Enhancing process-based hydrological models with embedded neural networks: A hybrid approach
Enhancing process-based hydrological models with embedded neural networks: A hybrid approach
复制标题
DOI：
10.1016/j.jhydrol.2023.130107
复制
发表时间：
2023-09-06
影响因子：
6.4
通讯作者：
Ni，Guangheng
中科院分区：
文献类型：
--
作者：
Li，Bu;Sun，Ting;Ni，Guangheng
深度学习（DL）模型在水文建模方面表现出卓越的性能;然而，与基于过程的水文模型相比，它们无法输出未经训练的水文变量，并且缺乏可解释性。我们提出了一种混合的方法，结合了嵌入式神经网络（恩斯）的概念EXP-Hydro模型，取代其内部模块，同时保持坚持水文知识。由此产生的混合模型可以预测未经训练的水文变量，而不需要后处理或预训练程序。我们使用CAMELS数据集测试了15个混合模型，这些模型取代了美国连续569个流域的不同内部模块。进行了额外的实验，以概括水文关系内恩斯，并进一步使用它们来提高EXP-Hydro模型的性能。结果表明，所有混合场景的性能都优于普通的EXP-Hydro模型，在评估期内的最佳中值Nash-Sutcliffe效率（NSE）为0.701，与最先进的LSTM和具有纠错后处理器的概念水文模型相当。径流和雪相关过程的合理模式被捕获的恩斯在各自的混合模式。我们进一步使用径流（雪相关）模式，以改善普通的EXP-Hydro模型，中值N S E从0.496增加到0.567（提高中值N S E从0.601到0.677在雪影响区）。我们的研究强调了使用恩斯在增强基于过程的水文模型的性能，同时保持在一个新的混合框架内的可解释性的潜力。
Deep learning (DL) models have demonstrated exceptional performance in hydrological modeling; however, they are limited by their inability to output untrained hydrological variables and lack of interpretability compared to process-based hydrological models. We propose a hybrid approach that combines the conceptual EXP-Hydro model with embedded neural networks (ENNs), replacing its internal modules while maintaining adherence to hydrological knowledge. The resulting hybrid model can predict untrained hydrological variables without requiring post-processing or pre-training procedures. We tested 15 hybrid models that replace different internal modules across 569 basins in the contiguous United States using the CAMELS dataset. Additional experiments were conducted to generalize hydrological relationships within ENNs and further use them to improve the EXP-Hydro model's performance. Results show that all hybrid scenarios outperform the ordinary EXP-Hydro model, with an optimal median Nash-Sutcliffe efficiency (NSE) of 0.701 in the evaluation period–comparable to state-of-the-art LSTM and conceptual hydrological model featuring an error-correcting post-processor. Reasonable patterns of runoff and snow-related processes are captured by ENNs in respective hybrid models. We further used the runoff (snow-related) pattern to improve the ordinary EXP-Hydro model with median N S E increasing from 0.496 to 0.567 (raising median N S E from 0.601 to 0.677 in snow-influenced region). Our study highlights the potential for using ENNs in enhancing process-based hydrological models' performance while maintaining interpretability within a novel hybrid framework.