Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Explore the effect of max_edge_distance #64

Open
bart1 opened this issue Mar 16, 2023 · 1 comment
Open

Explore the effect of max_edge_distance #64

bart1 opened this issue Mar 16, 2023 · 1 comment
Labels
data-pipeline discovery Related to investigation/visualization gnn-theory Involves knowledge of the theory of the GNN

Comments

@bart1
Copy link
Collaborator

bart1 commented Mar 16, 2023

To avoid fully connected networks there is currently a max_edge_distance (default 50 meter). How ever density of points is strongly dependent on distance from the radar. This means that the density of graphs will be dependent on distance from the radar this might be undesirable. Furthermore the distance between elevation scan as some distance from the radar might also exceed the threshold, as a result one might get unconnected graphs and occasions where no vertical information is included. Therefore it might be important to explore the effect of max_edge_distance and consider some other approach of connecting neighbors. Say minimally X neighbors and maybe a way to ensure vertical information is included.

@bart1
Copy link
Collaborator Author

bart1 commented Mar 16, 2023

might be related to #44

@abelsiqueira abelsiqueira added gnn-theory Involves knowledge of the theory of the GNN data-pipeline discovery Related to investigation/visualization labels Mar 28, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
data-pipeline discovery Related to investigation/visualization gnn-theory Involves knowledge of the theory of the GNN
Projects
None yet
Development

No branches or pull requests

2 participants