Multivariate forecasting in physical systems requires models that predict coupled temporal variables while preserving meaningful state evolution. Deep forecasters can fit temporal correlations, and physics-informed models can regularize predictions with scientific constraints, but these directions are often connected only at the decoded-output level. As a result, the hidden predictive state that generates future trajectories may remain statistically useful but physically unstructured. We introduce Phys-JEPA, a physics-informed joint-embedding predictive architecture for multivariate time-series forecasting. Phys-JEPA learns a latent world model in which predictive states are decomposed into physical and residual components, and physical consistency is imposed directly on latent states and latent transitions rather than only on decoded forecasts. This formulation uses known physical variables to organize the representation space while retaining residual capacity for unresolved dynamics. On Jena Climate 2009--2016, Phys-JEPA reduces aggregate MSE from 0.12482 to 0.12273 and temperature MSE from 0.01892 to 0.01831 at H=24. On Traffic, full Phys-JEPA improves aggregate MSE over the supervised baseline across all tested horizons, reducing H=192 MSE from 0.800784 to 0.773873. On Electricity, the best variant depends on horizon: static latent consistency is strongest at H=24 and H=48, while full Phys-JEPA gives the best aggregate and target-variable MSE at H=192. These initial results suggest that moving physics-informed learning from output space to latent predictive state space is a promising direction for interpretable temporal world models.

翻译：物理系统中的多元预测要求模型在保持有意义的状态演化的同时，对耦合的时间变量进行预测。深度预测模型能够拟合时间相关性，物理信息模型可通过科学约束正则化预测结果，但这些方向通常仅在解码输出层面建立联系。因此，生成未来轨迹的隐藏预测状态可能具有统计有效性，但缺乏物理意义上的结构性。我们提出Phys-JEPA——一种面向多元时间序列预测的物理信息联合嵌入预测架构。该架构学习潜在世界模型，将预测状态分解为物理分量与残差分量，并直接在潜在状态及潜在转换上施加物理一致性约束，而非仅作用于解码预测。该方法利用已知物理变量组织表征空间，同时保留对未解析动力学的残差容限能力。在Jena气候2009-2016数据集上，H=24时Phys-JEPA将聚合MSE从0.12482降至0.12273，温度MSE从0.01892降至0.01831。在Traffic数据集上，完整Phys-JEPA在所有测试预测跨度上均优于监督基线聚合MSE，将H=192时的MSE从0.800784降至0.773873。在Electricity数据集上，最优变体取决于预测跨度：H=24及H=48时静态潜一致性表现最佳，而H=192时完整Phys-JEPA在聚合MSE与目标变量MSE上均达最优。这些初步结果表明，将物理信息学习从输出空间迁移至潜在预测状态空间，是构建可解释时间世界模型的富有前景的研究方向。