This project was inspired by the fascinating patterns observed in the sunspot activity recorded over centuries. Sunspots, which are regions on the Sun's surface that appear darker due to lower temperatures, have been closely linked to solar phenomena that can have significant impacts on earth. Understanding and forecasting these activities can aid in preparing for solar events that affect satellite communications, weather patterns, and even power grids.
The project employs a comparative approach, utilizing various machine learning and deep learning techniques to forecast sunspot activity. Each model, including GNN, LSTM, RNN, and XGBoost, was trained on historical sunspot data, evaluated for accuracy, and fine-tuned for optimal performance.
Before we start training our models, let's explore the data and understand the patterns in sunspot activity. We need to clean the data by:
The comparative analysis revealed that while each model brought unique strengths to the forecasting task, the LSTM model demonstrated a superior balance of accuracy and efficiency. Detailed results and model comparisons are presented, showcasing the predictive capabilities and potential areas for improvement.
This project not only enhances our understanding of sunspot cycles but also contributes to the broader field of astrophysics by providing reliable forecasting tools. These insights can help mitigate the adverse effects of solar phenomena on modern technology and society.
