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

Show HN: My demo for vector embeddings for the Earth's surface

louisquissetlabs.com

Post reply on HN
Print view View original

21–30 of 42 posts

Re: Show HN: My demo for vector embeddings for the Earth's surface

#21

Post by lovasoa »

potatoman22 wrote: post #16
wyldfire wrote: post #7

Earlier quoted context omitted.

I'm pretty sure I'm not the intended audience but I also have no idea what this is used for. Surveying? Real estate tycoons? Oil & gas exploration?

It's a way to encode land to make predictions of it. E.g. is the land arable, is it rural, how similar is it to X, etc. Embeddings help encode data in formats more usable by ML models.

The question was: in what context do people need to answer a question like "which geographical points are close to X and similar to X"?

I don't understand who the target audience is and what this can be used for.

Re: Show HN: My demo for vector embeddings for the Earth's surface

#23

Post by ckrapu »

fnordpiglet wrote: post #5
ckrapu wrote: post #2

I've had to build out some version of a geospatial vector embedding / latent variable dataset for at least 4 separate projects now. Come see the viewer I've built on top of it! The embeddings come from globally available Copernicus land cover data.

Can you explain what I’m looking at? I don’t know how to interpret the hex tiles :-)

Sure! The basic idea is that each hexagon is a discrete unit of space for which I obtain a vector embedding. This vector is supposed to represent a sort of data-based summary of that location, obtained in this case using deep learning.

When you put the search on a hex, it looks up the vector for that hex and then performs a similarity search on all other vectors within the circle and shows the ones which are most similar in terms of land cover. The dependence on land cover / land use data is just because that was easy to get.

As other folks have pointed out here, raw satellite imagery is also a potential input source for this. I'm playing around with other sources and really want to integrate something like GeoVex (https://openreview.net/forum?id=7bvWopYY1H) into the embeddings as well.

Re: Show HN: My demo for vector embeddings for the Earth's surface

#24

Post by ckrapu »

lovasoa wrote: post #21
potatoman22 wrote: post #16

Earlier quoted context omitted.

It's a way to encode land to make predictions of it. E.g. is the land arable, is it rural, how similar is it to X, etc. Embeddings help encode data in formats more usable by ML models.

The question was: in what context do people need to answer a question like "which geographical points are close to X and similar to X"? I don't understand who the target audience is and what this can be used for.

The original idea came from something I saw at work - we needed a way to build generic feature sets representing something about real estate, but beyond the data we had on prices, floors, and other house-specific details.

Re: Show HN: My demo for vector embeddings for the Earth's surface

#25

Post by ckrapu »

spousty wrote: post #9
ckrapu wrote: post #2

I've had to build out some version of a geospatial vector embedding / latent variable dataset for at least 4 separate projects now. Come see the viewer I've built on top of it! The embeddings come from globally available Copernicus land cover data.

How did you generate the embeddings. The vectors are relatively small for all the embedding I have seen built from image and nlp models. Which copernicus bands were you using? Did you augment the data with DEM info?

The embeddings were obtained using a CNN triplet loss model (~10M parameters) on the Copernicus land cover data. I haven't used DEM data yet but I have done generative modeling on DEMs in other work and would like to do that too:

https://www.linkedin.com/in/christopher-krapu/overlay/157690...

Re: Show HN: My demo for vector embeddings for the Earth's surface

#28

Post by ckrapu »

spousty wrote: post #10
DerSaidin wrote: post #4

Seems to not handle the ocean well.

It's due to the fact that they used satellite imagery to create the embeddings. The map is just for visualization. They probably used 5 or more bands of the satellite data which means each pixel is going to be slightly different due to things like depth, amount of silt in the water, amount of plankton.... Having worked on these types of problems before the model is doing a pretty great job matching pixels.

Thanks! And you are giving it too much credit here - it's just trained on one-hot encoded land cover (24 classes) from Copernicus. Using imagery directly would be # 2 on my list of to-dos after including elevation in the input data.

Re: Show HN: My demo for vector embeddings for the Earth's surface

#30

Post by ckrapu »

foota wrote: post #19
wyldfire wrote: post #17

Earlier quoted context omitted.

Sure, I get that part -- but then how do people use the predictions?

The embeddings are used by algorithms, not people, generally. You could ask something like "what's the most similar place to X within Y", and it would using the embeddings (which cover a variety of facts) to calculate answer. An embedding is an N dimensional vector (where the dimensions may or may not be meaningful to us), and similarity can be implemented by looking at the similarity between vectors.

Yup, and while the similarity search is perhaps the most visually appealing way to work with it, the real use (in my opinion) is in providing generic sets of geospatial features which are reusable across applications. I've built out versions of H3-referenced feature sets at each of the jobs I've had over the last 10 years.
Post reply on HN