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

31–40 of 55 posts

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

#31

Post by lightedman »

A model I have trained on ASTER and LANDSAT data has major difficulties identifying spots for agate hunting. Even after I've given it extra instruction such as looking only in volcanic terrain (with USGS map provided,) or focusing on mixed signals of hydrous silica and iron, checking near known fault zones in said volcanic areas, it still gave me results everywhere, and almost none matching my criteria.

Plants are a way different and more difficult ballgame (they like to mess up my satellite data) so as I read I am not surprised to see that this didn't really give proper results.

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

#32

Post by jofer »

throwup238 wrote: post #30
jofer wrote: post #26

Earlier quoted context omitted.

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?

Usually airplanes because the instruments are heavy. But yeah, that's the most common case. Hyperspectral sats are much rarer than aerial hyperspectral.

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

#33

Post by folli »

jcims wrote: post #15

Seems like it could be pretty useful for archaeology as well.

As a hobby project, I was looking into using LiDAR data to view archeological points of interest in Switzerland: https://github.com/r-follador/delta-relief

It would be interesting to overlay TESSERA data there, although the resolution is of course very different.

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

#35

Post by dmbche »

NedF wrote: post #27

> 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, i…

https://gabrielmahler.org/environment/ai/ml/%F0%9F%A6%94/202...

For the "However, it is obvious that most of the generated findings aren’t brambles"

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

#37

Post by xarope »

NedF wrote: post #27

> 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, i…

isn't this the same findings as the old "we trained to identify huskies, but instead we identified snow" problem?

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

#39

Post by lloeki »

Well looks like they found a lot of brambles! Were there large areas without any bramble?

Cue dowsers, who successfully find water... but also who would anyway anywhere else because underground water isn't the underground river/pocket that people imagine and thus random chance by itself has high probability of finding water.

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

#40

Post by thinkingemote »

ggm wrote: post #24

If it can find sloes it's going to make sloe gin foragers very very angry. Generally when they find a usable crop they don't share it.

Brambles are blackberries. Sloes are from Blackthorn bushes. They are different plants but probably are in the same location!
Post reply on HN