🔍 Read the full analysis: 3 Things To Know About AI And Tasmania’s Giant Kelp 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 said on November 12 that AI and genomics are helping CSIRO identify genetic differences among surviving Tasmanian giant kelp, with the aim of guiding selective breeding. Two Australian reference genomes have been published in a peer-reviewed journal, but the reported analysis of 600 wild kelp has not yet been backed by a published paper or dataset, and survival in warmer seas remains untested.
Google said on November 12 that its AI tools are helping Australia’s national science agency, CSIRO, analyze giant kelp DNA to guide efforts to breed plants suited to Tasmania’s changing waters. The announcement describes an analysis of 600 wild specimens, but that result has not yet been presented in a paper or dataset identified in the source material; whether selectively bred kelp will survive warmer summers at sea remains untested.
The work addresses a sharp decline in giant kelp forests around Tasmania. CSIRO says the forests have fallen by 95%, while earlier research cited in a genome study puts the decline in East Tasmania at 95% to 98% since 1940. CSIRO attributes the loss to warmer, nutrient-poor water and sea urchins moving south as the East Australian Current extends further south. The kelp forms habitat for marine life, and CSIRO says the forest ecosystem disappears without it.
The AI is one part of a longer scientific process, not a tool that plants kelp or independently measures heat tolerance. Researchers first need DNA reference genomes, then compare DNA variation in wild plants with laboratory test results. Google says its tools helped produce two Australian reference genomes and that a version of its DeepVariant software, retrained for kelp DNA, was used to analyze samples from 40 sites along Tasmania’s coast. The aim is to help researchers select distinct native survivors for crossing.
The reference-genome work is the part independently documented in a June 2026 peer-reviewed paper in BMC Genomics, co-authored by CSIRO scientists and a Google researcher, with public data. It reports that the two Australian genomes differ from one another by 0.2%, while each differs from the Californian reference by 1.5%. The larger difference supports the case for using Australian references when studying Australian kelp. Google’s account of the 600-sample analysis and genetic isolation among remaining patches, by contrast, is so far based on its blog post and video.
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
Why Local Kelp DNA Matters
For conservation, the project’s immediate value is better information about the kelp that remains, not a demonstrated way to restore forests. A reference genome from a local plant can give researchers a more appropriate comparison point than one from California, since the published study found a larger genetic difference between Australian and Californian kelp than between the two Australian samples. That can matter when researchers look for variation to guide breeding.
If the reported finding that surviving Tasmanian patches are genetically isolated is borne out, it could affect how conservation teams choose parent plants and exchange material among sites. But the source does not establish that the AI has identified heat-tolerant kelp, nor that breeding will produce plants able to withstand future conditions. The practical test is whether young kelp grown from selected native survivors can establish and persist on reefs through warmer summers.
The stakes extend beyond a single seaweed. Giant kelp forests provide habitat and nursery areas for marine species. CSIRO says the community is listed as an endangered marine community type, and describes Tasmania’s waters as the last place for the kelp to retreat before Antarctica. That framing comes from CSIRO; the project’s outcome will depend on field results, not the announcement alone.
Products Worth Considering
Jackery Solar Generator 1000 v2 with Two 100W Solar Panels, 1024Wh LiFePO4 Battery
Apple iPad 11-inch (A16), 128GB, Wi-Fi, Silver
Amazon Kindle Scribe Colorsoft 64GB with 11-Inch Color Display and Premium Pen, Graphite
As an affiliate, we earn on qualifying purchases.
From Genome Maps to Reef Trials
Google Australia and CSIRO announced the 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. The project had two strands: using satellite imagery to map remaining kelp and using genomics to study the plants. The November 2026 announcement concerns the genomics strand. The original mapping plan involved Google Earth Engine and Vertex AI, with more than 7,000 square kilometres of imagery in scope; the source does not report a completed mapping result.
Before the new Australian genomes, researchers had relied on a reference from a Californian giant kelp specimen. The peer-reviewed study reports that scientists sequenced one plant from Victoria and one from Tasmania. It placed 98% to 99% of each genome into 35 pseudo-chromosomes, with genome sizes of 528 to 534 million base pairs. Google says DeepConsensus and DeepPolisher helped correct errors in raw genetic reads. Those tools support the sequencing work; the separate DeepVariant model was adapted for the reported analysis of wild specimens.
The next step described is selective breeding: crossing distinct native survivors in a laboratory and raising young kelp for planting on reefs. This is not genetic modification, according to the source material. The distinction matters: the project uses genomic analysis to inform which plants scientists breed, rather than editing their DNA. Neither the genome paper nor the announcement establishes that the resulting kelp has passed a real-world heat-survival test.
“trained a version of our AI model DeepVariant to analyze our wild samples”
— Google, in a video accompanying its November 12 announcement
The Missing Field-Survival Evidence
Several claims in Google’s November announcement are not yet supported by the published evidence described in the source material. These include the analysis of 600 wild specimens from 40 sites and the finding that remaining Tasmanian patches are genetically isolated. No paper or dataset for those results was identified, so their methods and findings cannot yet be checked against a published record.
It is also not clear which specific genetic traits, if any, are linked to tolerance of warmer water. The source says laboratory tests measure relevant responses and DNA data are linked to those tests, but it does not provide test results, identify a validated heat-tolerance marker or report survival outcomes from reef plantings. The peer-reviewed genome study establishes reference genomes and genetic differences; it does not establish that AI-selected kelp will thrive in the wild.
Breeding and Testing on Reefs
According to the project description, researchers plan to cross distinct native survivor plants in the laboratory, raise young kelp and plant them on reefs. The key next evidence will be whether those plants establish and survive through warmer summer conditions, and how their performance compares with other kelp. The source material does not give a planting date, trial locations, sample sizes or a timetable for results.
A published paper or released dataset detailing the 600-specimen analysis would also allow others to examine the reported genetic isolation and how the AI model was adapted and evaluated. Until those results and field trials are available, the work is best understood as a genomics-led breeding effort with a documented reference-genome foundation—not a proven restoration method.
Key Questions
What is AI being used for in the Tasmanian kelp project?
Google says an adapted version of its DeepVariant model was used to analyze the DNA of wild giant kelp. The intended role is to help researchers understand genetic differences and inform which native plants to cross; the AI does not plant kelp or itself establish that a plant can tolerate heat.
Has the AI analysis of 600 kelp specimens been published?
Not in the material available for this report. Google described the analysis in a November 12, 2026, blog post and video, but no paper or dataset documenting those results was identified.
What has been peer-reviewed?
A June 2026 paper in BMC Genomics reports two Australian giant kelp reference genomes. It found a 0.2% difference between the Australian genomes and a 1.5% difference between them and the Californian reference.
Is the project genetically modifying kelp?
No. The planned approach described in the source is selective breeding: crossing distinct native survivor plants in a laboratory. The source does not describe genetic modification.
Will the bred kelp survive warmer summers?
That remains unknown. The decisive test—whether young kelp planted on reefs can establish and persist through warmer summers—has not yet happened, according to the source material.
Source: ThorstenMeyerAI.com
