🔍 Read the full analysis: What We’re Learning About AI And Giant Kelp In Tasmania on ThorstenMeyerAI.com
Get business pricing on monitors, keyboards and dev gear
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
Google says its AI tools helped CSIRO researchers build Australian giant-kelp reference genomes and analyze 600 wild specimens from Tasmania. The findings about genetic isolation have so far been described in Google’s announcement, not a published paper or dataset; whether selectively bred kelp can survive warmer summers remains unknown.
Google says AI tools helped Australia’s national science agency, CSIRO, analyze DNA from 600 wild giant-kelp specimens collected at 40 sites along Tasmania’s coast, in research intended to inform selective breeding as the underwater forests decline. The company’s November 12 account says the remaining kelp patches are genetically isolated, but that result has not yet been presented in a research paper or dataset identified in the source material; whether bred kelp can withstand warmer seas remains untested.
The project does not use AI to grow kelp, plant it or directly test its heat tolerance. Google says researchers used a version of its DeepVariant software, adapted from models trained on human DNA, to analyze kelp genetic data. Laboratory tests assess traits such as heat tolerance; scientists can then compare those results with genetic differences to help choose parent plants for breeding.
A related, independently accessible part of the work is the creation of two Australian giant-kelp reference genomes. The genomes, from plants collected in Victoria and Tasmania, were published in the peer-reviewed journal BMC Genomics in June 2026, with CSIRO scientists and a Google researcher among the authors. The study reports that the two Australian genomes differ by 0.2%, while each differs from the Californian reference by 1.5%.
Google says its tools DeepConsensus and DeepPolisher helped correct errors in raw long-read DNA data used to build the genomes. Those local references then provided a guide for examining wild samples. The announcement describes the 600-specimen analysis and genetic isolation finding, but the material provided does not identify a corresponding paper or public dataset.
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
Breeding Kelp for Warmer Seas
The work addresses a conservation problem with consequences beyond the kelp itself. Giant kelp forests create habitat and nursery areas for marine life, including fish, octopuses and sea stars. CSIRO says that when the forests disappear, the wider ecosystem is affected. The source material reports a 95% decline in Tasmanian giant-kelp populations, attributing that figure to CSIRO.
Genetic information could help researchers select surviving plants with traits suited to local conditions and cross them through selective breeding. That offers a possible route to restoration, not a demonstrated fix. A genetic marker or laboratory result cannot by itself establish that young kelp will persist through hot summers, changing currents and other pressures in the ocean.
The distinction matters for interpreting the announcement: the genome work is published research, while the claims about the 600 wild specimens and their isolation are, for now, reported by Google. The practical measure of success will be whether bred kelp establishes and survives on reefs.
Popular right now
Ninja Foodi 10-Qt DualZone XL Air Fryer, 6-in-1, Gray (DZ401)
Hisense 75-Inch U7 Mini-LED ULED 4K UHD Smart Google TV (75U7SG)
Dyson Supersonic Travel Hair Dryer
As an affiliate, we earn on qualifying purchases.
From Reference Genomes to Reef Trials
Giant kelp, Macrocystis pyrifera, is a large brown seaweed found in cold, shallow waters. Around Tasmania, individuals grow to about 30 metres, according to the source material. CSIRO has attributed the decline to warmer, nutrient-poor water and sea urchins moving south as the East Australian Current extends further toward Tasmania. The material also says warming in the Tasman Sea is occurring at twice the global average; that comparison is attributed to CSIRO.
Google Australia and CSIRO announced a broader partnership 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. Its two strands included satellite mapping of kelp and genomic research. The November 2026 account focuses on the genomic strand, rather than reporting a completed restoration.
Before the Australian genomes were available, researchers relied on a Californian giant-kelp reference. The 2026 study’s comparison—1.5% difference between Australian and Californian genomes, against 0.2% between the two Australian samples—shows why a regional reference may matter when analyzing Tasmanian plants. The study’s genome data is public, according to the source material.
““trained a version of our AI model DeepVariant to analyze our wild samples””
— Google, in a video accompanying its November 12, 2026 announcement
The 600-Sample Findings Await Publication
The genetic isolation result comes from Google’s blog post and video in the material provided. No paper or dataset documenting that analysis is identified there, so its methods, underlying data and interpretation cannot yet be checked against a published study. The peer-reviewed genome paper is a separate, documented part of the research.
It is also not yet clear which specific genetic differences correspond to heat tolerance, how much those traits vary among the sampled plants, or how researchers will weigh heat tolerance against other conditions kelp must withstand. The source material does not report that the bred kelp has been planted on reefs or survived a warm summer.
The decline figures describe different measures in the cited material: CSIRO’s 95% estimate for Tasmanian populations and a preprint’s cited estimate of 95–98% loss of East Tasmanian kelp cover since 1940. They should not be treated as identical measurements.
Selective Crosses and Reef Planting
Researchers plan to cross genetically distinct native survivors in the laboratory through selective breeding, then plant young kelp on reefs, according to the source material. This is breeding from naturally occurring variation, not genetic modification. The material does not give a confirmed planting date or a schedule for field trials.
The next evidence to watch for includes publication or release of the 600-specimen analysis, details on how lab measurements connect genetic variation with heat tolerance, and results from reef trials. The central test remains whether the young kelp can persist through warmer summers under real marine conditions.
Key Questions
What did Google say its AI did?
Google says a version of DeepVariant was adapted to analyze DNA from 600 wild giant-kelp specimens collected at 40 Tasmanian coastal sites. The company also says its tools helped researchers build Australian reference genomes.
Has the AI finding about genetic isolation been peer reviewed?
Not in the source material provided. The finding that remaining Tasmanian patches are genetically isolated is described in Google’s announcement; no paper or dataset for that analysis is identified. The two Australian reference genomes are documented in a separate peer-reviewed BMC Genomics study.
Does the project genetically modify kelp?
No. The stated plan is to cross native kelp through selective breeding, using naturally occurring variation. The source material does not describe genetic modification.
Will the bred kelp survive warmer summers?
That has not been established. Laboratory tests can assess traits such as heat tolerance, but the decisive test is whether the bred kelp survives after planting on reefs through warm summers.
Source: ThorstenMeyerAI.com
