solar-flare-prediction

The SWAN-SF dataset is now fully preprocessed, optimized, and ready for binary classification tasks. Our team is excited to release the enhanced version of the SWAN-SF dataset across all five partitions.

Study solar flares and other phenomena using data from ISRO's Aditya-L1 space observatory

Accurate solar flare prediction is crucial for mitigating risks to astronauts, space equipment, and satellite communication. Our study enhances prediction accuracy using advanced preprocessing and a novel deep learning-based classifier called ContReg on the SWAN-SF dataset, outperforming previous methods.

FlaPLeT is an open-source, full-stack web platform that enables end-to-end machine learning workflows for solar flare prediction through an interactive user interface. Its modular design also provides a general blueprint for AI-driven web services, such as large language model applications, where asynchronous task execution is essential.

These notebooks provide a comprehensive workflow, from start to finish, for processing and analyzing the SWAN-SF dataset. They include detailed steps for reading the dataset files, performing full preprocessing, and executing classification.

By analyzing the results of this project, we can identify the most effective data preprocessing techniques and classifiers, ultimately leading to the development of a highly accurate solar flare prediction model.

AI-powered mission control dashboard that predicts X-Class solar flares from ISRO Aditya-L1 (SoLEXS/HEL1OS) telemetry using a Neupert-Effect-informed Random Forest model, with a live 3D magnetosphere visualization.

On March 7, 2012, active region 11429 produced an X5.4 flare (00:02 UTC).

An end-to-end machine learning project that predicts solar flare intensity using NASA's DONKI space weather dataset, enabling data-driven forecasting of events that can affect satellites, GPS systems, and power infrastructure.

CONTREX, a novel contrastive representation learning approach for multivariate time series data.