Cherry Bomb| 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.

Machine Learning Model for TCBs Prediction

Summary

*This Project uses a machine learning supervised model used to find TCBs through satellite signals that will be presented to it through a web app which has an image example that will be analyzed by the model, that will show the data that the model returned and we’ll explain how the model works. To use this app, the investigator has to go to the upload section to upload the file that will be analyzed, then the app will open another tab that will show the results of the analysis.

How We Addressed This Challenge

*We developed a machine learning supervised model in order to detect TCBs (transverse cirrus bands), which are irregularly spaced bandlike cirrus clouds that form nearly perpendicular to a jet stream axis, from satelital images. Since TCBs are often found in tropical cyclone outflow regions, our project can help lots of the people that are affected by storms every year by giving more information about cyclones and its path.

How We Developed This Project

*Our team, Cherry Bomb, is alway searching for true challenges that solve real life problems. With this idea in mind, we chose Automated Detection of Hazards and, after thinking it over we decided to focus on TCB detection. With a lot an effort and passion, we have created a website using HTML, CSS and JavaScript and we also connected it to a Python coded machine learning model that search TCBs from satelital images. Of course we have problems to achieve our goal, but with a good communication, teamwork and enthusiasm we could get over it, and it was very fun!

How We Used Space Agency Data in This Project

*We use the data provided by the space agency, obtaining satellite images to process them and to train our artificial neural network.

Project Demo

https://cherryb.herokuapp.com/

https://www.canva.com/design/DAEJrAfohHg/o-2FkfegEcyNNCOme5UWmw/view?utm_content=DAEJrAfohHg&utm_campaign=designshare&utm_medium=link&utm_source=sharebutton

Project Code
Data & Resources
  1. Canuma, P. (10 de Octubre de 2018). Image Pre-processing. Obtenido de Towards data science: https://towardsdatascience.com/image-pre-processing-c1aec0be3edf
  2. Earthdata. (2020, 5 octubre). EARTHDATA. https://earthdata.nasa.gov/
  3. GOES-East - Sector view: Mexico. (s. f.). GOES image viewer. Recuperado 4 de octubre de 2020, de https://www.star.nesdis.noaa.gov/GOES/sector.php?sat=G16§or=mex
Tags
#MachineLearning #TransverseCirrusBands
Judging
This project was submitted for consideration during the Space Apps Judging process.