Accurate evaluation of evapotranspiration (ET) is crucial for efficient agricultural water management. Data-driven models exhibit strong predictive ET capabilities, yet significant limitations like naive extrapolation hamper wider generalization. In this perspective, we explore a novel hybrid deep learning (DL) framework to integrate domain knowledge and demonstrate its potential for evaluating ET under the influence of soil salinity. Specifically, we integrated physical constraints from process models (Penman-Monteith or Shuttleworth-Wallace) and salinity-induced stomatal stress mechanisms into the DL algorithm, and evaluated its performance by comparing four diverse scenarios. Results demonstrate that hybrid DL framework offers a promising alternative for ET estimation, achieving comparable accuracy to pure DL during training and validation. Nonetheless, due to the limited available measurements, data-driven model may not adequately capture plant responses to salt stress, leading to significant prediction biases observed during independent testing. Encouragingly, the hybrid DL model (DL-SS) integrating Shuttleworth-Wallace and salinity-induced stomatal stress mechanisms demonstrated enhanced interpretability, generalizability, and extrapolation capabilities. During testing, DL-SS consistently showed optimal performance, yielding root mean square error (RMSE) values of 37.4 W m⁻² for sunflower and 39.2 W m⁻² for maize. Compared to traditional Jarvis-type approaches (JPM and JSW) and pure DL model during testing, DL-SS achieved substantial reductions in RMSE values: 51%, 33%, and 43% for sunflower, and 45%, 31%, and 35% for maize, respectively. These findings highlight the importance of integrating prior scientific knowledge into data-driven models to enhance extrapolation capability of ET modeling, especially in salinized regions where conventional models may struggle.

中文翻译：

---

考虑土壤盐度影响的用于评估田间蒸散的新型混合深度学习框架


准确评估蒸散量（ ET ）对于高效的农业用水管理至关重要。数据驱动模型表现出强大的预测ET能力，但朴素外推等重大限制阻碍了更广泛的推广。从这个角度来看，我们探索了一种新颖的混合深度学习（ DL ）框架来整合领域知识，并展示其在土壤盐分影响下评估蒸散的潜力。具体来说，我们将过程模型（Penman-Monteith 或 Shuttleworth-Wallace）的物理约束和盐度引起的气孔应力机制集成到深度学习算法中，并通过比较四种不同的场景来评估其性能。结果表明，混合深度学习框架为ET估计提供了一种有前途的替代方案，在训练和验证过程中实现了与纯深度学习相当的准确性。尽管如此，由于可用的测量有限，数据驱动模型可能无法充分捕捉植物对盐胁迫的反应，导致在独立测试期间观察到显着的预测偏差。令人鼓舞的是，整合 Shuttleworth-Wallace 和盐度诱导的气孔应激机制的混合深度学习模型 ( DL-SS ) 表现出增强的可解释性、普遍性和外推能力。在测试过程中， DL-SS始终表现出最佳性能，向日葵的均方根误差 ( RMSE ) 值为 37.4 W m ^-2 ，玉米的均方根误差 (RMSE) 值为 39.2 W m ^-2 。 与测试期间的传统 Jarvis 型方法（ JPM和JSW ）和纯DL模型相比， DL-SS实现了RMSE值的大幅降低：向日葵降低了 51%、33% 和 43%，向日葵降低了 45%、31% 和 35%分别为玉米的％。这些发现强调了将先验科学知识整合到数据驱动模型中以增强ET建模的外推能力的重要性，特别是在传统模型可能难以应对的盐碱化地区。