🔍 Read the full analysis: Tasmania’s Giant Kelp Recovery: What Google And CSIRO’s AI Shows on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
Google says CSIRO used a kelp-trained version of its DeepVariant tool to analyze DNA from 600 wild giant kelp specimens collected at 40 Tasmanian coastal sites. The peer-reviewed Australian reference genomes are published, but the larger specimen analysis and reported genetic isolation have not yet been documented in a paper or dataset identified by the source. Scientists plan selective breeding and reef plantings; survival through warmer summers remains untested.
Google said November 12 that Australia’s national science agency, CSIRO, used a version of Google’s DeepVariant AI tool to analyze DNA from 600 wild giant kelp specimens collected at 40 sites along Tasmania’s coast. The work is intended to help researchers select native kelp for selective breeding as forests have sharply declined, but it has not yet shown that bred kelp can withstand warmer ocean conditions.
The project uses AI to help read genetic differences, not to plant kelp or directly measure heat tolerance. According to Google’s announcement and video, researchers adapted DeepVariant, whose standard models are trained on human data, to analyze kelp DNA. The genetic results can be compared with laboratory tests to help scientists choose which surviving plants to cross. The source says the 600-specimen analysis and the finding that remaining Tasmanian patches are genetically isolated have so far been reported by Google, rather than in a paper or dataset identified by the source.
A separate part of the research has been published in BMC Genomics in June 2026. The peer-reviewed study, authored by CSIRO scientists and a Google researcher, presents two Australian giant kelp reference genomes, built from plants collected in Victoria and Tasmania. Its abstract reports that researchers placed 98–99% of each genome into 35 pseudo-chromosomes. The Australian genomes differ from each other by 0.2%, while the comparison with the Californian reference genome found a 1.5% difference.
Those local reference genomes provide a more relevant basis for studying Australian kelp than a Californian specimen alone. Google says its open-source tools DeepConsensus and DeepPolisher helped correct errors in raw genetic reads used to build the references. The study’s data is public, according to the source. The new Google announcement concerns the subsequent analysis of wild specimens, a distinct result whose supporting publication was not identified in the source material.
Giant kelp · Tasmania · CSIRO with Google AI
From the reef to the lab and back: where the AI fits
Five steps, as described by CSIRO and Google. The AI works in steps 2 and 3; people do the diving, the lab work and the planting.
1Reef
Collect wild kelp
600 wild specimens from 40 sites along the Tasmanian coast, according to Google.
2Lab + AI
Build a local reference
Long-read DNA plus Google’s DeepConsensus and DeepPolisher: two Australian reference genomes, published in BMC Genomics.
AI step3AI
Read each plant
A version of DeepVariant trained for kelp finds where each specimen’s DNA differs.
AI step4Lab
Choose and cross
Distinct survivors with genetic variation and heat-tolerant traits are crossed. Selective breeding, not genetic modification.
5Reef
Replant and watch
Young kelp is attached to rocky reef in pilot tests. Warm summers show which plants survive.
Sources: Google blog post, Nov 12, 2026, and Google Research video; Scharfenstein et al., BMC Genomics, 2026; CSIRO, 2024, and CSIRO on Google Arts & Culture. The scene is a schematic, not a map or real data.
Graphic: Powered by Thorsten Meyer AI
Selecting Kelp for Warmer Seas
The research addresses a conservation problem with consequences beyond the loss of a single seaweed. CSIRO says giant kelp forests provide habitat for marine life, including fish nurseries, octopuses, sea stars and sea lions. It has described the ecological stakes plainly: “Without Giant Kelp to form the forests, the entire ecosystem disappears.” A method for identifying genetic differences among survivors could help researchers decide which plants to breed, rather than relying on trial and error alone.
But the AI is one step in a longer chain, not a recovery result. DNA analysis can identify variation and help connect it to laboratory measurements; it cannot establish by itself that a particular plant will tolerate warming, or that a restored forest will persist in the ocean. The practical test will be whether selectively bred young kelp survive when planted on reefs exposed to the conditions that contributed to the decline. That field outcome has not yet been reported.
