Hadrons| Automated Detection of Hazards
Automated Detection of Hazards
Distributed hazard detection platform
Summary
We are team Hadrons from Kigali, Rwanda. We are a team of 3 members composed of 2 software engineers, and a machine learning engineer. Our priority is to use machine learning to predict a time series data in order to take preventive measures towards environmental hazards upfront.
How We Addressed This Challenge
Our platform detects and analyse hazard that might occur in a selected location using PM2.5 concentration, dew Point, temperature, pressure, combined wind direction, cumulated wind speed, cumulated hours of snow, cumulated hours of rain of a selected location at the certain point in the future.
How We Developed This Project
Due to the recent hazards that took place in Rwanda, we decided to work on a machine learning algorithm that uses data from the past to predict what might happen in the future. Some of the data we used to train the machine learning algorithm are Cumulated hours of rain, Cumulated hours of snow, Cumulated wind speed, PM2.5 concentration, Dew Point, Temperature, Pressure.
We used keras to train the machine learning algorithm, python (Flask) to build the web server and angular to build the frontend client for users to make prediction using the developed model.
How We Used Space Agency Data in This Project
- We used the data to better conceptualize our project.
Project Demo
Project demo: https://hadrons-automatic-detection.netlify.app/
Slides: https://docs.google.com/presentation/d/1M3qJyG_-n_zENO4zVD4h5J2EPupi0lnsWgvI7yvYKHk/edit?usp=sharing
Repo: https://github.com/teamhadrons/automatic-hazard-detection
Data & Resources
- https://developers.google.com/earth-engine/datasets/catalog/NASA_GLDAS_V021_NOAH_G025_T3H#bands
- https://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data