Skip to content

Commit

Permalink
update readme
Browse files Browse the repository at this point in the history
  • Loading branch information
nonnontrivial committed Jan 29, 2025
1 parent 2b6010d commit 7f4ce9a
Showing 1 changed file with 12 additions and 17 deletions.
29 changes: 12 additions & 17 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,33 +4,28 @@
CTTS is an open source application for reading [sky brightness](https://en.wikipedia.org/wiki/Sky_brightness) all over the earth's landmass, without a sensor.

## features
## about

- gRPC api for predicting sky brightness
This project is motivated by wanting an answer to the following question:

- publisher component that repeatedly generates sky brightness readings for coordinates of H3 cells
> where and when are the stars good?
It would be infeasible to have [sensors](http://unihedron.com/projects/darksky/TSL237-E32.pdf)
everywhere you would want a sky brightness measurement, but one path is to do inference of this value.

The approach this project takes is to use pytorch to capture the relationships within the [Globe At Night
dataset](https://globeatnight.org/maps-data/) and predict sky brightness for H3 cells at a configured [H3 resolution](https://h3geo.org/docs/core-library/restable/) (default `0`).

## features

- consumer component that stores sky brightness readings and finds reading with highest `mpsas` during last iteration over H3 cells
- passive collection of predicted sky brightness for H3 cells in earth's landmass.

## todos

- [ ] update open meteo data while app is running
- [ ] create typer app to manage brightness model
- [ ] brightness prediction cycle can push alerts

## about

This project is motivated by the desire to know:

> where and when are the stars good?
It would be infeasible to have [sensors](http://unihedron.com/projects/darksky/TSL237-E32.pdf)
everywhere you would want a sky brightness measurement, but one path is to do inference of this value.

The approach this project takes is to use pytorch to capture the relationships in the [Globe At Night
dataset](https://globeatnight.org/maps-data/) and use that captured relationship to
predict sky brightness for H3 cells at a configured [H3 resolution](https://h3geo.org/docs/core-library/restable/) (default `0`).

## running with docker

- `git clone`
Expand Down

0 comments on commit 7f4ce9a

Please sign in to comment.