🔍 Read the full analysis: Can AI Help Bring Tasmania’s Giant Kelp Forests Back? on ThorstenMeyerAI.com
Get the little things that make your day 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 AI tools and genomics are helping CSIRO identify genetic variation in wild giant kelp around Tasmania, with the aim of selecting plants for lab-based selective breeding. Two Australian reference genomes are published in a peer-reviewed journal; the reported analysis of 600 wild specimens and genetic isolation finding have not yet been documented in a paper or dataset cited in the announcement. Whether bred kelp can survive warmer summers at sea remains unknown.
Google and Australia’s CSIRO say AI-assisted DNA analysis is being used to help identify giant kelp plants that could be bred for restoration off Tasmania, where kelp forests have declined sharply. The work is a research step, not a demonstration that AI can restore the forests: whether selectively bred kelp can withstand warmer conditions in the ocean has not yet been tested.
In a post and video published on November 12, Google described a genomics project in which researchers used a version of its DeepVariant tool, trained to analyse kelp DNA, on 600 wild specimens collected from 40 sites along Tasmania’s coast. Google says the analysis found that remaining kelp patches are genetically isolated. The company’s announcement is the source for those details; the supplied reporting found no paper or dataset documenting the 600-sample analysis or that finding.
The work builds on two Australian giant kelp reference genomes created by CSIRO researchers with Google tools. A reference genome provides a standard for comparing DNA from other plants. The genomes, from specimens collected in Victoria and Tasmania, were published in June 2026 in the peer-reviewed journal BMC Genomics; the data is public. The paper reports that the two Australian genomes differ from each other by 0.2% and from a Californian reference genome by 1.5%.
Google says DeepConsensus and DeepPolisher helped correct errors in raw sequencing reads, while DeepVariant was adapted from models trained on human data to analyse kelp. The intended next use is to help researchers select and cross genetically distinct native plants in the lab. The method described is selective breeding, not genetic modification; planting young kelp on reefs is planned, but the supplied account gives no results from such restoration trials.
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
A Breeding Strategy for Kelp
Tasmania’s giant kelp forests provide habitat and nursery areas for marine life, including fish, octopuses, sea stars and sea lions. CSIRO says the kelp community has declined by 95% in recent decades, while a preprint citing earlier research puts the loss of East Tasmanian kelp cover at 95% to 98% since 1940. The loss affects more than one seaweed species: it threatens an underwater ecosystem built around the forest.
The genomic approach could help researchers identify and breed plants with useful genetic differences, rather than relying on a single source population. But DNA analysis is only one part of the restoration challenge. The researchers still need to establish whether selected kelp grows and persists in the conditions that contributed to the decline. Laboratory selection cannot by itself show survival through warmer summers in the sea.
Products Worth Considering
Therabody JetBoots Prime Wireless Compression Boots, Regular, 30–34 in Inseam
Oral-B iO Series 3 Rechargeable Electric Toothbrush for Adults, Black, with 2 Brush Heads and Travel Case
Garmin Forerunner 570 GPS Running Smartwatch, 42 mm, Aluminum, Bone/Mango
As an affiliate, we earn on qualifying purchases.
Why Local Genomes Matter
Giant kelp, Macrocystis pyrifera, grows in cold, shallow waters. CSIRO says plants in Tasmanian waters can reach around 30 metres, and individual plants can grow rapidly under suitable conditions. The remaining forests are under pressure from warmer, nutrient-poor water and sea urchins, according to CSIRO, as the East Australian Current extends farther south. CSIRO also says warming in the Tasman Sea is occurring at twice the global average.
Before the Australian genomes were published, the available reference genome came from a Californian specimen. The researchers’ paper reports a larger genetic difference between that genome and the Australian samples than between the two Australian genomes. That makes a local reference useful for comparisons of Australian kelp: relying only on the Californian genome could give researchers a less accurate picture of variation in southern populations.
The broader project was announced in February 2024 by Google Australia and partners including 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. It included a mapping strand using satellite imagery as well as genomics. The November announcement focuses on the genomic work, not a confirmed finding from the earlier mapping plan.
“trained a version of our AI model DeepVariant to analyze our wild samples”
— Google, in the November 12 announcement video
The Field Test Is Pending
The key ecological result remains unproven: the supplied source material reports no field test showing that bred kelp survives warmer summers. It is also not yet clear how many plants will be selected and crossed, when young kelp will be planted on reefs, or what measures researchers will use to judge whether restoration is working.
The two Australian reference genomes are supported by a peer-reviewed paper and public data. By contrast, the account of the 600 wild specimens and the conclusion that surviving Tasmanian patches are genetically isolated come from Google’s announcement and video. The supplied reporting found no paper or dataset for those findings yet. The announcement does not establish how much of the reported genetic variation corresponds to heat tolerance or other traits needed for recovery.
From Lab Crosses to Reefs
Researchers plan to cross genetically distinct native survivors in laboratory breeding work, then plant young kelp on reefs. The next evidence readers should look for is a published account of the 600-specimen analysis, details of the breeding and planting programme, and results from monitoring kelp after it is returned to the sea.
Those steps will show whether the genomic findings can guide practical restoration and whether selected plants persist through warm conditions. For now, the project offers a way to investigate and choose among remaining kelp populations; it does not yet show that the forests can be brought back.
Key Questions
What is the AI doing in the kelp project?
Google says a version of its DeepVariant tool was trained to analyse kelp DNA from wild specimens. The analysis is intended to help researchers compare plants and inform selective breeding; the AI does not plant kelp or directly test whether it tolerates heat.
Has the AI analysis of 600 kelp specimens been peer-reviewed?
The supplied reporting found no paper or dataset documenting the 600-specimen analysis or the reported genetic isolation finding. Those details appear in Google’s November 12 announcement and video. The two Australian reference genomes, a separate part of the work, were published in BMC Genomics.
Are the researchers genetically modifying the kelp?
No genetic modification is described in the source material. The planned approach is selective breeding: crossing native kelp with different genetic profiles in a laboratory.
Why are Australian reference genomes useful?
The published genomes give researchers a local baseline for comparing Australian kelp DNA. The paper reports that the Australian samples differ from the Californian reference by 1.5%, compared with a 0.2% difference between the two Australian genomes.
Is the project known to have restored Tasmania’s kelp forests?
No. The announcement describes genomic research and planned breeding and planting, but provides no results showing that bred kelp has survived on reefs or restored forests. Field survival in warmer seas remains an open question.
Source: ThorstenMeyerAI.com
