Enhancing Geomagnetic Disturbance Predictions with Neural Networks: A Case Study on K-Index Classification

Abstract

To explore the application of neural networks for estimating geomagnetic field disturbances, this study pays particular attention to K-index classification. The primary goal is to develop a robust and efficient method for classifying different levels of geomagnetic activity using neural networks. Our work encompasses data preprocessing, model architecture optimization, and a thorough evaluation of classification performance. A new neural-network approach is proposed to address the specific complexities of geomagnetic data, and its merits are compared with those of conventional techniques. Notably, Long Short-Term Memory (LSTM) models significantly outperformed traditional methods, achieving up to 98% classification accuracy. These findings demonstrate that neural networks can be effectively applied in geomagnetic studies, supporting AI-based forecasting and enabling further integration into space weather research