🔍 Read the full analysis: Could AI Help Scientists Bring Back 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 build Australian giant kelp reference genomes and analyze DNA from 600 wild specimens. Researchers plan to use the genetic information to guide selective breeding, but the analysis has not yet been published in a paper or dataset, and survival of bred kelp in warmer seas remains untested.
Google said on November 12 that AI tools developed by the company have helped Australia’s national science agency, CSIRO, analyze giant kelp DNA, a step researchers hope will guide breeding of kelp suited to Tasmania’s warming waters. The work comes as giant kelp forests around Tasmania have declined by about 95%, according to CSIRO; whether selectively bred plants can withstand warmer summers in the ocean has not yet been tested.
The project uses genomics and machine-learning tools to help researchers compare wild kelp and identify genetic differences that could inform breeding. Google says a version of its DeepVariant tool, adapted from models trained on human DNA, was used to analyze 600 wild specimens collected at 40 sites along the Tasmanian coast. The company says the analysis found that remaining kelp patches are genetically isolated. That finding is described in Google’s announcement and video; the source account reported no paper or public dataset for the 600-sample analysis at the time of publication.
A separate part of the work is documented in a peer-reviewed BMC Genomics paper published in June 2026. CSIRO researchers and a Google researcher reported two Australian giant kelp reference genomes, built using long-read DNA sequencing and computational tools. The genomes are from specimens collected in Victoria and Tasmania. The researchers placed 98–99% of each genome into 35 pseudo-chromosomes, according to the paper’s abstract.
The study reported that the two Australian genomes differ from one another by 0.2% and from the Californian reference genome by 1.5%. Google says its DeepConsensus and DeepPolisher tools were used to correct errors in raw genetic reads. A locally relevant reference genome can help researchers compare Australian samples more accurately than relying only on a genome from a distant population, but the genome work alone does not show which kelp will survive future marine conditions.
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 Tool, Not a Sea Rescue
The proposed value of the AI is that it may help scientists identify genetic differences among surviving kelp and select parents for conventional selective breeding. That could support efforts to restore forests that provide habitat and nursery areas for marine life, including fish, octopuses and sea stars. It is a research aid: the software analyzes sequence data and does not plant kelp, test heat tolerance by itself or restore a reef.
The ecological challenge is unusually difficult because the pressures described by CSIRO include warmer, nutrient-poor water and expanding sea urchin populations. CSIRO links these pressures to the East Australian Current moving farther south and says warming in the Tasman Sea is occurring at twice the global average. Identifying genetic variation could help guide experiments, but it cannot by itself resolve those environmental pressures or establish that bred kelp will persist at sea.
For readers, the distinction matters: the project is a potential contribution to restoration science, not evidence that the forests have recovered or that AI has solved the problem. The key measure of progress will be whether bred young kelp can establish and survive through warm summers in the marine environment.
Popular right now
Vitamix 5200 Blender with 64 oz Container, Black
Dyson V8 Motorhead Origin Cordless Vacuum
eufy C28 Robot Vacuum and Mop for Pet Hair, 15,000 Pa
As an affiliate, we earn on qualifying purchases.
From Genome Maps to Reef Trials
Giant kelp, Macrocystis pyrifera, is a brown seaweed that forms underwater forests in cold, shallow seas. Around Tasmania, plants grow to about 30 metres, according to the source account, while CSIRO says the species can grow much taller in some settings. The forests support a broader marine community. CSIRO has described the giant kelp forest as an endangered marine community type and says there is little room for the species to move farther south.
In February 2024, Google Australia announced a 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 initiative included mapping remaining kelp using satellite imagery as well as a genomics strand. Google’s November 2026 account focuses on the genomic work, not a reported result from the satellite-mapping effort.
Before the 2026 study, the available giant kelp reference genome came from a Californian specimen. The peer-reviewed study’s comparison found greater genetic distance between the Californian and Australian genomes than between the two Australian ones. The researchers made the Australian reference data public, according to the source account. That published genome work should be distinguished from Google’s separate account of the 600 wild samples, whose results were not accompanied by a paper or dataset in the material provided.
““Without Giant Kelp to form the forests, the entire ecosystem disappears.””
— CSIRO
The Ocean Test Has Not Happened
The central open question is whether kelp selected through breeding will survive warmer summers and establish on reefs. The source material says researchers plan to cross distinct native survivors in a lab and plant young kelp, but it provides no results from sea trials or a timeline for them.
The status of the 600-specimen analysis is also less clear than that of the reference genomes. The sample count, collection sites and finding of genetic isolation are reported in Google’s blog post and video. The source account found no accompanying paper or dataset, so the methods, full results and independent assessment of that finding remain unavailable in the supplied material. It is also unclear how the project’s separate satellite-mapping strand has progressed.
The genetic comparisons in the published paper establish differences between the sampled genomes; they do not, on their own, show that a particular variant causes heat tolerance or that breeding will produce kelp able to withstand future conditions. No evidence provided here establishes that restoration has begun at scale or that the kelp forests are recovering.
Breeding and Reef Monitoring
Researchers’ stated next step is to cross genetically distinct native kelp in the lab through selective breeding, then plant young kelp on reefs. The approach described is not genetic modification. The source material does not give a schedule, planting locations or a confirmed monitoring plan, so those details should not be treated as settled.
Future evidence will need to show how the bred kelp performs in the sea, especially through warm summers, and whether plants persist and help rebuild forest habitat. Publication of the 600-sample analysis and data, if made available, would also allow researchers outside the project to examine how the findings were reached. Until those steps are reported, the work is best understood as an effort to improve the information available for breeding—not proof that restoration will succeed.
Key Questions
What is AI doing in the Tasmanian kelp project?
Google says adapted AI tools helped process kelp DNA and analyze samples from 600 wild specimens. The tools assist with genetic analysis; they do not plant kelp or independently determine whether a plant can tolerate heat.
Has the AI analysis of the 600 specimens been peer reviewed?
Not according to the source material. The 600-sample findings were described in Google’s announcement and video, and the source account reported no paper or dataset for that analysis. A separate study of two Australian reference genomes was published in BMC Genomics in June 2026.
Does the project genetically modify kelp?
The planned approach described is selective breeding: crossing distinct native survivors in a lab. The source material says this is not genetic modification.
Why are Australian reference genomes useful?
They give researchers a local comparison point for Australian kelp DNA. The 2026 study reported that the two Australian genomes differed from each other by 0.2%, while each differed from the Californian reference by 1.5% in the reported comparison.
Has bred kelp been shown to survive warmer Tasmanian seas?
No such result is reported in the source material. Researchers plan to plant young kelp on reefs, but whether it survives warm summers remains untested and unclear.
Source: ThorstenMeyerAI.com
