AI reshapes how we observe the stars
Peer-Reviewed Publication
Updates every hour. Last Updated: 2-May-2025 10:57 ET (2-May-2025 14:57 GMT/UTC)
AI tools are transforming how we observe the world around us — and even the stars beyond. Recently, an international team proved that deep learning techniques and large language models can help astronomers classify stars with high accuracy and efficiency. Their study, “Deep Learning and Methods Based on Large Language Models Applied to Stellar Light Curve Classification,” was published Feb. 26 in Intelligent Computing, a Science Partner Journal.
Josephson microwave microscopy integrating Josephson junctions onto a nanoprobe enables spectroscopic imaging of near-field microwave with a broad bandwidth, presenting a non-destructive technique to characterize microwave devices.
Full Waveform Inversion (FWI) is capable of finely characterizing the velocity structure, anisotropy, viscoelasticity, and attenuation properties of subsurface media, which provides critical constraints for scientific problems such as understanding the Earth’s internal structure and material composition, earthquake preparation and occurrence, and plate motion and dynamic processes. In recent years, with advancements in high-performance computing platforms, improvements in numerical methods, and the cross-integration of multidisciplinary, FWI has demonstrated broad application prospects in deep underground structure exploration, resource and energy exploration, engineering geophysics, and even medical imaging. In this paper, we provide a comprehensive review and analysis of the development of the FWI method, addressing its current challenges, identifying key issues, future directions, and potential research areas in the theory, methodology, and application of high-resolution FWI imaging. The related findings were published in SCIENCE CHNIA: Earth Science, 68(2): 315‒342, 2025.