YU-CHIAO LIANGLutsko, Nicholas J.Nicholas J.LutskoKwon, Young‐OhYoung‐OhKwon2025-12-312025-12-312025-11https://www.scopus.com/pages/publications/105021546439https://scholars.lib.ntu.edu.tw/handle/123456789/734916The rapid loss of Arctic sea ice is a striking consequence of anthropogenic global warming. Its remote impacts on mid-latitude weather and climate have attracted scientific and media attention. In this study, we use a hybrid (dynamical plus machine-learning) atmospheric model—Google's NeuralGCM—to investigate the mid-latitude atmospheric circulation responses to Arctic sea-ice loss for the first time. We conduct experiments in which NeuralGCM is forced with pre-industrial and future sea-ice concentrations following the protocol of the Polar Amplification Model Intercomparisom Project. To assess the performance of NeuralGCM, we compare the results with those simulated by two physics-based climate models. NeuralGCM produces a comparable response of near-surface warming to sea-ice loss and the subsequent weakened zonal wind in mid-latitudes. However, there is a substantial discrepancy between the two models' stratospheric responses, where different temperature responses in these models are associated with different zonal wind and geopotential height responses. Further investigation of North Atlantic blocking shows that NeuralGCM produces stronger, more frequent, and more realistic blocking events. Our results demonstrate the capability of NeuralGCM in simulating the tropospheric responses to Arctic sea-ice loss, but improvements may be needed for the stratospheric representation.Arctic sea-ice losshybrid modelmachine-learning atmospheric modeljournal article10.1029/2025ms005264