Interpretable Framework of Physics‐Guided Neural Network With Attention Mechanism: Simulating Paddy Field Water Temperature Variations
Interpretable Framework of Physics‐Guided Neural Network With Attention Mechanism: Simulating Paddy Field Water Temperature Variations
复制标题
DOI：
10.1029/2021wr030493
复制
发表时间：
2022-05
影响因子：
5.4
通讯作者：
W. Xie;M. Kimura;K. Takaki;Y. Asada;T. Iida;X. Jia
中科院分区：
文献类型：
--
作者：
W. Xie;M. Kimura;K. Takaki;Y. Asada;T. Iida;X. Jia
随着东亚大规模水稻种植管理举措的发展，人们担心单位面积人类耕作人数的减少可能导致水资源管理不善，这可能导致土地生产力下降，因为异常的高温和低温会对作物造成损害。准确模拟稻田水温对于研究其对作物的影响以及提供及时的信息以帮助决策以在有限的资源下进行更有效的管理非常重要。我们提出了一个神经网络框架，该框架考虑了植被冠层的热传递，并在其训练中应用物理理论约束。提出了一种新的调谐方法，以科普训练过程中水温精度和物理一致性之间的权衡，以确保计算的稻田水温变化具有高精度和物理一致性。在实验中，所提出的框架优于物理过程模型和纯神经网络模型，同时保持高精度的稀疏数据集的情况下。此外，注意力机制输入层被集成到模型中以排名特征重要性，为所提出的框架提供全局解释。我们还对物理过程进行了敏感性分析，并提出了模型来比较它们不同的特征排序策略。结果表明，这两种方法对不同的特征模式有不同的敏感性，但它们是相辅相成的。综上所述，所提出的模型是可靠的和稳定的实际应用，并有可能指导更有效的水稻管理。
With the development of large‐scale rice cultivation management initiatives in East Asia, there is concern that a reduction in the number of human cultivators per unit area may lead to poor water management, which could result in decreased land productivity, owing to abnormally high‐ and low‐temperature damage to crops. Accurate simulation of paddy field water temperature is important for studying its impact on crops and providing timely information to aid in decision‐making for more efficient management under limited resources. We propose a neural‐network framework that considers the heat transfer by the vegetation canopy and applies physical‐theory constraints in its training. A novel tuning method is proposed to cope with the trade‐off between water temperature accuracy and physical consistency during training to ensure that the calculated water temperature variations in a paddy field enjoy high accuracy and physical consistency. In the experiments, the proposed framework outperforms physical process models and pure neural network models while maintaining high accuracy in the case of sparse data sets. Furthermore, an attention‐mechanism input layer is integrated into the model to rank feature importance, providing global interpretation to the proposed framework. We also perform sensitivity analysis on the physical process and propose models to compare their different strategies of feature ranking. The results show that the two methods have different sensitivities to different feature patterns, but they complement each other. In summary, the proposed model is credible and stable for practical applications and has the potential to guide more efficient paddy management.