A-team - Space Apps Challenge

A-team| Automated Detection of Hazards

Awards & Nominations

A-team has received the following awards and nominations. Way to go!

Local Peoples' Choice Winner

Automated Detection of Hazards

Countless phenomena such as floods, fires, and algae blooms routinely impact ecosystems, economies, and human safety. Your challenge is to use satellite data to create a machine learning model that detects a specific phenomenon and build an interface that not only displays the detected phenomenon, but also layers it alongside ancillary data to help researchers and decision-makers better understand its impacts and scope.

Look4dood

Summary

Ecologists, urbanists, and citizens of Dushanbe are challenged to come up with smoke produced by the combusting of leaves and huge traps. And the difficulty is not only to explore smoke spreading in surroundings, but to detect location. Our main goal was to detect locations of huge combusting in a city and suburban, provide with useful data like air quality, temperature, population, and risks Look4dood is a web service that allows us to detect, explore, report on combusting locations using data of Fire Information for Resource Management System. It provides an opportunity to warn citizens, research smoke spreading, and the effect of it.

How We Addressed This Challenge

In the autumn, in most streets combusting leaves. The poisonous smoke moves through the city and affects air quality, health. By the way, everyday poisonous gases have been producing for 40 years the Dushanbe Combusting Landfill that is 11 km away from the city, and smoke effects on the nearest citizens.

Look4dood is a web service that allows us to detect, explore, report on combusting locations.

We want to provide citizens and researches with a map that shows the effect of combustion, risks and to focus the attention on the upcoming danger of combusting hazard

How We Developed This Project

First of all, we identified our users to provide them comfoable UI and worked on prototypes.

In this project, we decided to focus on detecting huge combusting landfills.

To do this, we visited LandFill and used data from Fire Information for Resource Management System to examine the deviation of data gained.

Also we used map of winds earth.nullschool.net.

Then we analysed dataset from

https://firms.modaps.eosdis.nasa.gov/active_fire/#firms-txt

https://github.com/nasa/spaceapps-phenomena_detection/tree/dev/data/labeled#biomass-burning-smoke

During the research, we impacted by limitations as low-resolution and low-qualitative data of air quality of Dushanbe and suburban area we decided to collect data from API's from Google Maps and we developed a frontend prototype connecting it with Google API, Air Quality Open Data Platform

How We Used Space Agency Data in This Project

Our research goal was to detect smoke locations in Dushanbe and suburban to analyze the environment. We used datasets provided by Space Apps https://github.com/nasa/spaceapps-phenomena_detection/tree/dev/data/labeled#biomass-burning-smoke . And Fire Information for Resource Management System to find combustions

Project Demo

figma: https://www.figma.com/proto/xR5YkiRJUANU0LXMtSk3tl/Look-4-Dood?node-id=3%3A587&viewport=-2001%2C-306%2C0.3568885624408722&scaling=min-zoom

web-service: http://look4dood.velkomb.com/

Project Code

https://github.com/krem4ik/Look-For-Dud-Frontend and https://github.com/krem4ik/Look-For-Dud-Backend

Data & Resources

https://open.nasa.gov/open-data/

https://modis.gsfc.nasa.gov/

https://earth.nullschool.net/ru/about.html#aot