GLIn

Inspiration

Supply chain management is crucial since the demand is rapidly increasing for the earth with a growing population. Our motivation is to decrease the human effect on nature and keep logistics services sustainable.

What it does

It aims to provide a guide to businesses expanding by analyzing the potential carbon footprint of their logistics operations. It ranks the potential route strategies and guiding on new operation routes by keeping the rural areas away from the operation diameters.

How we built it

We built it in flask as backend to display the maps generated by plotly. the data collected from Rasdaman and further processed by density based spatial clustering to find the areas to target. As the last step, we calculated the routes by projecting them on the region maps using open street map.

Challenges we ran into

• Arbitrarily shaped blob detection is a non-trivial issue
• Integration between components is complex

Accomplishments that we're proud of

Working

What we learned

Communication and agreeing on compatible datastructures is a key part of project development, specially when working on a fast paced situations.

What's next for GLIn

Finish up the integration to make sure that components can actually work with one another and not just separately with their own assumptions.

Built With

• flask
• geopandas
• openstreetmap
• osmnx
• plotly
• python
• sklearn