Assessing the Physical Realism of Deep Learning Hydrologic Model Projections Under Climate Change
Assessing the Physical Realism of Deep Learning Hydrologic Model Projections Under Climate Change
复制标题
DOI：
10.1029/2022wr032123
复制
发表时间：
2022-08
影响因子：
5.4
通讯作者：
S. Wi;S. Steinschneider
中科院分区：
文献类型：
--
作者：
S. Wi;S. Steinschneider
这项研究探讨了深度学习模型是否可以在变暖的情况下产生可靠的未来流量预测。我们在加州的15个流域训练了一个区域性的长短期记忆网络（LSTM），并开发了三个过程模型（HYMOD、SAC‐SMA和维克）作为基准。我们迫使所有模型与变暖的情况下，并评估其水文响应，包括在过程线和总径流比的变化。所有的过程模型都显示出更多的冬季径流，夏季径流减少，径流比下降，由于蒸散量增加。LSTM预测了类似的过程线变化，但在某些流域预测了径流率的不切实际的增加。然后，我们测试了LSTM的两个替代版本，其中流程模型输出被用作额外的训练目标（即，多输出LSTM）或输入功能。结果表明，多输出LSTM并不能纠正变暖下不切实际的径流预测。混合LSTM使用SAC‐SMA的蒸散估计作为额外的输入特征，产生更真实的径流预测，但这不适用于维克或HYMOD。这表明混合方法依赖于过程模型的保真度。最后，我们在一个经过训练的LSTM下测试了美国500多个流域的气候变化响应，并在变暖的情况下找到了更现实的径流预测。最终，这项工作表明，混合建模可能支持使用LSTM水文预测气候变化下，但也可以培训LSTM一个大的，不同的集水区。
This study examines whether deep learning models can produce reliable future projections of streamflow under warming. We train a regional long short‐term memory network (LSTM) to daily streamflow in 15 watersheds in California and develop three process models (HYMOD, SAC‐SMA, and VIC) as benchmarks. We force all models with scenarios of warming and assess their hydrologic response, including shifts in the hydrograph and total runoff ratio. All process models show a shift to more winter runoff, reduced summer runoff, and a decline in the runoff ratio due to increased evapotranspiration. The LSTM predicts similar hydrograph shifts but in some watersheds predicts an unrealistic increase in the runoff ratio. We then test two alternative versions of the LSTM in which process model outputs are used as either additional training targets (i.e., multi‐output LSTM) or input features. Results indicate that the multi‐output LSTM does not correct the unrealistic streamflow projections under warming. The hybrid LSTM using estimates of evapotranspiration from SAC‐SMA as an additional input feature produces more realistic streamflow projections, but this does not hold for VIC or HYMOD. This suggests that the hybrid method depends on the fidelity of the process model. Finally, we test climate change responses under an LSTM trained to over 500 watersheds across the United States and find more realistic streamflow projections under warming. Ultimately, this work suggests that hybrid modeling may support the use of LSTMs for hydrologic projections under climate change, but so may training LSTMs to a large, diverse set of watersheds.