Ocean general circulation models (OGCMs) are essential to climate science but computationally expensive, limiting ensemble size and forcing scenarios. Neural emulators promise orders-of-magnitude speedups, yet existing ocean emulators have not combined fine spatial resolution with multi-year autoregressive rollouts. Samudra, the first autoregressive neural ocean emulator to produce multi-decade global rollouts, is limited to $1^\circ$ resolution and exhibits two long-horizon failure modes: \emph{variance collapse}, the loss of temporal variability, and \emph{imprinting artifacts}, in which velocity patterns leak into deep-ocean fields. We present Samudra 2, which introduces a wider U-Net backbone with modified ConvNeXt-style blocks and a reduced block-internal expansion factor, together with a dynamic loss that reweights output channels according to their prediction errors, strengthening gradients for slow-evolving deep-ocean fields. At $1^\circ$, Samudra 2 increases upper-ocean global-mean temperature $R^2$ from 0.56 to 0.87 and reduces deep-ocean temperature error by roughly sevenfold. The same architecture scales to $1/2^\circ$ and $1/4^\circ$ over approximately 8-year autoregressive rollouts, recovering mesoscale eddies and sharp western boundary currents. Running on a single GPU, Samudra 2 enables larger ensembles for sea-level projections, ocean heat uptake, and climate variability studies. We provide code, documentation, and benchmark resources at https://openathena.ai/Ocean_Emulator/.

翻译：海洋环流模式（OGCMs）是气候科学的核心工具，但其计算成本高昂，限制了集合规模和强迫场景的规模。神经仿真器有望实现数个数量级的加速，然而现有的海洋仿真器未能将精细空间分辨率与多年自回归推演相结合。Samudra作为首个能生成数十年全球自回归推演的神经海洋仿真器，仅局限于1°分辨率，并存在两种长期推演失效模式：方差崩溃（时间变率丧失）与印记伪影（速度模式渗入深海场）。我们提出Samudra 2，其通过引入更宽的U-Net主干网络（采用改进的ConvNeXt-style模块并降低模块内部扩张因子），以及根据预测误差对输出通道重新加权（增强缓慢演化深海场的梯度）的动态损失函数，实现了架构革新。在1°分辨率下，Samudra 2将上层海洋全球平均温度的R²从0.56提升至0.87，并将深海温度误差降低约七倍。相同架构可扩展至1/2°和1/4°分辨率，支持约8年自回归推演，成功恢复中尺度涡旋与强西边界流。基于单GPU运行，Samudra 2为海平面预估、海洋热吸收及气候变率研究提供了更大规模的集合模拟能力。我们已在https://openathena.ai/Ocean_Emulator/公开代码、文档及基准测试资源。