Machine learning is playing an increasing role in hydrology, supplementing or replacing physics-based models. One notable example is the use of recurrent neural networks (RNNs) for forecasting streamflow given observed precipitation and geographic characteristics. Training of such a model over the continental United States has demonstrated that a single set of model parameters can be used across independent catchments, and that RNNs can outperform physics-based models. In this work, we take a next step and study the performance of RNNs for river routing in land surface models (LSMs). Instead of observed precipitation, the LSM-RNN uses instantaneous runoff calculated from physics-based models as an input. We train the model with data from river basins spanning the globe and test it in streamflow hindcasts. The model demonstrates skill at generalization across basins (predicting streamflow in unseen catchments) and across time (predicting streamflow during years not used in training). We compare the predictions from the LSM-RNN to an existing physics-based model calibrated with a similar dataset and find that the LSM-RNN outperforms the physics-based model. Our results give further evidence that RNNs are effective for global streamflow prediction from runoff inputs and motivate the development of complete routing models that can capture nested sub-basis connections.

翻译：机器学习在水文学中扮演着日益重要的角色，补充或替代基于物理的模型。一个显著的例子是利用循环神经网络（RNNs）根据观测到的降水和地理特征预测径流。在全美大陆范围内对该类模型的训练表明，单一组模型参数可适用于独立集水区，且RNN的性能可超越基于物理的模型。本研究进一步探索了RNN在陆面模型（LSMs）河流汇流模拟中的表现：与使用观测降水不同，LSM-RNN以基于物理模型计算的瞬时径流作为输入。我们利用全球多个流域的数据训练模型，并在径流后报模拟中测试其性能。该模型在跨流域泛化（预测未观测集水区的径流）和跨时间泛化（预测训练年份外的径流）方面均展现出优越能力。我们将LSM-RNN的预测结果与基于相似数据集校准的现有物理模型进行对比，发现LSM-RNN表现更优。我们的结果进一步证明RNN在基于径流输入的全球径流预测中具有有效性，并推动了可捕捉嵌套子流域连接的完整汇流模型开发。