TL;DR
Google said on November 12 that CSIRO used AI tools and genomics to analyze 600 giant kelp specimens from Tasmania, supporting work to breed plants for restoration. Two Australian reference genomes have been published in a peer-reviewed journal, but the specimen analysis and reported genetic isolation have so far been described in Google’s announcement. No evidence yet shows whether selectively bred kelp can withstand warm summers in the ocean.
Google said November 12 that Australia’s CSIRO used AI-based genomics tools to analyze 600 wild giant kelp specimens collected from 40 sites along Tasmania’s coast, work intended to help scientists select plants for selective breeding. The announcement describes a research step in efforts to restore kelp forests that CSIRO says have declined by 95%; it does not show that the bred kelp has survived warmer conditions at sea.
Get everyday essentials delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
According to Google, the team used a version of DeepVariant retrained to read kelp DNA to identify genetic differences among the collected specimens. The analysis follows work to build two Australian reference genomes using long-read sequencing and Google’s DeepConsensus and DeepPolisher tools. Those reference genomes were published in BMC Genomics in June 2026, in a paper co-authored by CSIRO scientists and a Google researcher, and the data is public.
The published genomes show that the Australian giant kelp reference differs from a Californian reference genome by 1.5%, while the two Australian genomes differ from each other by 0.2%, according to the source material. Google’s November announcement also says the remaining Tasmanian kelp patches are genetically isolated. That finding, along with the analysis of all 600 specimens, was reported in Google’s post and video; the source material says no paper or dataset for those results was found.
The AI does not test heat tolerance or restore the reefs directly. Scientists conduct laboratory tests and connect those results with genetic information, then plan to cross selected native kelp through selective breeding. The project description says this is not genetic modification. Young kelp is intended for pilot planting on rocky reefs, where researchers can observe how it fares.
The Test Is Survival at Sea
The research could help scientists identify genetic variation among the kelp that remains and choose which plants to cross. That matters because Tasmania’s giant kelp forests have suffered a major decline, and restoration depends on finding plants suited to local conditions. A genetic analysis can inform those choices, but it cannot by itself establish that selected kelp will tolerate warmer water or persist after planting.
For readers, the distinction is between a research tool and a proven restoration result. The genomes and the restoration aim are documented; the reported 600-specimen analysis is currently described by Google, and survival through warm summers remains untested in published field results. The project’s value will depend on what happens when bred kelp is returned to the reef.
Products Worth Considering
Samsung 27-inch Odyssey OLED G6 QHD Gaming Monitor
LG UltraGear 34-inch Curved OLED Gaming Monitor, WQHD 1440p, 240Hz, 0.03ms, 800R
LG UltraGear evo 27-inch 5K Mini-LED Gaming Monitor
As an affiliate, we earn on qualifying purchases.
Why Tasmania’s Kelp Declined
Giant kelp, or Macrocystis pyrifera, forms underwater forests in cold, shallow seas. CSIRO says plants in Tasmanian waters can grow to around 30 metres. The forests provide habitat for marine life, including fish, octopuses, sea stars and sea lions. CSIRO has described the ecosystem as dependent on the kelp forest.
CSIRO attributes the decline to warmer, nutrient-poor water and invading sea urchins, with the East Australian Current moving farther south. CSIRO says the forests around Tasmania have declined by 95% in recent decades. A 2026 genome-paper preprint, citing earlier research, gives a 95% to 98% loss of giant kelp cover in eastern Tasmania since 1940. These figures refer to different descriptions and time frames in the cited material.
The genomics work is part of a broader partnership announced by Google Australia and CSIRO in February 2024 with the University of Tasmania’s Institute for Marine and Antarctic Studies, The Nature Conservancy, the Great Southern Reef Foundation and the Kelp Forest Alliance. The original project also included plans to map kelp using satellite imagery, Google Earth Engine and Vertex AI. Google’s November 2026 update focuses on the genomics strand.
““Without Giant Kelp to form the forests, the entire ecosystem disappears.””
— CSIRO
Evidence Still Awaiting Publication
The source material identifies the two Australian reference genomes as peer-reviewed research, but says the 600-specimen analysis and genetic-isolation finding have so far appeared in Google’s post and video rather than a paper or dataset. The methods and results for that analysis therefore cannot be assessed from the published material cited here.
It is also unknown whether the selected and crossed kelp will survive on Tasmanian reefs through warm summers. The source material reports no survival data from field plantings. The scale, timing and results of planned reef trials are not specified in Google’s announcement as summarized here.
From Breeding to Reef Trials
Researchers plan to cross distinct native survivors in laboratory selective-breeding work, using genetic variation and heat-tolerance traits to inform their choices. They then plan to attach young kelp to rocky reefs in pilot tests. Field survival through warm summers will be a key practical measure of whether the breeding approach can support restoration.
Further reporting will depend on publication of the specimen-analysis results and data, as well as updates on when reef plantings begin and how the kelp performs. Until those results are available, the work remains a research and restoration effort rather than evidence of a successful recovery.
Key Questions
What did Google and CSIRO report?
Google said CSIRO used a kelp-adapted version of DeepVariant to analyze 600 wild specimens collected from 40 sites along Tasmania’s coast, as part of research to inform selective breeding.
Has the AI restored Tasmania’s kelp forests?
No restoration outcome is reported. The AI tools help analyze DNA; scientists still need to breed kelp, plant it on reefs and assess its survival.
Which part of the work is peer reviewed?
Two Australian giant kelp reference genomes were published in BMC Genomics in June 2026. The source material says the 600-specimen analysis and genetic-isolation finding have so far been reported in Google’s post and video.
Are the scientists genetically modifying the kelp?
The project description says scientists plan to use selective breeding, crossing native plants. It does not describe genetic modification.
Do the bred plants survive warmer summers?
That remains unknown. The source material reports no published field-survival data for bred kelp in warm summer conditions.
Source: Thorsten Meyer AI
