🔍 Read the full analysis: What Google And CSIRO Have Shown About AI And Tasmania’s Giant Kelp on ThorstenMeyerAI.com
Get business pricing on tech for your team
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
Google says it and CSIRO used a kelp-trained version of DeepVariant to analyze DNA from 600 wild giant kelp samples collected at 40 Tasmanian coastal sites. Two Australian reference genomes have been published in a peer-reviewed journal, but the larger sample analysis and reported genetic isolation have so far been described in Google’s announcement; whether selectively bred kelp can withstand warmer seas remains untested.
Google says it worked with Australia’s national science agency, CSIRO, to use a kelp-trained DNA analysis model on 600 wild giant kelp samples from Tasmania, with the aim of identifying survivors for selective breeding. The work addresses the decline of Tasmania’s giant kelp forests, but the 600-sample findings have so far been described in Google’s announcement, and the bred kelp’s ability to survive warmer seas has not yet been tested in the ocean.
In a post published November 12, Google described researchers using a version of its DeepVariant tool, retrained for kelp DNA, to analyze 600 specimens collected from 40 sites along Tasmania’s coast. Google said the analysis found that remaining kelp patches are genetically isolated. The company’s post and accompanying video are the cited sources for those details; the supplied source reports that no paper or dataset for this analysis was available at the time of writing.
A separate part of the project has been published in BMC Genomics. The June 2026 peer-reviewed paper reports two Australian giant kelp reference genomes, assembled from plants collected in Victoria and Tasmania. The genomes differ from each other by 0.2% and from the Californian reference genome by 1.5%. The paper’s authors include CSIRO scientists and a Google researcher, and the data is public.
Google says its tools, including DeepConsensus and DeepPolisher, helped correct errors in raw DNA sequencing reads used to build the references. The stated next stage is to cross genetically distinct native kelp in laboratory breeding, then plant young kelp on reefs. The work described is selective breeding, not genetic modification; it does not mean AI itself measures heat tolerance or restores kelp forests.
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
Can Selective Breeding Aid Kelp Recovery?
Tasmania’s giant kelp decline has consequences beyond the loss of a conspicuous seaweed. The forests provide habitat and nursery areas for marine life, and CSIRO says the wider ecosystem depends on them. The source material reports that kelp populations have fallen by 95% from historic numbers, while a preprint citing earlier research places the East Tasmanian loss in kelp cover at 95–98% since 1940. These figures use different descriptions and should not be treated as identical measurements.
The genomic work may help researchers choose parent plants with more genetic diversity, a potential resource for breeding kelp suited to changing conditions. A locally sourced reference genome also gives scientists a better basis for comparing Australian samples than relying only on a Californian genome. But neither the genome publication nor Google’s account of the sample analysis establishes that selected offspring will tolerate warmer water, or that breeding can reverse the environmental pressures contributing to the decline.
The practical importance is therefore both a research tool and a test still to come. If bred kelp survives in the field, it could support restoration efforts; if it does not, DNA analysis alone will not address warming, nutrient-poor water or sea urchin impacts.
Products Worth Considering
Apple Watch Series 11 GPS + Cellular, 46mm Jet Black Aluminum Case with Black Sport Band (M/L)
Bose QuietComfort True Wireless Earbuds with Active Noise Cancellation, Bluetooth 5.3, USB-C Charging, IPX4, Black
Samsung 32-Inch Odyssey G5 QHD 180Hz Gaming Monitor
As an affiliate, we earn on qualifying purchases.
From Kelp Mapping to DNA
The collaboration was announced in February 2024 by Google Australia, CSIRO and partners including 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 had two strands: mapping remaining kelp using satellite imagery and cloud-based tools, and studying kelp genetics. Google’s November 2026 post focuses on the genomics strand, not a newly reported outcome from the mapping effort.
Giant kelp, Macrocystis pyrifera, forms tall underwater forests in cold seas. In Tasmanian waters, plants can grow to around 30 metres, according to the source material. CSIRO attributes the local decline to warmer, nutrient-poor water and invading sea urchins, with the East Australian Current extending farther south. It also says warming in the Tasman Sea is occurring at twice the global average. The kelp forest is listed as an endangered marine community type.
Before the new Australian assemblies, researchers had a Californian reference genome to compare with other giant kelp. The published genome study says the genetic distance between Australian and Californian kelp makes a regional reference valuable. These reference genomes provide a framework for reading and comparing samples; they are not, by themselves, evidence that a particular plant is heat-resistant.
““trained a version of our AI model DeepVariant to analyze our wild samples””
— Google, in a video accompanying its November 12, 2026 announcement
The Field Test Is Still Ahead
The key open question is whether selectively bred kelp will survive warmer summers after it is planted on reefs. The source material says that test has not yet happened. Google’s announcement also does not, on the information provided, establish how the reported genetic isolation was measured, whether the analysis has been independently evaluated, or how researchers will select plants for breeding.
The two Australian reference genomes are documented in a peer-reviewed paper, but the reported analysis of 600 specimens is currently attributed to Google’s post and video. The reported 95% decline is likewise presented as a figure from Google, while the source material separately cites a preprint referencing earlier research for a 95–98% loss of East Tasmanian kelp cover since 1940. The precise methods, monitoring periods and comparison baselines behind those figures are not fully detailed here.
It also remains uncertain how much selective breeding could offset pressures from warming, nutrient-poor water and sea urchins. No restoration outcome or survival rate is reported.
Breeding and Reef Planting
According to the project description, researchers plan to use genetic information to cross distinct native survivors in the lab. They then intend to plant young kelp on reefs and assess how it performs. The next meaningful evidence will be published methods and results from the 600-sample analysis, followed by data on the bred kelp’s survival and growth under sea conditions.
Until those results are available, the work is best understood as an effort to develop genomic tools for choosing breeding stock, rather than a demonstrated recovery of Tasmania’s kelp forests. The timing, reef locations, scale of planting and criteria for judging success are not specified in the source material.
Key Questions
What did Google and CSIRO use AI to do?
Google says a version of DeepVariant, adapted for kelp DNA, was used to analyze 600 wild giant kelp specimens from 40 sites along Tasmania’s coast. The AI is described as a genomics analysis tool, not a system that plants kelp or directly measures heat tolerance.
What has been peer-reviewed?
A June 2026 paper in BMC Genomics reports two Australian giant kelp reference genomes. The source material says the 600-sample analysis and its reported finding of genetic isolation have been described in Google’s announcement, with no paper or dataset available there at the time.
Does the project genetically modify kelp?
No genetic modification is described. The planned approach is selective breeding: crossing distinct native survivors in a laboratory and then planting young kelp on reefs.
Has the kelp been shown to survive warmer summers?
No. The field test of whether bred kelp can withstand warmer summers has not yet happened, according to the supplied source material. No survival or restoration results are reported.
Why do Australian reference genomes matter?
The published study reports that the two Australian genomes differ from each other by 0.2%, while they differ from a Californian reference by 1.5%. A local reference can give researchers a more relevant basis for comparing Australian kelp DNA, but it does not by itself show which plants will tolerate heat.
Source: ThorstenMeyerAI.com
