Introduction

The Carrington Event, which occurred between September 1 and 2, 1859, during solar cycle 10, was the most powerful geomagnetic storm ever recorded.It caused sparking and even fires in multiple telegraph stations and produced powerful auroral displays that were reported worldwide. A coronal mass ejection (CME) from the Sun that came into contact with Earth's magnetosphere was most likely the cause of the geomagnetic storm.

Objective

If a major space weather event like the Carrington Event of 1859 were to occur today, the impacts to society could be devastating. Your challenge is to develop a machine learning algorithm or neural network pipeline to correctly track changes in the peak solar wind speed and provide an early warning of the next potential Carrington-like event.

Data

In the given dataset we got many attributes that got to be dealt in different ways, but first we take our numeric attribute and plot them to understand our data set we considered attributes like "bx_gse", "bx_gsm", "bt", "density", "speed" and "temperature"

Frequency of Speed w.r.t bx_gse

In this picture when we plot the bx_gse on the basis of solar winds can actually see the relation of speed and bx_gse the maximum count of speed according to this plot is 8

Frequency of Speed w.r.t by_gse

In this picture when we plot the bx_gse on the basis of solar winds can actually see the relation of speed and by_gse the maximum count of speed according to this plot is 7

Frequency of Speed w.r.t bz_gse

In this picture when we plot the bx_gse on the basis of solar winds can actually see the relation of speed and bz_gse the maximum count of speed according to this plot is 7

Frequency of Speed w.r.t density and temperature

As we can se from the initial study of database and scientific knowledge that density and temperature plays a very vital role in the frequency of speed to relation of density and temperature can be acknowledged by this plot

Frequency of density w.r.t bt and speed

As we can se from the initial study of database and scientific knowledge that density and bt plays a very vital role in the frequency of speed to relation of density and bt can be acknowledged by this plot which tells us that when bt and density are low the speed is high

Frequency of temperature w.r.t density and speed

As we can se from the initial study of database and scientific knowledge that density and temperature plays a very vital role in the frequency of speed to relation of density and temperature can be acknowledged by this plot which tells us that when bt and temperature are low the speed is high

Model Training by Machine Learning Algorithms

Based on the analysis and visualization we have trained our model based on the regression Algorithms for which we have used Linear Regression,Ridge and Losso , it tells us by the help of the plot that Linear Regression produces the most accurate r2 score

Conclusion

As we got the data of solar winds we first got to remove all the null values from the data and also take the data that comes from sourc disocvr after, after all the preprocessing we did some visualization we got us to the results that, when bt and density are low the speed is high and when bt and temperature are low the speed is high. which means that low temperature,density and bt often lead us to the peak in speed of solar wind that lead to geomagnetic storms like carrington event and also w proved our point by training our model via using diffierent model among which Linear Regression algorithm was giving the optimal results.