Aspire| Chasers of the Lost Data

Project Details

Awards & Nominations

Aspire has received the following awards and nominations. Way to go!

Global Nominee

The Challenge | Chasers of the Lost Data

Help find ways to improve the performance of machine learning and predictive models by filling in gaps in the datasets prior to model training. This entails finding methods to computationally recover or approximate data that is missing due to sensor issues or signal noise that compromises experimental data collection. This work is inspired by data collection during additive manufacturing (AM) processes where sensors capture build characteristics in-situ, but it has applications across many NASA domains.

Aspire Data Recovery Technology (ADRT)

Aspire Data Recovery Technology (ADRT) is a lightweight and innovative solution to recover missing data such as velocity and altitude of fireballs.

Aspire

THE TEAM

ASPIRE is composed of 5 enthusiastic university students - with disciplines ranging from Aerospace Engineering to Computer science & a vast array of skills that allowed us to effectively tackle the demands of the "Chasers of The Lost Data" challenge. We are:

Ben Kearney : Front End Developer -Queen's University Belfast

Ceilidh Davison : Back End Developer - UlsterUniversity

Jordan Smart : BackEnd Developer - Ulster University

Luke Collingwood : Front End Developer - Queen's UniversityBelfast

Mikhail Kondrashenkov : Scrum Master / Presentation Lead – Queen’sUniversity Belfast


BACKGROUND

Fireballs and bolides are astronomical terms for exceptionally bright meteors that are spectacular enough to to be seen over a very wide area. The following table provides a chronological data summary of fireball and bolide events provided by U.S. Government sensors. Ground-based observers sometimes also witness these events at night, or much more rarely in daylight, as impressive atmospheric light displays. This website is not meant to be a complete list of all fireball events. Only the brightest fireballs are noted.

PROBLEMS WE ENCOUNTERED

Back end

- The team had worked for a majority of day one of the hack using the meteorite dataset however after encountering issues with date formatting and being unable to find a solution by 6pm, decided to start over with the fireball dataset as we wanted to be able to present a solution rather than present an unfiished AI

Front End

- The team initially tried to code the front end in Python using Djang as it woud be easy to integrate the backend, however found it very difficut having no previous python knowledge. After this they tried to develop it in Java however, again, ran into issues with the framework. In the end, the front end team decided to develop the website in HTML, CSS and JavaScript. This however caused a large setback and resulted in us being unable to connect the front and back end together.


THE PROGRAM

The backend team developed a Python AI on Google Collabs to predict the altitude of a fireball with velocity components and total radiated energy, using a linear regression algorithm. To do this we used Python imports such as Numpy, Pandas, MatPlotLib and Sklearn.

The front end team developed the website using HTML, CSS and JavaScript. The team used Pingento to initially develop the design of the website to speed up the process of development due to the deadline of the hackathon. The graph on the results page of the website was made using Google Charts.

Due to the time constraints, we were unable to integrate the back and front end together and therefore the current website is a prototype which only works with the specific dataset we chose to work with.


RESOURCES

ASPIRE wants to inspire other students to make the impossible possible & so we have decided to share our work publicly. This includes our algorithm, the dataset, our hackathon presentation & the prototype of our website.