News
A Reconstructing Model Based on Time–Space–Depth Partitioning for Global Ocean Dissolved Oxygen Concentration
Abstract.
"Dissolved oxygen (DO) is essential for assessing and monitoring the health of marine ecosystems. The phenomenon of ocean deoxygenation is widely recognized. Nevertheless, the limited availability of observations poses a challenge in achieving a comprehensive understanding of global ocean DO dynamics and trends. The study addresses the challenge of unevenly distributed Argo DO data by developing time–space–depth machine learning (TSD-ML), a novel machine learning-based model designed to enhance reconstruction accuracy in data-sparse regions. [...]".
Source: MDPI
Authors: Zhenguo Wang et al.
DOI: https://doi.org/10.3390/rs16020228
Reconstruction of dissolved oxygen in the Indian Ocean from 1980 to 2019 based on machine learning techniques
Abstract.
"Oceanic dissolved oxygen (DO) decline in the Indian Ocean has profound implications for Earth’s climate and human habitation in Eurasia and Africa. Owing to sparse observations, there is little research on DO variations, regional comparisons, and its relationship with marine environmental changes in the entire Indian Ocean. In this study, we applied different machine learning algorithms to fit regression models between measured DO, ocean reanalysis physical variables, and spatiotemporal variables. [...]".
Source: Frontiers in Marine Science
Authors: Sheng Huang et al.
DOI: https://doi.org/10.3389/fmars.2023.1291232
GOBAI-O2: temporally and spatially resolved fields of ocean interior dissolved oxygen over nearly 2 decades
Abstract.
"For about 2 decades, oceanographers have been installing oxygen sensors on Argo profiling floats to be deployed throughout the world ocean, with the stated objective of better constraining trends and variability in the ocean's inventory of oxygen. Until now, measurements from these Argo-float-mounted oxygen sensors have been mainly used for localized process studies on air–sea oxygen exchange, upper-ocean primary production, biological pump efficiency, and oxygen minimum zone dynamics. Here, we present a new four-dimensional gridded product of ocean interior oxygen, derived via machine learning algorithms trained on dissolved oxygen [...]".
Source: Earth System Science Data
Authors: Jonathan D. Sharp et al.
DOI: https://doi.org/10.5194/essd-15-4481-2023
Using machine learning to understand climate change
"Methane is a potent greenhouse gas that is being added to the atmosphere through both natural processes and human activities, such as energy production and agriculture.
To predict the impacts of human emissions, researchers need a complete picture of the atmosphere’s methane cycle. They need to know the size of the inputs—both natural and human—as well as the outputs. They also need to know how long methane resides in the atmosphere.
To help develop this understanding, Tom Weber, an assistant professor of earth and environmental sciences at the University of Rochester; undergraduate researcher Nicola Wiseman ’18, now a graduate student at the University of California, Irvine; and their colleague Annette Kock at the GEOMAR Helmholtz Centre for Ocean Research in Germany, used data science to determine how much methane is emitted from the ocean into the atmosphere each year. [...]"
Source: University of Rochester
Newsletter
It is possible to subscribe to our email newsletter list.
Depending on the amount of publications, we will summarize the activities on this blog in a newsletter for everyone not following the blog regularly.
If you want to subscribe to the email list to receive the newsletter, please send an email to sfb754@geomar.de with the header "subscribe".
If you want to unsubscribe from the newsletter, please send an email to sfb754@geomar.de with the header "unsubscribe".
You cannot forward any messages as a regular member to the list. If you want to suggest new articles or would like to contact us because of any other issue, please send an email to sfb754@geomar.de.