Products Worth Considering
Samsung 27-inch Odyssey OLED G6 QHD Gaming Monitor
Logitech MX Master 4 Ergonomic Wireless Mouse with Haptic Feedback, Graphite
Bose QuietComfort Wireless Bluetooth Headphones – Active Over‑Ear Noise Cancelling with Mic, USB‑C Charging, Deep Bass, up to 24 h Playtime,
As an affiliate, we earn on qualifying purchases.
From Genome Maps to Wild Samples
CSIRO attributes the decline of Tasmanian giant kelp to warmer, nutrient-poor water and invading sea urchins, with the East Australian Current carrying these conditions farther south. The source reports that Tasmanian forests have fallen by about 95% of historic numbers, while a preprint citing earlier research describes a 95–98% loss of East Tasmanian kelp cover since 1940. These figures come from different source descriptions and should not be treated as an identical measurement.
Google Australia announced a broader partnership with CSIRO and other organizations in February 2024. Its two strands included mapping remaining kelp in more than 7,000 square kilometres of satellite imagery and using genomics. The November 2026 announcement focuses on the genomics work. Until the new Australian references were published, researchers had relied on a Californian giant kelp reference. The peer-reviewed study found a 1.5% genetic difference between Australian and Californian references, compared with 0.2% between the two Australian genomes, supporting the use of locally sourced references for this work.
““trained a version of our AI model DeepVariant to analyze our wild samples””
— Google, in a video accompanying its November 12 announcement
Evidence Still Awaiting Publication
The evidence has different levels of public documentation. The two Australian reference genomes are described in a peer-reviewed paper, and the source says their data is public. By contrast, the 600-sample analysis and reported genetic isolation of remaining kelp patches are described in Google’s blog post and video; the source reports finding no associated paper or dataset. The announcement therefore offers a company account of those results, not the same level of independently inspectable evidence as the published genome study.
It is also not yet clear which genetic differences correspond to greater heat tolerance, how those traits will perform outside laboratory conditions, or when reef plantings will occur. The central ecological question—whether selectively bred kelp survives warmer summers at sea—remains unanswered. The project’s AI does not itself test that outcome.
Breeding and Reef Trials Ahead
Researchers plan to cross genetically distinct native survivors through selective breeding, then grow young kelp for planting on reefs. The source distinguishes this approach from genetic modification. Lab tests are expected to help connect DNA variation with traits of interest, while later plantings would test whether the kelp can establish and persist in the sea.
The next evidence readers can look for includes a publication or public dataset describing the 600 wild specimens, details of how candidate parent plants are selected, and results from reef trials. No timing or survival results for those trials are provided in the source material. Until field evidence is available, the project shows a way to support conservation decisions—not proof that Tasmania’s kelp forests are recovering.
Key Questions
What did Google and CSIRO use AI to do?
Google says researchers adapted its DeepVariant tool to analyze DNA from 600 wild giant kelp specimens collected at 40 sites along Tasmania’s coast. The analysis is intended to help identify genetic differences that can guide selective breeding; it does not directly measure ocean heat tolerance.
Has the 600-specimen analysis been peer-reviewed?
The source says the findings about the 600 specimens and genetic isolation were described in Google’s announcement and video, and that it found no paper or dataset for them. A separate study presenting two Australian reference genomes was published in BMC Genomics in June 2026.
How much have Tasmanian giant kelp forests declined?
Google’s account says populations have dwindled to 5% of historic numbers, and CSIRO describes a decline of about 95%. A preprint cited in the source reports a 95–98% loss of East Tasmanian kelp cover since 1940, based on earlier research.
Is the kelp being genetically modified?
No genetic modification is described. Researchers plan to cross native kelp through selective breeding, using genetic analysis and laboratory tests to help choose parent plants.
Has the bred kelp survived warmer summers in the ocean?
No such result is reported. The source says the researchers plan reef plantings, but whether selectively bred kelp will survive warmer summers remains an open question.
Source: ThorstenMeyerAI.com
