Alon

Our team proposes an application that would help low-income communities respond to disaster better by creating a monitoring system that prioritizes rural areas as high-risk.

This venture is essential to society because it is inclusive to those in rural areas to help prepare for devastating natural disasters like that of floods.

Additionally, through machine learning, the application is also capable of improving by receiving feedback and reports from users. It could also include collaboration with other organizations that would be willing to provide aid through relief goods, evacuation centers, etc. With further improvement and implementation, this application would be able to play a big part in revolutionizing the way countries, such as the Philippines, handle one of the most prevalent natural disasters.

A negative association between income per capita and natural disaster risk measures has been found in recent empirical literature, supporting the logic that higher incomes allow countries to minimize the risk of disasters. With this, there is a need to label low-income areas as high risk especially to heavy typhoons.

With the added negative impact of the pandemic, our team felt as though the Philippines and other countries are in dire need of assistance when it comes to mitigating the effects of floods.

The application prototype will be created through a web application called Thunkable. One of the members also has experience in creating ML models as part of her past research.

As for the problems, the team’s lack of equipment capable of supporting the ambition of the project may have been the most notable hindrance. There were also instances of connectivity issues which led to further setbacks. Rest assured, the potential of this project is unmatched when it comes to benefiting the masses and it will surely contribute to positive global change.

*Our proposal might be a bit incomplete as we registered for the hackathon late, but we have done research for this concept

Built With

• python
• thunkable