This is all far outside of my wheel house but I'm curious if there's any way to use this for rocks and geology? Identifying dikes and veins on cliff sides from satellites would be really cool.

▲

jofer 10 hours ago | parent | next [-]

A major limitation is that most different rock types look essentially identical in visual+NIR spectral ranges. Things separate once you get out to SWIR bands. Sentinel2 does have some SWIR bands and it may work reasonably well with embeddings. But a lot of the signal the embeddings are going to be focused on encoding may not be the right features to distinguish rock types. Methods more focused specifically on the SWIR range are more likely to work reliably. E.g. simple band ratios of SWIR bands may give a cleaner signal than general purpose embeddings in this case.

Hyperspectral in the SWIR range is what you really want for this, but that's a whole different ball game.

▲

throwup238 9 hours ago | parent [-]

> Hyperspectral in the SWIR range is what you really want for this, but that's a whole different ball game.

Are there any hyperspectral surveys with UAVs etc instead of satellites?

	▲	jofer 8 hours ago \| parent [-]
		Usually airplanes because the instruments are heavy. But yeah, that's the most common case. Hyperspectral sats are much rarer than aerial hyperspectral.

▲

sadiq 11 hours ago | parent | prev | next [-]

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.

▲

throwup238 9 hours ago | parent [-]

Is there a way to cluster the embeddings spatially or look for patterns isolated so some dimensions? (Again, way out of my wheel house)

What I mean is a vein is usually a few meters wide but can be hundreds of meters long so ten meter resolution is probably not very helpful unless the embeddings can encode some sort of pattern that stretches across many cells.

	▲	sadiq 4 minutes ago \| parent [-]
		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.

▲

tony_cannistra 11 hours ago | parent | prev [-]

almost definitely!