His work has uncovered a number of really tricky bugs in the multicore runtime but what's brilliant is the reports normally come with a minimal reproduction. This makes working out the cause so much easier.
https://github.com/ucam-eo/geotessera has an image showing our embedding coverage at the moment. Blue areas we have complete coverage for 2024, green areas we cover 2017-2024. We're slowly trying to populate everything 2017-2024 but the constraint is GPU and storage at the moment - each year takes ~20k GPU/200k CPU hours and requires storing and serving 200 terabytes of data. The world is big!
If there is an area you would like prioritised, there's an issue template on the geotessera github repo which we can use to move regions around in the processing queue.
It's possible to use embeddings as input to a convolutional network and then train that using labels. We've done that for at least one of the downstream tasks in the TESSERA paper: https://arxiv.org/abs/2506.20380 to estimate canopy height.
The downside of that approach is that you need to spend valuable labels on learning the spatial feature extraction during training. To fix that we're working on building some pre-trained spatial feature extractors that you should only need to minimally fine-tune.
I was a lot more optimistic about Gabriel's model than he was. It is essentially a presence-only species distribution model where accuracy depends largely on assumptions around prevalence and which really needs some presence-absence data to calibrate.
As I mentioned in one of the other comments, the model is also only pixel-wise. That is, it is not using spatial information for predictions.
We did note several places during the trip that didn't contain bramble. The hotspot in the middle of the residential area was also entirely isolated.
For a proper evaluation you would need to be more methodological but as a sanity-check we were very happy with it.
One other thing to point out about the bramble model is that it is pixel-wise. That is each prediction is exclusively only what is within the 10 metre pixel (give or take the georeferencing error).
It might work. TESSERA's embeddings are at a 10 metre resolution, so it might depend on the size of the features you are looking for. If those features have distinct changes in colour or texture over time or they scatter radar in different ways compared with their surroundings then you should be able to discriminate them.
The easiest way to test is to try out the interactive notebook and drop some labels in known areas.
There is the issue of just how visible truffles are from space though, if they grow under cover. That said, it may still work because you can find habitats that are very likely to have truffles. We've had some promising results looking at fungal biomass.
That's actually a great idea! I wonder what kind of feature size would be needed though - TESSERA's embeddings are at a 10 metre resolution so for larger structures you might need some kind of spatial aggregation.
Hyperspectral data is really neat though it's worth pointing out that TESSERA is only trained on multispectral (optical + SAR) data.
You are very right on the temporal aspect though, that's what makes the representation so powerful. Crops grow and change colour or scatter patterns in distinct ways.
It's worth pointing out the model and training code is under an Apache2 license and the global embeddings are under a CC-BY-A. We have a python library that makes working with them pretty easy: https://github.com/ucam-eo/geotessera
Hi! You can find a bit more about Gabriel's model through some of his posts over the last few weeks: https://gabrielmahler.org/posts/
When it comes to the satellite images, the model actually used TESSERA (https://arxiv.org/abs/2506.20380) which is a model we trained to produce embeddings for every point on earth that encodes the temporal-spectral properties over a year.
Think of it like a compression of potentially fifty or a hundred observations of a particular point in earth down to a single 128 dimension vector.
This is a really nicely written and illustrated post.
An advanced extension to this is that there are algorithms which calculate the number of records to skip rather than doing a trial per record. This has a good write-up of them: https://richardstartin.github.io/posts/reservoir-sampling
I've been doing some work with colleagues at Cambridge and Imperial over the last year on using LLMs to improve evidence synthesis, primarily trying to find papers on the effectiveness of certain Conservation interventions. It's becoming clear that you really need to move beyond screening papers only by title and abstract - there's often information buried deep within papers that can only be found with access to full text. My colleague Anil Madhavapeddy has written a bit about our adventures in trying to ingest full-text academic papers: https://anil.recoil.org/notes/uk-national-data-lib
His work has uncovered a number of really tricky bugs in the multicore runtime but what's brilliant is the reports normally come with a minimal reproduction. This makes working out the cause so much easier.
Great work Jan.