Inspiration
Our team is part of the company Genie Enterprise Inc., which is a member of the Ecoliance Rheinland-Pfalz, Germany. We feel responsible for our environment and support projects that focus on sustainability and achieving the UN climate goals.
The Fiware4water challenge is a great place to showcase our support in helping the environment and taking a deeper look at the real time problems. It is also a platform for us to showcase our expertise.
What it does
SewageR is a modern day, digital sewage prediction system, which takes the current day's weather and rainfall levels as input and predicts if there would be overflow happening or not. It runs a binary classification model in the background and uses the weather and rainfall data as the features.
How we built it
We have applied some unconditional pre processing techniques to get the shape of the provided data into action. We have tried expanding the data and moving average to make the data useful. Later we have built a binary classifier. We encapsulated the model into a working web application, using flask environment.
Challenges we ran into
The data pre-processing was tricky and challenging as the data collected is not symmetric. We had to run analysis and try some techniques to get the data useful.
The other challenge is the solution cannot be made open source but a collaboration would be possible. We would love to support ""Fire4Water" and accomplish some wonderful results.
Accomplishments that we're proud of
Building a working solution in a short period of time.
What's next for SevageR
We will continue working on this toolchain to make it part of our solutions portfolio.
Log in or sign up for Devpost to join the conversation.