In the era of global space industry's rapid expansion, reusable launch technology addresses cost reduction, but achieving high launch cadence and flight reliability remains critical. This study published in the Chinese Journal of Aeronautics (Volume 38, Issue 10, October 2025, https://doi.org/10.1016/j.cja.2025.103756), proposes that artificial intelligence (AI) would be the potential disruptive technology to solve these challenges. AI enables transformative capabilities for launch vehicles are pointed out in four domains: Agile launch operations enabling automate testing, fault diagnosis, and decision-making for targeting hour-level launch cycles and minute-level fault resolution; High-reliability flight enabling real-time autonomous fault diagnosis, mission replanning, and fault-tolerant control within seconds during anomalies, potentially improving reliability by 1-2 orders of magnitude; Rapid maintenance enabling real-time health monitoring and lifespan prediction for swift re-launch decisions; and Efficient space traffic management enabling predict/resolve orbital conflicts amid growing congestion from satellites and debris. The key challenges for AI applications are analyzed as well, including multi-system coupling, uncertain failure modes and narrow flight corridors, limited sensor data, and massive heterogeneous data processing. Finally, the study also proposes that AI promises substantial efficiency gains in launch vehicle design, manufacturing, and testing through multidisciplinary optimization and reduced reliance on physical testing.

A new study by researchers at the Icahn School of Medicine at Mount Sinai suggests that artificial intelligence (AI) could help predict which critically ill patients on ventilators are at risk of underfeeding, potentially enabling clinicians to adjust nutrition early and improve patient care. Details of the study were published in the December 17 online issue of Nature Communications.

New simulator and computational tool generate realistic “virtual tissues” and map cell-to-cell “conversations” from spatial transcriptomics data.

The tools could accelerate AI-driven discoveries in cancer, brain disorders and precision medicine by revealing which genes control how cells interact.