🔍 Read the full analysis: Can AI Help Giant Kelp Return To Tasmania’s Waters? on ThorstenMeyerAI.com
Prime made for students and young adults
- Fast, free delivery for dorm and study essentials
- Prime Video and Amazon Music included
- Member-only deals
TL;DR
Google said on November 12 that AI and genomic tools are helping CSIRO study genetic variation in Tasmania’s remaining giant kelp. Two Australian reference genomes have been published in a peer-reviewed journal; the reported analysis of 600 wild samples and genetic isolation finding have not yet been independently documented in a paper or dataset. Scientists plan to selectively breed kelp, but whether it will withstand warm summers at sea is unknown.
Google said on November 12 that its AI and genomic tools are helping Australia’s national science agency, CSIRO, analyze wild giant kelp as researchers work toward breeding plants that could help restore Tasmania’s declining underwater forests. The effort combines a peer-reviewed set of Australian reference genomes with a further analysis of 600 wild specimens that Google has described but that has not yet been presented in a paper or dataset identified in the source material; whether selectively bred kelp can survive warmer seas remains untested.
According to Google’s announcement and video, researchers used an adapted version of DeepVariant to analyze 600 giant kelp specimens collected from 40 sites along Tasmania’s coast. Google said the model’s standard versions are trained on human data, so its team trained a version for kelp DNA. The aim is to identify genetic differences that can help scientists choose native plants for selective breeding. The AI does not measure heat tolerance directly: lab tests assess traits, and researchers connect those results with genetic data.
A related foundation for the work is published in BMC Genomics, a peer-reviewed journal. CSIRO scientists and a Google researcher reported two Australian giant kelp reference genomes, assembled from samples from Victoria and Tasmania. The paper’s abstract says 98–99% of each genome was placed into 35 pseudo-chromosomes. The two Australian genomes differ by 0.2%; each differs from a Californian reference by 1.5%, a distinction the authors describe as seven-fold greater.
Google’s account says the analysis of the 600 samples found that remaining Tasmanian patches are genetically isolated. That specific finding is currently reported in the company’s blog post and video, rather than a paper or dataset identified in the source material. Researchers plan to cross distinct native survivors in the lab and plant young kelp on reefs. This is selective breeding, not genetic modification, and it is not yet evidence that the plants can persist through warmer summers.
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 Forests
The work could give conservation teams a way to use genetic diversity among surviving kelp when choosing plants to breed, rather than relying on a reference genome from a distant population. A more relevant Australian genome can help researchers compare local samples and interpret their genetic differences. If the breeding and restoration work succeeds, it could support recovery of an endangered marine community and the species that depend on it.
The scale of the decline makes the research consequential, but it does not establish that AI can reverse it. Laboratory analysis and genome comparison are steps in a longer process: selecting parents, growing young kelp, planting it on reefs and monitoring survival. The central conservation test is whether kelp can persist under the conditions that contributed to forest loss, including warmer, nutrient-poor water and sea urchin pressure.
Popular right now
Dyson V8 Motorhead Origin Cordless Vacuum
Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation
Shark WANDVAC Power PET Cordless Handheld Vacuum, White, WV410WH
As an affiliate, we earn on qualifying purchases.
Why Tasmania Lost Its Kelp
Giant kelp, or Macrocystis pyrifera, forms tall underwater forests in cold, shallow seas. CSIRO says the plants can grow to about 30 metres in Tasmanian waters, providing habitat for marine life including fish, octopuses, sea stars and sea lions. The agency says kelp forests around Tasmania have declined by 95% from historic numbers. A 2026 genome preprint, citing earlier research, gives a 95–98% loss of giant kelp cover in eastern Tasmania since 1940.
CSIRO attributes pressure on the forests to warmer, nutrient-poor water and invading sea urchins as the East Australian Current extends farther south. The agency says the Tasman Sea is warming at twice the global average and describes the kelp forest as an endangered marine community type. The geography limits the options for movement into cooler waters: Tasmania lies near the southern end of the species’ range in the region.
The collaboration was announced in February 2024 by Google Australia and partners including 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 work included mapping kelp from satellite imagery as well as genomics. Google’s November update focuses on the genomics strand, not a report that restoration has already succeeded.
““trained a version of our AI model DeepVariant to analyze our wild samples””
— Google, in its video accompanying the November 12 announcement
The Field Test Is Still Ahead
The main unresolved question is whether kelp selected through genomic analysis and selective breeding will survive in the sea through warmer summers. No field-survival result is reported in the source material. The work described so far does not show that AI itself can predict heat tolerance or that breeding will overcome the environmental pressures affecting Tasmania’s forests.
The reported analysis of 600 specimens from 40 sites, including the finding that remaining patches are genetically isolated, comes from Google’s announcement and video. The source material identifies no paper or dataset for those results yet. It is also not clear when the full analysis will be published, how researchers will define successful restoration, or how many kelp plants will be bred and planted.
From Lab Crosses to Reef Trials
Researchers plan to cross distinct native survivors in laboratory conditions using selective breeding, then plant young kelp on reefs. The next evidence readers will need is a published account of the wild-sample analysis, followed by details of breeding outcomes and reef trials. Those stages could clarify which traits were selected and how the plants perform outside the lab.
Monitoring will need to show whether planted kelp survives local conditions, including warm periods, and whether it contributes to rebuilding forest habitat. Until those results are available, the project is a research and restoration plan, not proof that Tasmania’s lost kelp forests are returning.
Key Questions
What is AI doing in the kelp project?
Google says a version of its DeepVariant model was trained to analyze kelp DNA from wild samples. The analysis is intended to help researchers compare genetic variation and select plants for breeding; the AI does not plant kelp or directly test heat tolerance.
Has the analysis of 600 kelp samples been peer-reviewed?
The source material identifies the 600-sample analysis and its genetic-isolation finding in Google’s blog post and video. It does not identify a related paper or dataset. The two Australian reference genomes, a separate part of the work, were published in peer-reviewed journal BMC Genomics.
Are scientists genetically modifying the kelp?
No. The planned next step is described as selective breeding: crossing distinct native survivors in a lab and growing young kelp for reef planting. The source material does not describe genetic modification.
Why are Australian reference genomes useful?
The published genomes provide local references for comparing Australian kelp. In the paper’s abstract, the two Australian genomes differ by 0.2%, while the Australian and Californian reference genomes differ by 1.5%. That gap can matter when researchers interpret genetic variation in local populations.
Do researchers know whether the bred kelp will survive?
No. The source material reports no field-survival results. Whether selectively bred kelp can persist through warmer summers and other pressures remains the key question for planned reef trials.
Source: ThorstenMeyerAI.com
