Space Apps Challenge 2018

250 milion people are affected by flood disasters.

3.5 million are spent helping victims and reparing damages.

Costs of prevention are in average 5% of the costs of repairing the damage of floods.

Our goal is to reduces money spent on reparing by spending on prevention. We used satellite data from NASA so we can get coverage from all small cities over the world, get historical precipitation data and crosses with a specific soil type and its specificities (like runoff curve number) to get what will be the cost of reparing that area.

We believe that with proper data analysis, sourced from NASA satellites we can better assist aid agencies to improve the selection proces of the ground teams that will help these communities.

Resources

PRECIPITATION DATA: Daily accumulated precipitation product is generated from the research-quality 3-hourly TRMM Multi-Satellite Precipitation Analysis TMPA (3B42). We used a 5-years dataset focused on South America area.

hhttps://disc.gsfc.nasa.gov/datasets/TRMM_3B42_Dail...

FINANCIAL DATA AND MODELING: We used multiple data to estimate cost of reparing using a citizen/dolar rate. We crossed this data with population number, soil type, area (in m²). We focused on using global data but mainly using Brazil study cases.

http://australianbusinessroundtable.com.au/

http://research.un.org/en/disaster/un-resources

http://www.mi.gov.br/defesacivil/publicacoes

MODELING: Math modeling to runoff estimation.

https://en.wikipedia.org/wiki/Runoff_curve_number

Tools

We used Python3 with Flask to Data Procecssing micro-framework to deploy our API.

Our mobile cross-plataform app was made with love using React Native.

We also used some Linux stuff to our web crawler to get NASA data from DISC.

https://github.com/orion-spaceapps-bsb