High-Level Project Summary
We made an application called the NASA Carrington event, which is an application that predicts the occurrence of a Carrington event a time before it based on a set of features on which the machine learning model we built dependsWe have done the preprocessing and the data needs to be ready to be passed through the machine learning model.We used a model called LSTM, one of the Neural Network models, which gave us an Accuracy of 56 percent final score.The machine learning model called LSTM takes the data and then trains it to show the results, which are before the occurrence of the Carrington event based on the emissions and magnetic energy emitted by the sun and directly affecting the earth
Link to Final Project
Link to Project "Demo"
Detailed Project Description
We made an application called the NASA Carrington event, which is an application that predicts the occurrence of a Carrington event a time before it based on a set of features on which the machine learning model we built depends.
We have done the preprocessing and the data needs to be ready to be passed through the machine learning model.
We used a model called LSTM, one of the Neural Network models, which gave us an Accuracy of 56 percent final score.
The machine learning model called LSTM takes the data and then trains it to show the results, which are before the occurrence of the Carrington event based on the emissions and magnetic energy emitted by the sun and directly affecting the earth, and based on which the application will determine the time of the occurrence of the Carrington event11:26 AM
LSTM is a special kind of recurrent neural network that is capable of learning long-term dependencies in data. This is achieved because the recurring module of the model has a combination of four layers interacting with each other11:31 AM.
The ability to anticipate the event before it actually happens affects a lot, and the more the model can anticipate it for a longer period, the better it is to try to avoid losses that may occur, whether for institutions or lives.
▲
Space Agency Data
NASA Space apps resources.
Hackathon Journey
The first day we made an android app that works with static data and the second day we worked on a presentation and AI model that predict the date of the event and explain its data.
References
https://cdaweb.gsfc.nasa.gov/pub/data/dscovr/h0/mag/2022/
Tags
#event