027s changing, where the changes are occurring, and why,\u201d said \u003Ca href=\u0022https:\/\/eas.gatech.edu\/people\/cervania-ahron\u0022\u003EAhron Cervania\u003C\/a\u003E, a Ph.D. student in Ito\u2019s lab. \u201cStatistical methods have long been used for these estimates, but machine learning techniques can improve the accuracy and resolution of our oxygen assessments.\u201d\u003C\/p\u003E\u003Cp\u003EThe project began three years ago with support from the National Science Foundation, and the team initially focused solely 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 missing oxygen level information using only a fraction of the data combined with machine learning. After developing this method, the team expanded to global ocean observations, involving undergraduate students and delegating tasks across different ocean basins.\u003C\/p\u003E\u003Cp\u003EUnder Ito\u2019s guidance, Cervania and other student researchers developed algorithms to analyze the relationships between oxygen content and variables like temperature, salinity, and pressure. They used a dataset of historical, ship-based oxygen observations since the 1960s and recent data from Argo floats \u2014 autonomous drifting devices that collect and measure temperature and salinity. Although oxygen data existed before the 1960s, earlier records have accuracy issues, so the team focused on data from the 1960s onward. They then created a global monthly map of ocean oxygen content from 1965 to the present.\u003C\/p\u003E\u003Cp\u003E\u201cUsing a machine learning approach, we were able to assess the rate of oxygen loss more precisely across different periods and locations,\u201d Cervania said. \u201cOur findings indicate that incorporating float data significantly enhances the estimate of oxygen loss while also reducing uncertainty.\u201d\u003C\/p\u003E\u003Cp\u003EThe team found that the world\u2019s oceans have lost oxygen at a rate of about 0.7% per decade from 1970 to 2010. This estimate suggests a relatively rapid ocean response to recent climate change, with potential long-term impacts on marine ecosystems\u2019 health and sustainability. Their estimate also falls within the range of decline suggested by other studies, indicating the accuracy and efficacy of their approach.\u003C\/p\u003E\u003Cp\u003E\u201cWe calculated trends in global oxygen levels and the ocean\u2019s inventory, essentially looking at the rate of change over the last five decades,\u201d Cervania said. \u201cIt\u2019s encouraging to see that our rate aligns with previous estimates from other methods, which gives us confidence. We are building a robust estimate from both our study and other studies.\u201d\u003C\/p\u003E\u003Cp\u003EAccording to Ito, the team\u2019s new approach addresses an ongoing challenge in the oceanographic community: how to effectively combine different data sources with varying accuracies and uncertainties to better understand ocean changes. \u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u201cThe integration of advanced technologies like machine learning will be essential in filling data gaps and providing a clearer picture of how our oceans are responding to climate change.\u201d\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECitation\u003C\/strong\u003E: Ito, T., Cervania, A., Cross, K., Ainchwar, S., \u0026amp; Delawalla, S. (2024). Mapping dissolved oxygen concentrations by combining shipboard and Argo observations using machine learning algorithms. Journal of Geophysical Research: Machine Learning and Computation, 1, e2024JH000272.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDOI\u003C\/strong\u003E: https:\/\/doi.org\/10.1029\/2024JH000272\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EFunding\u003C\/strong\u003E: National Science Foundation\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EGeorgia Tech researchers introduced a groundbreaking machine learning technique to improve the assessment and analysis of declining oxygen levels in the ocean.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Georgia Tech researchers introduced a groundbreaking machine learning technique to improve the assessment and analysis of declining oxygen levels in the ocean."