Inspiration

Landslides are catastrophic natural hazards that often lead to loss of life, property damage, and economic disruption. Image-based landslide investigations are crucial for determining landslide susceptibility and risk.

What it does

Segment selected regions of land and mark possible landslides.

How we built it

We use two neural networks

  • First neural network was build using PyTorch, and it was GAN architecture, which didn't provide good results, so we moved to the classic U-NET architecture which performed better. The result of the U-NET is a binary mask with segmented landslides. ## Challenges we ran into Inconsistency of specific region of data. ## Accomplishments that we're proud of We build a model which is capable to mark possible landslides

Built With

Share this project:

Updates