I'm Building LLM for Satellite Data EarthGPT.app
earthgpt.app> - The "turbo" colormap which provides good visualization of the variations in water turbidity
Your LLM might want to consider decades of color science and not do that. E.g. the canonical https://web.archive.org/web/20001119231700/https://www.resea...
Thanks for the feedback! Yep you are right - actually in the intro video[1] i talk about hallucinations too, as we are very alpha. The good thing is there's a panel on the right that lets you overwrite the AI's selection or you can even ask the LLM to change it. I've update the params manually so if you go to the demo now you will see another color map - Virids :-) [1] https://www.youtube.com/watch?v=ikEDbnUVfYQ
Turbo was designed to mitgate those issues, was it not?
you are right, sorry for being color blind there
oh yea! I rainbow is the the one we wanna avoid.
The domain is getting pretty big. There is an obligatory awesome list which includes general foundation models as well as LLM integrations:
https://github.com/Jack-bo1220/Awesome-Remote-Sensing-Founda...
Reminds me a little bit of another paper I read that used an LLM to generate google earth engine code and make similar natural language queries : https://satgpt.net/
First of all: love the idea, a plug for geobase! But I wanted to see what I can do and check the mining pollution example, but can't, even with being signed up. How about showing more predefined examples to check out?
Thanks mate! Yes we are working now with remote sensing people to have more targeted end-to-end use cases. So flooding is one another would be environmental impact of mining. Can you email me on hi@earthgpt.app would love to incorporate more feedback
What does this use LLM to do that one couldn’t do or would be harder without the LLM?
If you have never done a graduate course in Satellite Remote Sensing there are a lot of techniques that you use on satellite imagery that the LLM guides you through without knowing it upfront. Additionally having a way to have the imagery loaded with the LLM in a single interface and apply the LLMs suggestions isn't a trivial engineering problem. We have done that too.
After spending years building remote sensing analysis products I decided it's time to bring LLMs in the mix and let them see the imagery along with context of spectral bands to do the heavy lifting!
love this -- feels like Planet/Descartes/etc should be on this same path!
apologies if i missed the feature, but it would be really cool to "set a callback function" to react to changes between refreshed data in a boundary.
Thanks! going in the roadmap
sweet!
I great idea indeed