🔍 Read the full analysis: What AI Can Tell Us About Tasmania’s Giant Kelp Comeback on ThorstenMeyerAI.com
Get the latest gadgets 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 a kelp-trained version of its DeepVariant tool was used to analyze DNA from 600 wild giant kelp specimens collected at 40 Tasmanian coastal sites. The work is intended to help scientists select native kelp for selective breeding; survival in warmer seas has not yet been demonstrated, and the 600-sample analysis has not been published in a paper or dataset identified in the source material.
Google said November 12 that a version of its DeepVariant AI tool, adapted to read kelp DNA, helped analyze 600 wild giant kelp specimens collected from 40 sites along Tasmania’s coast. The work is intended to guide selective breeding by scientists seeking to restore forests that have declined sharply, but the analysis has so far been described in Google’s announcement rather than a peer-reviewed paper, and the bred kelp has not yet been shown to survive warmer summers at sea.
The project addresses a severe decline in giant kelp forests around Tasmania. CSIRO estimates the forests have fallen by 95%, while a preprint cited in the source material reports a 95% to 98% loss of East Tasmanian kelp cover since 1940, based on earlier research. CSIRO attributes pressure on the forests to warmer, nutrient-poor water and invading sea urchins, with the East Australian Current extending farther south.
Google’s account says its researchers adapted DeepVariant, whose standard models are trained on human data, to analyze kelp specimens against newly assembled Australian reference genomes. Those references were built from plants collected in Victoria and Tasmania. A separate tool, DeepConsensus, and DeepPolisher were used to help correct errors in raw genetic reads, according to a video released with Google’s announcement. The AI analyzes genetic information; laboratory tests measure traits such as heat tolerance.
The reference genomes are documented in a peer-reviewed paper in BMC Genomics, published in June 2026, with CSIRO scientists and a Google researcher among the authors. The paper reports that the two Australian genomes differ from each other by 0.2%, while each differs from the Californian reference by 1.5%. The genomes and associated data are public. By contrast, Google’s reported analysis of 600 wild specimens and its conclusion that surviving Tasmanian patches are genetically isolated were not 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
Selecting Kelp for Warmer Reefs
Giant kelp forms underwater forests that provide habitat for marine life, including fish, octopuses, sea stars and sea lions. The loss of those forests affects more than the seaweed itself: the habitat and the species that depend on it are also at stake. CSIRO describes giant kelp forest as an endangered marine community type.
The genomic work could help scientists choose which surviving native plants to cross in a breeding program. A reference genome suited to Australian kelp matters because the peer-reviewed study found a larger difference between Australian and Californian genomes than between the two Australian samples. That supports using local genetic information when comparing Australian plants, rather than relying only on a Californian reference.
Still, genetic analysis is not evidence of successful restoration. The project does not use AI to plant kelp or directly establish that a specimen can tolerate future sea temperatures. Researchers must test candidate plants, breed them, and determine whether young kelp can establish and persist on reefs. The ecological stakes are high, but the outcome remains an open scientific question.
Products Worth Considering
Samsung 37-inch Odyssey G7 Curved 4K UHD Gaming Monitor (G75F)
Bose TV Speaker (2nd Gen) Compact Soundbar
Bose QuietComfort True Wireless Earbuds with Active Noise Cancellation, Bluetooth 5.3, USB-C Charging, IPX4, Black
As an affiliate, we earn on qualifying purchases.
From Genome References to Field Trials
The work is part of a collaboration 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. The initiative had two strands: mapping remaining kelp and studying its genetics. The latest Google account concerns the genomics strand.
For the mapping work, the partners planned to use Google Earth Engine and Vertex AI to search more than 7,000 square kilometres of satellite imagery for kelp. The genomic strand first needed reference genomes: assembled DNA sequences that researchers can use to compare individual samples. Before the Australian assemblies, the only giant kelp reference genome came from a Californian specimen.
The peer-reviewed Australian genome study reports that researchers used long-read sequencing and placed 98% to 99% of each genome into 35 pseudo-chromosomes. The genome sizes were estimated at 528 to 534 million base pairs. These results establish a resource for further research; they do not by themselves show which plants will withstand hotter conditions.
“trained a version of our AI model DeepVariant to analyze our wild samples”
— Google video accompanying the November 12 announcement
The Missing Test: Survival at Sea
The 600-specimen analysis and the claim that remaining patches are genetically isolated are reported by Google, but the source material identifies no published paper or dataset for those results. The peer-reviewed genome study supports the availability and comparison of Australian reference genomes; it should not be treated as independent confirmation of every claim in Google’s announcement.
It is also not yet clear which genetic differences will prove useful for breeding, how candidate kelp will perform under sustained heat stress, or whether young plants will establish on reefs. The stated next step is to cross distinct native survivors in a laboratory and plant young kelp on reefs. Whether those plants persist through warm summers is untested.
Breeding and Reef Planting Ahead
Scientists plan to use the genetic analysis to select distinct native survivors for selective breeding in the laboratory. The source describes this as breeding, not genetic modification. The resulting young kelp are then intended for planting on reefs, where researchers can assess whether they establish and survive.
The next evidence readers should look for includes a paper or public dataset describing the 600 specimens and their analysis, followed by results from laboratory breeding and reef trials. No timetable or specific release date for those results is given in the source material. Until field survival data are available, the project is best understood as an effort to identify breeding candidates, not a demonstrated kelp comeback.
Key Questions
What did the AI do?
Google says researchers adapted DeepVariant to analyze DNA from 600 wild giant kelp specimens gathered at 40 Tasmanian coastal sites. The tool helps researchers compare genetic data; laboratory tests, not the AI, assess traits such as heat tolerance.
Has the AI analysis been peer reviewed?
The two Australian reference genomes are described in a peer-reviewed BMC Genomics paper published in June 2026. The source material says the 600-specimen analysis and the finding about genetic isolation were reported in Google’s announcement, with no paper or dataset identified for them yet.
Does this mean kelp forests are recovering?
No recovery has been demonstrated in the material provided. Scientists plan to breed selected native kelp and plant young plants on reefs. Whether they survive warmer summers remains unknown.
Why were Australian reference genomes needed?
The peer-reviewed study found the two Australian genomes differed by 0.2%, compared with a 1.5% difference between Australian and Californian giant kelp. Local references give researchers a basis for comparing Australian specimens without relying only on a genome from a different region.
Source: ThorstenMeyerAI.com
