🔍 Read the full analysis: Can AI Play A Part In Restoring Tasmania’s Giant Kelp? on ThorstenMeyerAI.com
Get business pricing on office and shipping supplies
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
Google says it used a kelp-adapted version of its DeepVariant AI tool to analyze DNA from 600 wild giant kelp specimens collected at 40 Tasmanian coastal sites. The work is intended to help researchers choose native plants for selective breeding, but the analysis has not yet been published in a paper or dataset, and survival in warmer seas remains untested.
Google says researchers have used AI to analyze DNA from 600 wild giant kelp specimens collected along Tasmania’s coast, in work intended to help Australia’s national science agency, CSIRO, select plants for selective breeding. The effort addresses a severe decline in Tasmanian kelp forests, but the 600-specimen analysis has so far been described in Google’s November 12 announcement rather than a published research paper, and it has not yet shown whether bred kelp can survive warmer summers at sea.
According to Google, the specimens came from 40 sites along the Tasmanian coast. Researchers adapted a version of DeepVariant, Google’s AI tool for identifying genetic variants, to analyze kelp DNA. Google says the standard models are trained on human data, so the team retrained a version for this project using newly assembled Australian giant kelp reference genomes.
The AI does not measure heat tolerance on its own or restore kelp forests directly. The intended process is to compare genetic information with results from laboratory tests, then use that information to help choose native survivors for breeding. Scientists plan to cross selected kelp in the lab and plant young kelp on reefs. The work is described as selective breeding, not genetic modification.
There is a published foundation for part of the project. Two Australian giant kelp reference genomes, assembled from plants in Victoria and Tasmania, were reported in BMC Genomics in June 2026. The study involved CSIRO scientists and a Google researcher, and the data is public. It reports that the Australian genomes differ from one another by 0.2% and from the Californian reference genome by 1.5%. The separate analysis of 600 wild specimens, including Google’s reported finding that remaining Tasmanian patches are genetically isolated, has not yet been accompanied by a paper or dataset 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
A Breeding Strategy for Kelp
Tasmania’s giant kelp decline is not simply a loss of a large seaweed. Kelp forests provide habitat and nursery grounds for marine life, including fish, octopuses, sea stars and sea lions. CSIRO says the forests’ disappearance affects the wider ecosystem. The agency reports that giant kelp forests around Tasmania have declined by 95% in recent decades; an earlier research estimate cited in the genome study puts the loss of East Tasmanian kelp cover at 95% to 98% since 1940.
The project’s potential value is practical: a locally relevant genetic reference and analysis of wild plants could help researchers identify which survivors to cross, rather than relying on a Californian genome that differs more substantially from Australian kelp. But this is a research pathway, not evidence that AI has restored the forests. Field survival through warm summers is the test that would show whether the breeding approach can help under the conditions linked to the decline.
Popular right now
Ninja Foodi DZ201 8-Quart DualZone 6-in-1 Air Fryer
Dyson V15 Detect Cordless Vacuum
De’Longhi Classic Matte Black Espresso Machine with Milk Frother
As an affiliate, we earn on qualifying purchases.
From Genome Maps to Wild Samples
The project brings together Google, 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. Announced in February 2024, it included two strands: mapping kelp using satellite imagery and genomics. The current Google announcement concerns the genomics strand. The original mapping plan involved Google Earth Engine and Vertex AI to search more than 7,000 square kilometres of satellite imagery for remaining kelp.
Reference genomes give researchers a sequence against which they can compare DNA from other plants. Until the Australian genomes were assembled, the available giant kelp reference came from a Californian specimen. The 2026 study says the Australian kelp differs from that genome by 1.5%, compared with 0.2% between the two Australian samples, a difference relevant to interpreting genetic variation in local populations. Google also says its DeepConsensus and DeepPolisher tools helped correct errors in raw long-read sequencing data used to build the references.
CSIRO attributes the decline to warmer, nutrient-poor water and invading sea urchins, with the East Australian Current extending farther south. The source material says warming in the Tasman Sea is occurring at twice the global average. CSIRO describes giant kelp forest as an endangered marine community type and says there is little room for the species to retreat farther south.
“trained a version of our AI model DeepVariant to analyze our wild samples”
— Google, in a video accompanying its November 2026 announcement
The Field Test Is Pending
Several key details remain unsettled. The reported analysis of 600 specimens from 40 sites, and Google’s claim that surviving Tasmanian patches are genetically isolated, are currently supported in the source material by the company’s blog post and video. No associated scientific paper or dataset was identified there, so the analysis and its interpretation have not been independently assessed through a published study.
It is also unclear which specific genetic traits researchers will use to select breeding parents, how well those traits predict heat tolerance, or when young kelp will be planted on reefs. Laboratory tests can inform breeding decisions, but the decisive ecological question is whether the resulting kelp survives warmer summers and persists in the sea. The source material does not report that this test has taken place.
From Lab Crosses to Reef Trials
Researchers’ next stated steps are to cross distinct native survivors in the lab using selective breeding, raise young kelp and plant it on reefs. The published Australian reference genomes provide a basis for comparing local plants, while the 600-specimen analysis is intended to help identify genetic differences among wild survivors. The schedule for breeding and planting, and the locations or scale of any reef trials, have not been specified in the source material.
Future reporting will need to establish whether the specimen analysis is published with supporting data, what traits the team selects for, and how planted kelp performs over time. Until results from sea trials are available, the project should be understood as an effort to inform restoration—not proof that AI-guided breeding can reverse Tasmania’s kelp decline.
Key Questions
What is AI doing in the Tasmanian kelp project?
Google says a kelp-adapted version of DeepVariant analyzed DNA from 600 wild giant kelp specimens. The analysis is meant to help researchers compare plants and choose candidates for selective breeding; AI is not planting kelp or directly testing heat tolerance.
Has the AI analysis been peer reviewed?
The two Australian reference genomes were published in BMC Genomics in June 2026. The separate analysis of 600 wild specimens is described in Google’s November announcement, but the source material does not identify a related paper or dataset.
Are researchers genetically modifying the kelp?
No. The planned approach described in the source material is selective breeding: crossing distinct native survivors in the lab and raising young kelp for reef planting.
Why are Tasmanian kelp forests declining?
CSIRO cites warmer, nutrient-poor water and invading sea urchins, alongside the East Australian Current moving farther south. The agency reports that Tasmanian giant kelp forests have declined by 95% in recent decades.
Will the bred kelp survive warmer summers?
That remains unknown. The source material says the decisive test—whether bred kelp can survive warmer summers in the sea—has not yet happened.
Source: ThorstenMeyerAI.com