}],"uid":"36123","created_gmt":"2024-11-06 20:22:39","changed_gmt":"2024-12-04 19:19:32","author":"Catherine Barzler","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2024-11-11T00:00:00-05:00","iso_date":"2024-11-11T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"675578":{"id":"675578","type":"image","title":"Argo-photo-book-2009-05-06-11.30.49-Mizue-scaled (1).jpg","body":"\u003Cp\u003EUsing data from Argo floats (pictured) and historic ship measurements, Georgia Tech researchers developed new machine learning techniques to better understand global ocean oxygen loss. (Credit: Argo Program, UCSD)\u003C\/p\u003E","created":"1731359935","gmt_created":"2024-11-11 21:18:55","changed":"1731359935","gmt_changed":"2024-11-11 21:18:55","alt":"Argo float","file":{"fid":"259218","name":"Argo-photo-book-2009-05-06-11.30.49-Mizue-scaled (1).jpg","image_path":"\/sites\/default\/files\/2024\/11\/11\/Argo-photo-book-2009-05-06-11.30.49-Mizue-scaled%20%281%29.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/11\/Argo-photo-book-2009-05-06-11.30.49-Mizue-scaled%20%281%29.jpg","mime":"image\/jpeg","size":549965,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/11\/Argo-photo-book-2009-05-06-11.30.49-Mizue-scaled%20%281%29.jpg?itok=HOMR582-"}},"675579":{"id":"675579","type":"image","title":"o2 inventory.png","body":"\u003Cp\u003EBasin-scale oxygen inventory trend with global ocean divided to 10 basins. Blue lines and shading show ensemble mean and ensemble range for ship-only reconstructions, and red lines and shading are for ship and Argo float reconstructions. The research team divided up the task by working on different basins.\u0026nbsp;(Credit: Georgia Institute of Technology)\u003C\/p\u003E","created":"1731360589","gmt_created":"2024-11-11 21:29:49","changed":"1731360589","gmt_changed":"2024-11-11 21:29:49","alt":"Oxygen timeseries figure","file":{"fid":"259219","name":"o2 inventory.png","image_path":"\/sites\/default\/files\/2024\/11\/11\/o2%20inventory.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/11\/o2%20inventory.png","mime":"image\/png","size":494667,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/11\/o2%20inventory.png?itok=DngpypMZ"}},"675581":{"id":"675581","type":"image","title":"ito.jpg","body":"\u003Cp\u003ETaka Ito, oceanographer and professor in the School of Earth and Atmospheric Sciences.\u003C\/p\u003E","created":"1731361023","gmt_created":"2024-11-11 21:37:03","changed":"1731361023","gmt_changed":"2024-11-11 21:37:03","alt":"Taka Ito","file":{"fid":"259221","name":"ito.jpg","image_path":"\/sites\/default\/files\/2024\/11\/11\/ito.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/11\/ito.jpg","mime":"image\/jpeg","size":62373,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/11\/ito.jpg?itok=NAgUWRhW"}},"675582":{"id":"675582","type":"image","title":"sm ahron cervania.jpg","body":"\u003Cp\u003EAhron Cervania, a Ph.D. student in Earth and Atmospheric Sciences.\u003C\/p\u003E","created":"1731361568","gmt_created":"2024-11-11 21:46:08","changed":"1731361568","gmt_changed":"2024-11-11 21:46:08","alt":"Ahron Cervania","file":{"fid":"259222","name":"sm ahron cervania.jpg","image_path":"\/sites\/default\/files\/2024\/11\/11\/sm%20ahron%20cervania.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/11\/sm%20ahron%20cervania.jpg","mime":"image\/jpeg","size":111846,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/11\/sm%20ahron%20cervania.jpg?itok=lpsUBGrA"}}},"media_ids":["675578","675579","675581","675582"],"groups":[{"id":"1278","name":"College of Sciences"},{"id":"1214","name":"News Room"},{"id":"1188","name":"Research Horizons"},{"id":"364801","name":"School of Earth and Atmospheric Sciences (EAS)"}],"categories":[],"keywords":[{"id":"187915","name":"go-researchnews"},{"id":"192254","name":"cos-climate"},{"id":"193266","name":"cos-research"}],"core_research_areas":[],"news_room_topics":[{"id":"71911","name":"Earth and Environment"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ECatherine Barzler, Senior Research Writer\/Editor\u003Cbr\u003EInstitute Communications\u003Cbr\u003E\u003Ca href=\u0022mailto:catherine.barzler@gatech.edu\u0022\u003Ecatherine.barzler@gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":["catherine.barzler@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}