Code-for-Tomorrow - Space Apps Challenge

Code-for-Tomorrow| Automated Detection of Hazards

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.

Automated detection and flood forecasting via flood Inundation mapping and deep learning

Summary

The application produces flood Inundation mapping by combining GNSS-R Signals with topographical Information along with deep learning time series forecasting info to produce a reliable warning system

How I Addressed This Challenge

Every year states like Kerala and North Eastern states like Assam are hit by floods leading to loss of life and money, I intend to create a reliable flood forecasting system by coming deep learning along with remote sensing technologies to prevent loss of life

This application is based on research carried out by Keshav Unnithan a PhD student at IIT-Bombay Monash research academy. The model was able to map and predict kerela floods of 2018 beforehand and produce maximum effective area of flood.

How I Developed This Project

For font-end I used html,css javascript and for backend firebase Auto ML used along with google maps and google cloud platform

How I Used Space Agency Data in This Project

Without datasets I could not have thought to design the ML model

NASA CYGNSS dataset

https://podaac.jpl.nasa.gov/dataaccess

JAXA Datasets

http://earth.jaxa.jp/en.html#

Project Demo

https://drive.google.com/file/d/1kMg2XV6o-lwG869FpSi5ra6CbV_WDrwD/view?usp=sharing

Project Code

https://github.com/gr8geek/SpaceApps-Challenge-2020

Data & Resources