Can a model trained on satellite data really find brambles on the ground?
1–10 of 55 posts
Re: Can a model trained on satellite data really find brambles on the ground?
#2So 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?
Re: Can a model trained on satellite data really find brambles on the ground?
#3[dead]
Re: Can a model trained on satellite data really find brambles on the ground?
#4Not much detail on the method? Like what data it takes from iNaturalist - for example if it's taking in GPS coordinates of observations of brambles then it's not clear what there is for the ML model to do.
What detail was in the satellite images, was it taking signals of the type of spaces brambles are in, or was it just visually identifying bramble patches?
In the UK you get brambles in pretty much every non-cultivated green space. I wonder how well the classifier did?
Interesting project.
Re: Can a model trained on satellite data really find brambles on the ground?
#5So 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?
I haven’t done this kind of thing since undergrad, but hyperspectral data is really frickin cool this way. Not only can you use spectral signatures to identify specific things, but also figure out what those things are made out of by unmixing the spectra.
For example, figure out what crop someone’s growing and decide how healthy it is. With sufficient temporal resolution, you can understand when things are planted and how well they’re growing, how weedy or infiltrated they are by pest plants, how long the soil remains wet or if rainwater runs off and leaves the crop dry earlier than desired. Etc.
If you’re a good guy, you’d leverage this data to empower farmers. If you’re an asshole, you’re looking to see who has planted your crop illegally, or who is breaking your insurance fine print, etc.
Re: Can a model trained on satellite data really find brambles on the ground?
#6Not much detail on the method? Like what data it takes from iNaturalist - for example if it's taking in GPS coordinates of observations of brambles then it's not clear what there is for the ML model to do. What detail was in the satellite images, was it taking signals of the type of spaces brambles are in, or was it just visually identifying bramble patches? In the UK you get brambles in pretty much every non-cultiva…
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.
Happy to answer any other questions.
Re: Can a model trained on satellite data really find brambles on the ground?
#7So 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?
I haven’t done this kind of thing since undergrad, but hyperspectral data is really frickin cool this way. Not only can you use spectral signatures to identify specific things, but also figure out what those things are made out of by unmixing the spectra. For example, figure out what crop someone’s growing and decide how healthy it is. With sufficient temporal resolution, you can understand when things are planted an…
> If you’re a good guy, you’d leverage this data to empower farmers. If you’re an asshole, you’re looking to see who has planted your crop illegally, or who is breaking your insurance fine print, etc.
How does using it to speculate on crop futures rank?
Re: Can a model trained on satellite data really find brambles on the ground?
#8So 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! TESSERA is very new so we're still exploring how well it works for various things.
We're hoping to try it with a few different things for our next field trip, maybe some that are much harder to find than brambles.
Re: Can a model trained on satellite data really find brambles on the ground?
#9So 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?
I've wondered this about finding hot springs.
Re: Can a model trained on satellite data really find brambles on the ground?
#10FarmLogs (YC 12) did exactly this. We used sat imagery in the near-infrared spectrum to determine crop health remotely. Modern farming utilizes a practice called precision ag - where your machine essentially has a map of zones on the field for where treatments are or aren't needed and controllers that can turn spray nozzles on/off depending on boundaries. We used sat imagery as the base for an automated prescription system, too. So a farmer can reduce waste by only applying fertilizer or herbicide in specific areas that need it.