🔍 Read the full analysis: AI And Giant Kelp: What Google And CSIRO’s Tasmania Work Reveals on ThorstenMeyerAI.com
Get hardware and tech essentials 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 version of Google’s DeepVariant tool, adapted for giant kelp DNA, to analyse 600 wild specimens from 40 Tasmanian coastal sites. The work is intended to help scientists select kelp for laboratory breeding; whether the resulting kelp can survive warmer summers at sea has not yet been established.
Google says its researchers and Australia’s national science agency, CSIRO, used a version of Google’s DeepVariant AI tool adapted for kelp DNA to analyse 600 wild giant kelp specimens collected from 40 sites along Tasmania’s coast. The analysis is intended to help identify plants for selective breeding as scientists seek to restore kelp forests that have sharply declined, but the reported genetic work does not show whether bred kelp will withstand warmer summers at sea.
In a post and video published on November 12, Google described using its AI tools alongside genomics to study giant kelp, a large brown seaweed that forms underwater forests. The company says the researchers trained a version of DeepVariant, whose standard models are trained on human data, to analyse kelp samples. Google reports that the 600 specimens came from 40 locations along the Tasmanian coast.
Google says its analysis found that the surviving Tasmanian kelp patches are genetically isolated. That result and the 600-specimen analysis are described in Google’s announcement and video; the source material reports that no paper or dataset documenting those findings was available at publication. They should not be confused with the separate genome study that has been published in a peer-reviewed journal.
For that study, CSIRO scientists and collaborators produced two Australian giant-kelp reference genomes, using specimens from Victoria and Tasmania. The paper appeared in BMC Genomics in June 2026, and its data are public. It reports that the Australian genomes differ from each other by 0.2% and from the Californian reference genome by 1.5%. Google says its DeepConsensus and DeepPolisher tools helped correct errors in raw genetic reads used in assembling the genomes.
The proposed next step is selective breeding in a laboratory: scientists plan to cross distinct native survivors and later plant young kelp on reefs. This is not genetic modification, and the AI is not planting kelp or directly testing heat tolerance. Laboratory tests provide the traits researchers can compare with genetic data; the goal is to use that information to guide breeding choices.
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
From DNA Analysis to Reef Restoration
The project addresses a severe ecological decline, while also illustrating the limits of what AI has shown so far. CSIRO says Tasmanian giant kelp populations have declined by 95%, with warmer, nutrient-poor water and invading sea urchins among the pressures. The source material also cites earlier research estimating a 95–98% loss of giant-kelp cover in eastern Tasmania since 1940. Those figures refer to different descriptions of the decline and should not be treated as the same measurement.
Giant-kelp forests provide habitat and nursery grounds for marine life, including fish and invertebrates. Their loss affects an ecosystem, not just one seaweed species. A local reference genome can also improve comparisons: the published study’s reported genetic difference between Australian and Californian kelp suggests that a Californian genome alone may not represent southern populations well.
Still, identifying genetic variation is an early step, not proof of restoration. The practical test is whether selected kelp can grow and persist under local ocean conditions, including warmer summers. The announcement describes a potential tool for choosing breeding stock; it does not establish that the approach has restored forests or will reverse the pressures that contributed to their decline.
Products Worth Considering
LG UltraGear evo 52-Inch 5K2K 240Hz Curved Gaming Monitor
Ledger Nano X Bluetooth Crypto Wallet
Apple MacBook Air 13-inch Laptop with M5 Chip, 16GB Memory, 512GB SSD, Liquid Retina Display, and 12MP Center Stage Camera (2026, Silver)
As an affiliate, we earn on qualifying purchases.
Why Australian Reference Genomes Matter
The collaboration began as a broader effort announced in February 2024 by Google Australia, 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. Its two strands included mapping kelp and studying its genetics. The November announcement focuses on the genomics work, rather than reporting a new result from the mapping strand.
For the mapping strand, partners planned to use Google Earth Engine and Vertex AI to search more than 7,000 square kilometres of satellite imagery for remaining kelp. The source material does not give an update on the status or results of that mapping effort. The genetics work first required reference genomes: assembled DNA sequences that let researchers compare individual plants. Before the two Australian genomes were published, the reference available for giant kelp came from a Californian specimen.
CSIRO describes Tasmanian giant kelp as growing to about 30 metres in local shallow waters. The agency attributes the decline to a combination of warming, nutrient-poor water associated with the East Australian Current pushing farther south, and sea urchins. It says warming in the Tasman Sea is occurring at twice the global average. Giant-kelp forest is listed as an endangered marine community type, according to the source material.
““trained a version of our AI model DeepVariant to analyze our wild samples””
— Google video accompanying the November 12 announcement
The Unproven Test at Sea
The 600-specimen analysis and Google’s finding that remaining Tasmanian patches are genetically isolated are reported in the company’s post and video. The source material says no paper or dataset for those results was available when it was prepared, so the methods, detailed results and independent scrutiny of that analysis remain unclear.
It is also not yet clear which kelp traits will be selected for breeding, how many crosses are planned, when young kelp will be planted, or where reef trials will take place. Most important, there is no reported evidence yet that selectively bred kelp survives warmer summers or restores a forest in the ocean. The published reference-genome paper supports the genomic groundwork, but it does not establish the success of later breeding or restoration.
Breeding and Reef Trials Ahead
According to the project description, scientists plan to use genetic information and laboratory tests to choose distinct native survivors for selective crosses. The resulting young kelp are intended for planting on reefs. The source material gives no confirmed timetable for those plantings or for reporting trial results.
The next evidence to watch for is a published account of the 600-sample analysis, details of the breeding and the traits being tested, and results from any reef plantings. Those reports would help show whether the approach can produce kelp that persists in warmer conditions. Until such results are available, the work is best understood as a research effort to guide breeding, not a demonstrated restoration outcome.
Key Questions
What did Google and CSIRO use AI to do?
Google says a version of its DeepVariant tool, adapted for kelp DNA, analysed 600 wild giant-kelp specimens from 40 Tasmanian coastal sites. The analysis is intended to inform selective breeding; it does not itself plant kelp or test survival in the ocean.
Has the 600-specimen result been peer reviewed?
The source material reports the analysis and the claim of genetic isolation in Google’s post and video, and says no paper or dataset documenting those results was available. A separate study reporting two Australian reference genomes was published in BMC Genomics in June 2026.
Are the scientists genetically modifying the kelp?
No. The planned approach is described as selective breeding: crossing distinct native kelp survivors in a laboratory. The source material does not describe genetic modification.
Will the bred kelp survive warmer summers?
That has not been established. Researchers plan to plant young kelp on reefs, but the source material reports no sea-trial results showing whether selected kelp can withstand warmer summers.
How much have Tasmania’s kelp forests declined?
CSIRO says giant-kelp populations have declined by 95%. The source material also cites earlier research estimating a 95–98% loss of kelp cover in eastern Tasmania since 1940; these are differently described figures.
Source: ThorstenMeyerAI.com
