Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Can a model trained on satellite data really find brambles on the ground?

toao.com

Post reply on HN
Print view View original

21–30 of 55 posts

Re: Can a model trained on satellite data really find brambles on the ground?

#21

Post by throwup238 »

avsm wrote: post #12
cuno wrote: post #2

So after transforming multispectral satellite data into a 128-dimensional embedding vector you can play "Where's Wally" to pinpoint blackberry bushes? I hope they tasted good! I'm guessing you can pretty much pinpoint any other kind of thing as well then?

Yes it's very good fun just exploring the embeddings! It's all wrapped by the geotessera Python library, so with uv and gdal installed just try this for your favourite region to get a false-colour map of the 128-dimensional embeddings: # for cambridge # https://github.com/ucam-eo/geotessera/blob/main/example/CB.geojson curl -OL https://raw.githubusercontent.com/ucam-eo/geotessera/refs/heads/main/example/CB.geojson #…

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.

Re: Can a model trained on satellite data really find brambles on the ground?

#22

Post by tony_cannistra »

throwup238 wrote: post #21
avsm wrote: post #12

Earlier quoted context omitted.

Yes it's very good fun just exploring the embeddings! It's all wrapped by the geotessera Python library, so with uv and gdal installed just try this for your favourite region to get a false-colour map of the 128-dimensional embeddings: # for cambridge # https://github.com/ucam-eo/geotessera/blob/main/example/CB.geojson curl -OL https://raw.githubusercontent.com/ucam-eo/geotessera/refs/heads/main/example/CB.geojson #…

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.

almost definitely!

Re: Can a model trained on satellite data really find brambles on the ground?

#23

Post by sadiq »

throwup238 wrote: post #21
avsm wrote: post #12

Earlier quoted context omitted.

Yes it's very good fun just exploring the embeddings! It's all wrapped by the geotessera Python library, so with uv and gdal installed just try this for your favourite region to get a false-colour map of the 128-dimensional embeddings: # for cambridge # https://github.com/ucam-eo/geotessera/blob/main/example/CB.geojson curl -OL https://raw.githubusercontent.com/ucam-eo/geotessera/refs/heads/main/example/CB.geojson #…

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.

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.

Re: Can a model trained on satellite data really find brambles on the ground?

#26

Post by jofer »

throwup238 wrote: post #21
avsm wrote: post #12

Earlier quoted context omitted.

Yes it's very good fun just exploring the embeddings! It's all wrapped by the geotessera Python library, so with uv and gdal installed just try this for your favourite region to get a false-colour map of the 128-dimensional embeddings: # for cambridge # https://github.com/ucam-eo/geotessera/blob/main/example/CB.geojson curl -OL https://raw.githubusercontent.com/ucam-eo/geotessera/refs/heads/main/example/CB.geojson #…

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.

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.

Re: Can a model trained on satellite data really find brambles on the ground?

#27

Post by NedF »

> Can a model trained on satellite data really find brambles on the ground?

No, as per researcher, "However, it is obvious that most of the generated findings aren’t brambles" and obviously no.

All the model did was think they followed roads, all roads.

If it was oil and gas where people put in effort and their results where checked vs universities where meaningless citations matter and results are never confirmed, it would be more believable.

What they are asking is impossible, increasing the likelihood without silly hacks like it's not in rivers or on top of buildings is an interesting problem but out of scope for academics.

Re: Can a model trained on satellite data really find brambles on the ground?

#29

Post by throwup238 »

sadiq wrote: post #23
throwup238 wrote: post #21

Earlier quoted context omitted.

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.

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 are…

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.

Re: Can a model trained on satellite data really find brambles on the ground?

#30

Post by throwup238 »

jofer wrote: post #26
throwup238 wrote: post #21

Earlier quoted context omitted.

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.

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 SWI…

> 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?

Post reply on HN