We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (K_eff) of a binary K grid. A deep learning algorithm (UNET) can infer K_eff with extremely high accuracy (R² > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained directly on this information. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems.

中文翻译：

---

深度学习能否从网格化传导场中提取有关能量耗散和有效水力传导率的有用信息？

我们确认能量耗散加权提供了最准确的方法来确定二元 K 网格的有效水力传导率 (K _eff )。深学习算法（UNET）可以推断ķ _EFF以极高的精度（R ²> 0.99）。可以训练 UNET 架构从 K 分布的图像推断能量耗散加权模式，尽管对于控制流动的高度局部化结构的情况不太准确。此外，UNET 架构学会了推断能量耗散权重，即使它没有直接根据此信息进行训练。然而，权重在 UNET 中以一种人类用户无法立即解释的方式表示。这重申了这样一种观点，即即使 ML/DL 算法经过训练可以准确地进行一些水文预测，如果要将其结果用于提高我们对水文系统的理解，它们也必须经过设计和训练以提供每个用户所需的输出。