在训练自回归模拟器时，硬守恒校正器可能会掩盖模型的退化
Hard conservation correctors can hide a degrading model when training autoregressive emulators
浏览论文内容
中文总结 AI 辅助
研究AI天气和气候模拟器中硬守恒校正器掩盖模型退化问题，通过微调全球大气模拟器并结合水预算校正器训练，发现尺度简并致原始降水偏差增大，两项改变恢复稳定，强调校正时要跟踪原始场和校正，精确闭合不能说明模型是否学懂预算。
中文摘要 AI 辅助
人工智能天气和气候模拟器越来越多地将物理原理纳入其公式中。一种方法是应用硬校正器来修改网络输出，以使全球质量、水或能量预算闭合。先前的工作在CREDIT框架中引入了这种训练时校正器，并报告了降水偏差的减少和稳定性的提高。受这些结果的启发，我们使用水预算校正器对全球大气模拟器进行了微调，在监督损失中使用校正后的预测，并通过校正后的预算闭合进行评估。从这个角度来看，训练似乎是成功的。每个输出场都将水分预算闭合到机器精度。然而，在18个训练周期中，原始降水出现了越来越大的全球低偏差，而所需的校正从约2%增加到约24%。原因是尺度简并。原始降水幅度的均匀变化被校正因子的补偿变化抵消，使校正后的场以及监督损失保持不变。这种不变性消除了对原始降水幅度的恢复力，允许其他训练压力驱动漂移。两项改变恢复了稳定行为。我们监督校正前的预测并惩罚其原始预算不平衡，而硬校正则保留在输出场中。在下一个周期内，所需的校正恢复到小于1%。一个受控的2x2消融实验表明，只有在校正输出监督与无不平衡惩罚相结合时才会出现失控情况。因此，精确的校正后闭合对于原始模型是否学习了预算几乎没有说明。当校正器从损失中去除信息时，需要跟踪原始场和应用的校正。
英文摘要
AI weather and climate emulators increasingly incorporate physical principles into their formulation. One approach is to apply hard correctors that modify network outputs so that global mass, water, or energy budgets close. Prior work introduced such training-time correctors in the CREDIT framework and reported reduced precipitation bias and improved stability. Motivated by those results, we fine-tuned a global atmosphere emulator with a water-budget corrector, using the corrected prediction in the supervised loss and evaluating through post-correction budget closure. By that measure, training appeared successful. Every delivered field closed the moisture budget to machine precision. However, raw precipitation developed a growing global low bias over 18 training epochs, while the required correction increased from about 2% to roughly 24%. The cause is a scale degeneracy. A uniform change in raw precipitation amplitude is offset by a compensating change in the correction factor, leaving the corrected field, and therefore the supervised loss, unchanged. This invariance removes the restoring force on raw precipitation amplitude, allowing other training pressures to drive drift. Two changes recovered stable behavior. We supervised the pre-correction prediction and penalized its raw budget imbalance, while the hard correction remained in place for the delivered field. The required correction returned to less than 1% within the next epoch. A controlled 2x2 ablation showed that the runaway occurred only when corrected-output supervision was combined with no imbalance penalty. Exact post-correction closure therefore says little about whether the raw model has learned the budget. When a corrector removes information from the loss, the raw fields and the applied correction need to be tracked.
