🔍 Read the full analysis: Can Machine Learning Help Tasmania’s Giant Kelp Recover? 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 it and CSIRO used a kelp-trained version of DeepVariant to analyze DNA from 600 wild giant kelp specimens collected at 40 sites around Tasmania. The work is intended to help scientists select native kelp for selective breeding, but the analysis is not yet described in a published paper or dataset, and survival in warmer seas remains untested.
Google says a version of its DeepVariant DNA-analysis tool, retrained for giant kelp, has been used with CSIRO to analyze 600 wild specimens from 40 sites along Tasmania’s coast. The work is intended to help researchers choose native kelp for selective breeding as they seek to restore forests that CSIRO says have declined by 95%; whether bred kelp can withstand warmer summers in the sea has not yet been tested.
The project’s immediate aim is to identify genetic differences among surviving kelp, not to plant or genetically modify seaweed. According to Google’s November 12 post and accompanying video, researchers used a version of DeepVariant adapted to kelp DNA to analyze the 600 samples. The company says the analysis found that remaining Tasmanian patches are genetically isolated. That specific result is reported in Google’s announcement; the source material says a paper or dataset documenting it was not available.
The analysis builds on two Australian giant kelp reference genomes produced by CSIRO scientists and a Google researcher. The genomes, from specimens collected in Victoria and Tasmania, were published in BMC Genomics in June 2026, and the data are public. The paper reports that the Australian genomes differ from one another by 0.2%, while each differs from the Californian reference genome by 1.5%. The researchers say the comparison matters because a Californian genome may not adequately represent southern-hemisphere kelp.
Google says its tools, including DeepConsensus and DeepPolisher, helped correct errors in raw long-read DNA data used to assemble the Australian genomes. The later DeepVariant analysis is a separate step: it compares genetic variation across samples against a reference. Researchers can then combine genetic information with laboratory test results to choose parent plants for breeding. AI does not itself measure heat tolerance; lab tests provide that evidence.
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
Can Selective Breeding Aid Recovery?
The research could give restoration teams a better basis for choosing which surviving kelp to breed. If samples from isolated patches contain useful genetic variation, crossing plants from different groups may help produce young kelp better suited to changing conditions. That is a research goal, not a demonstrated outcome: the announcement does not establish that the selected plants will tolerate higher temperatures or survive once placed on reefs.
The stakes extend beyond the seaweed itself. Giant kelp forests provide habitat and nursery areas for marine life, including fish, octopuses and sea stars. CSIRO has described the forest-forming kelp as supporting an ecosystem that disappears when the forests are lost. Tasmania is also a particularly exposed setting: the source material says the East Australian Current has pushed farther south, carrying warmer, nutrient-poor water and sea urchins into the region, while warming in the Tasman Sea is twice the global average.
For readers following AI in environmental science, the project shows a narrower, more testable role than claims that artificial intelligence can restore an ecosystem on its own. Here, the tools assist genome assembly and DNA analysis. The outcome still depends on breeding decisions, field trials, marine conditions and whether young kelp can persist through warm summers.
Products Worth Considering
DJI Osmo Mobile 8 3-Axis Phone Gimbal Stabilizer
Bose QuietComfort Wireless Noise-Cancelling Headphones, White Smoke
Amazon Kindle Paperwhite (12th Generation, 2024), 16GB, 7-Inch Display, Raspberry
As an affiliate, we earn on qualifying purchases.
From Reference Genomes to Reef Trials
In February 2024, Google Australia announced a wider partnership with CSIRO, 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 project had two strands: mapping kelp and studying its genetics. The mapping work was planned to use Google Earth Engine and Vertex AI to search more than 7,000 square kilometres of satellite imagery. Google’s latest announcement focuses on the genomics strand.
Until the Australian reference genomes were assembled, researchers had a Californian giant kelp genome to use as their main point of comparison. The June 2026 paper reports that the genetic difference between the Australian and Californian genomes is 1.5%, compared with 0.2% between the two Australian genomes. It places 98% to 99% of each Australian genome into 35 pseudo-chromosomes. The authors argue that locally relevant references are needed to study Australian kelp accurately.
Giant kelp, Macrocystis pyrifera, grows in cold, shallow seas. CSIRO says plants in Tasmanian waters can reach about 30 metres. The source material reports a 95% decline in forests around Tasmania; a cited preprint gives an estimate of 95% to 98% loss of giant kelp cover in eastern Tasmania since 1940. The preprint’s estimate draws on earlier research, while the two reference genomes have appeared in a peer-reviewed journal.
“We trained a version of our AI model DeepVariant to analyze our wild samples.”
— Google, in a video accompanying its November 12, 2026 announcement
The Field Test Is Still Ahead
The main open question is whether kelp selected and bred using these genetic analyses can survive warmer summers in Tasmanian waters. The supplied material says the researchers plan to cross distinct native survivors in the lab and plant young kelp on reefs, but it does not report completed field trials or survival results.
There is also a gap between the published genome research and the newer claim about 600 specimens. The two reference genomes and their comparisons are described in a peer-reviewed BMC Genomics paper. The 600-sample analysis and the claim that remaining kelp patches are genetically isolated are described in Google’s post and video; the source material reports no associated paper or dataset yet. The methods, detailed findings and evidence behind the isolation claim therefore remain to be assessed independently.
The project’s mapping strand is not detailed in this announcement, and the source material does not say whether its planned satellite analysis has produced a public map or a final estimate of remaining forest area. Nor does it establish how much of the decline can be reversed through breeding while warming, nutrient-poor water and sea urchins continue to affect the ecosystem.
Breeding and Reef Survival Tests
According to the project description, scientists plan to cross selected native kelp in laboratory breeding work, using distinct surviving plants. This is selective breeding, not genetic modification. The young kelp are then intended for planting on reefs, where researchers can test whether they establish and persist under real marine conditions.
The next useful evidence will include a detailed account of the 600-sample analysis, its methods and data, along with results from laboratory tests and reef trials. Those results would help show whether genetic differences identified by the software correspond to traits relevant to survival. Until field tests report how the bred kelp fares through warm seasons, the research remains a possible tool for recovery rather than evidence that the forests are returning.
Key Questions
What did the AI do in the giant kelp project?
Google says a version of DeepVariant adapted for kelp DNA analyzed 600 wild specimens from 40 Tasmanian coastal sites. Other Google tools helped correct sequencing errors while researchers assembled two Australian reference genomes. The AI analyzes DNA data; it does not plant kelp or directly measure heat tolerance.
Has the 600-sample analysis been peer reviewed?
The source material identifies Google’s November 12, 2026 post and video as the basis for the 600-sample analysis and its claim that surviving patches are genetically isolated. It says no paper or dataset for those findings had been identified. The two Australian reference genomes, a related but separate research result, were published in BMC Genomics in June 2026.
Does the project genetically modify kelp?
No. The planned next step is selective breeding: crossing distinct native survivor plants in a laboratory, then planting young kelp on reefs. The source material describes no genetic modification.
Why does Tasmania need local reference genomes?
The June 2026 paper reports that the two Australian genomes differ from each other by 0.2%, while they differ from the Californian reference genome by 1.5%. A local reference may give researchers a more suitable basis for studying genetic variation in Australian kelp.
Has bred kelp been shown to survive warmer summers?
No field survival result is reported in the source material. Whether selected and bred kelp can withstand warmer summers and persist after planting on reefs remains an open question.
Source: ThorstenMeyerAI.com
