- Conservationists can now monitor climate impacts to expansive marine ecosystems over extended periods of time, a task that used to be impossible, using a tool developed by scientists in the U.S.
- The machine learning tool, called Delta Maps, provides a new way to assess which reefs might be best suited for survival, and which play a key role in delivering larvae to others, and therefore should be targeted for preservation efforts, according to the scientists.
- The scientists used the tool to examine the impacts of climate change on connectivity and biodiversity in the Pacific Ocean’s Coral Triangle, the planet’s most diverse and biologically complex marine ecosystem.
- The authors also noted that the Coral Triangle had more opportunities for rebuilding biodiversity, thanks to the region’s dynamic climate component, than anywhere else on the planet.
Machine learning can help conservationists monitor climate impacts across large swaths of marine ecosystems over extended periods of time, a task never possible before.
The Delta Maps machine learning tool provides a new way to assess which reefs might be best-suited for survival and which play a key role in delivering larvae to others, and therefore should be targeted for preservation efforts, according to researchers in a paper published recently in the journal Communications Biology.
The authors write that while this method could revolutionize monitoring of sea surface temperatures at scale, previously measurable only through satellites or remote infrared instruments, it won’t obviate the importance of on-site monitoring.
“The approach we propose, which converges machine learning tools and physical understanding of oceanography and climate variability, can be applied to any ocean from equatorial to mid latitudes, to assess the spatio-temporal evolution of marine ecoregions and their connectivity — and connectivity changes over time,” Lyuba Novi, a postdoctoral fellow at Georgia Tech’s School of Earth and Atmospheric Sciences and one of the duo who developed the method, told Mongabay in an email.
The scientists used the tool to examine the impacts of climate change on the connectivity and biodiversity in the Pacific Ocean’s Coral Triangle, the planet’s most diverse and biologically complex marine ecosystem. They mapped out the regions within the Coral Triangle that share the same dynamic and connectivity, and then separated the time periods based on major climate events, such as El Niño, La Niña, and neutral or “normal” times.
The Coral Triangle is a patch of the western Pacific that encompasses the waters around the Philippines, Indonesia, Malaysia, Papua New Guinea, the Solomon Islands and Timor-Leste. A 2018 report by the Intergovernmental Panel on Climate Change (IPCC) estimated that 70-90% of coral reefs will decline as temperatures exceed 1.5° Celsius (2.7° Fahrenheit) of warming above pre-industrial levels, and that 99% of corals will be lost with 2°C (3.6°F) of warming.
“Of course, each ecosystem is different and an oceanographic understanding of the system is necessary to assess which components may be important for it,” Novi said.
The researchers found that climate dynamics impacted biodiversity by affecting the currents in the equatorial Pacific. Their findings also showed that changes due to El Niño and La Niña events allowed for significant genetic exchanges between the Indian and Pacific oceans and enabled the ecosystems to survive through a variety of different climate scenarios.
“One of the striking discoveries has been to find that ENSO [El Niño Southern Oscillation] has not only a detrimental effect on coral survivorship, but it has also a strong positive impact in terms of larval transport and biodiversity maintenance across the area,” study co-author Annalisa Bracco, a professor and associate chair for research at Georgia Tech’s School of Earth and Atmospheric Sciences, told Mongabay in the same email.
“Recognizing this role for ENSO allowed us to interpret within a climate variability context the evolution of species richness in the Indo-Pacific through geological times, which was outside the original goal of our project and a very interesting discovery,” she added.
Novi and Bracco also noted that the Coral Triangle had more opportunities for rebuilding biodiversity, thanks to the region’s dynamic climate component, than anywhere else on the planet. This is crucial as conservation experts and authorities around the world work to identify which ecosystems need the strictest monitoring and protection.
“Biologists collect data in situ, which is extremely important,” Bracco said in a statement. “But it’s not possible to monitor enormous regions in situ for many years — that would require a constant presence of scuba divers. So, figuring out how different ocean regions and large marine ecosystems are connected over time, especially in terms of foundational species like coral, becomes important.”
They said they plan to present their findings to the U.S. National Oceanic and Atmospheric Administration (NOAA), and hope to add information about other stressors, such as sources of pollution, overfishing maps, and others, to improve the outcome and potentially develop a monitoring system for seasonal to annual time scales.
“Alone may or may not be sufficient, but in conjunction with in-situ monitoring we believe will revolutionize coral monitoring,” Bracco said.
Novi, L. & Bracco, A. (2023). Machine learning prediction of connectivity, biodiversity and resilience in the Coral Triangle. Communications Biology, 5(1359). doi:10.1038/s42003-022-04330-8
Basten Gokkon is a senior staff writer for Indonesia at Mongabay. Find him on Twitter @bgokkon.
See related from this reporter:
FEEDBACK: Use this form to send a message to the author of this post. If you want to post a public comment, you can do that at the bottom of the page.
This story first appeared on Mongabay
South Africa Today – Environment
This article is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
You may republish this article, so long as you credit the authors and Mongabay, and do not change the text. Please include a link back to the original article.