Detecting Anomalies in James Webb Space Telescope (JWST) Data Using Machine Learning: A Study on Data Integrity for Science and Security

This research investigates the importance of ensuring the integrity and reliability of astronomical data collected by the James Webb Space Telescope (JWST). Using machine learning–based anomaly detection models, this study identifies irregular patterns in JWST datasets such as time series, images, and spectra to detect potential anomalies or data manipulation attempts. The findings demonstrate accuracy rates above 87% across all data types, highlighting the importance of AI-driven quality assurance in astrophysical data pipelines. This work contributes to both scientific advancement and cybersecurity awareness in the context of space data processing. The associated project and codebase are available at GitHub.