CNN-based anomaly signal detection for telescopes

Anomaly signal detection is particularly crucial in the field of astronomy, especially for monitoring signals from telescopes. With advancements in astronomical observation technology, the cosmic signals captured by telescopes have become increasingly complex, concealing significant scientific information related to phenomena such as supernova explosions and black hole mergers. Traditional anomaly detection methods often struggle to address these intricate signals, highlighting the urgent need for advanced artificial intelligence techniques. This paper introduces an end-to-end astronomical telescope signal detection method based on Convolutional Neural Networks (CNNs). Experiments conducted on the SETI dataset achieved a detection accuracy of 87%, demonstrating the model's effectiveness in processing complex cosmic signals. The research indicates that CNNs can automatically extract signal features, adapt to dynamic signal environments, and efficiently process vast amounts of data, thereby uncovering potential anomalies.