Aurora Borealis

https://github.com/Aurora-Borealis-NASA-Space-Apps-2022/Aurora-Borealis

https://youtu.be/B_uEVxWl69A

• Our project's proposal is that we are creating an alert system that can speculate changes of any solar flares; thus, can help us predict any incoming carrington event in the future. Which can be achieved by using Mahcine learning technology.

• We have developed a dataset system that was designed by gathering up raw data from previous years (I.e: 2021 for our solution.) For every 6 months throughout 1 year, we monitor closely on the following parameters:

- Magnetic field magnitude (BW[nT]) using "Wind Mission Magnetic Field Dataset".

• We are creating a neural network pipeline that can accurately track changes in the peak solar wind speed and give a head start on the possibility for the next Carrington-like event​.

• Our approach is based on the overall electrical flux and the magnetic fields produced by the solar wind tests utilizing the numbers for both sensors and the Faraday's cup (1) and (2). We project voltage/current spectra as the result using these parameters. We are creating a neural network pipeline that can accurately track changes in the peak solar wind speed and give a head start on the possibility for the next Carrington-like event​.

• The project can set as an immense benefit for humanity, as by speculation, the Carrington event is set to occur in the near future. This is a precautionary step to avoid widespread impact if eventually it happens. As we aim to provide analytics and visuals based on quality data to avoid widespread impact of the next Carrington-like event​.

• We hope that in the future, people can prepare in advance or even stay away from instruments that can trigger a reaction when the flare hits the Earth. Also, scientists can provide an anti-flare shield such that during the event, no one will be hurt even if close to conductors.

• Programming language used : Python.
• Tools and software used: GoDaddy, Canva, iMovie, GitHub, Weebly, Spacepy and Visual Studio Code.

The project website: theauroraborealis.co

The datasets were taken from the Nasa resources as well as from the Canadian Space Agency (CSA).

These resources were utilized in such a way that we used the Nasa resources to create the model and algorithm for training the dataset using NN to produce the desired outputs. Then for verification purposes, we only used the Magnetometer datasets to so that our outputs are inclined.

What inspired us was that the ability to make or design such an algorithm that uses old dataset so that we can predict some sort of what damage it will cause us.

"It couldn't have been better." This is what my teammates and I have said just a few minutes ago. The experience with experimenting with new technology, learning more about our beloved earth and how to improve the humanitarian experience on earth. We learned that there are always different and unique ways to address challenges. There's no solution that fits all problems and there's no what is so called "the right way" to do things. You can do mistakes and learn, educate yourself, practice, do more mistakes, execute and it's all part of the process. We also learned more about the Carrington event and its possible catastrophic consequences on earth. We learned more about the machine learning technology and developing datasets through the different tools available while also making sure to make the best use if available resources either provided by Nasa Space Apps or external resources. When we were deciding on choosing the challenge, we somehow felt connected to this challenge. Sure, we believed that our skills fit the most with tackling this challenge, but as someone (me) who experience electricity cutouts on frequent basis (even though it isn't compared to the catastrophic consequences of the original event) it still had me to feel the urge to tackle such issue so people won't have to experience anything similar to it, and my team has had similar experiences too, and together we realized how much of an issue it can really be. Our approach was to educate ourselves first with the problem and then try to reach to the root cause or in other words try to emulate it on a small scale and then we try to look at the big picture. We definitely had some setbacks and challenges , mostly the time management aspect. For sure, everyone had different commitments and different time allocations so it was necessary to get things in order while not having to affect our productivity levels and thatw as achieved by civil and professional communication with a room for empathy, in order to have a healthy work environment. Another challenge that I, myself had was the electricity cutout waves, resulting in some issues in the scheduling and also having to still work in a hard environment, however my teammates showed their consideration and empathy for my situation and we were able to come over it together as a team. I was also able to use another space to help in completing the project with my team. I would like to thank all of my teammates who showed their continuous support and their sacrifice to truly achieve our mission and if not for all the effort they have contributed we wouldn't be able to achieve our mission on time. We would also like to thank Nasa Space Apps for this amazing opportunity to help saving earth and let us youth, have the opportunity to be a part of the solution together.

Software tools used:

- Visual Studio Code (IDE)

- Python V3.10.7 for writing code

- Spacepy documentation for understanding and analyzing CDF files.

- Used GitHub for maintaining the code online

- Used GoDaddy to create a website

-Used Weebly for design the layout of the website

Images and videos:

https://www.nasaspaceflight.com/2020/08/carrington-event-warning/

https://www.pexels.com/video/cg-animation-of-fire-sun-854422/

#auroraborealis #software #machinelearning #Carrington