The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment
The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment
复制标题
DOI：
10.5194/hess-27-2357-2023
复制
发表时间：
2023-06
影响因子：
6.3
通讯作者：
D. Feng;H. Beck;K. Lawson;Chaopeng Shen
中科院分区：
文献类型：
--
作者：
D. Feng;H. Beck;K. Lawson;Chaopeng Shen
抽象的。作为一种基于物理学的机器学习类型，具有区域化的基于深度网络的参数化管道的基于可微过程的水文模型（简称δ或三角洲模型）最近被证明可以提供接近最先进的长短期记忆（LSTM）深度网络的每日径流预测性能。与此同时，δ模型提供了一整套诊断物理变量，并保证了质量守恒。在这里，我们进行了实验，以测试（1）他们的能力外推到地区远离流量计和（2）他们的能力，使长期（十年尺度）变化趋势的可靠预测。我们根据日过程线指标（Nash-Sutcliffe模型效率系数等）对模型进行了评估。并预测了十年径流趋势。对于无资料盆地（PUB;代表空间插值的随机采样无资料盆地）的预测，δ模型在每日过程线度量方面接近或超过LSTM的性能，这取决于所使用的气象强迫数据。对于年平均流量和高流量，它们的趋势性能与LSTM相当，但对于低流量，趋势更差。对于无资料地区的预测（PUR;在高度数据稀疏的情况下代表空间外推的区域保持测试），δ模型在日过程度量方面超过了LSTM，它们在平均和高流量趋势方面的优势变得突出。此外，一个未经训练的变量，蒸散量，保留良好的季节性，即使外推的情况下。δ模型的基于深层网络的参数化管道产生的参数字段即使在高度数据稀缺的情况下也能保持非常稳定的空间模式，这解释了它们的鲁棒性。δ模型具有可解释性和吸收多源观测数据的能力，是区域和全球尺度水文模拟和气候变化影响评估的有力候选者。
Abstract. As a genre of physics-informed machine learning, differentiable process-based hydrologic models (abbreviated as δ or delta models) with regionalized deep-network-based parameterization pipelines were recently shown to provide daily streamflow prediction performance closely approaching that of state-of-the-art long short-term memory (LSTM) deep networks. Meanwhile, δ models provide a full suite of diagnostic physical variables and guaranteed mass conservation. Here, we ran experiments to test (1) their ability to extrapolate to regions far from streamflow gauges and (2) their ability to make credible predictions of long-term (decadal-scale) change trends. We evaluated the models based on daily hydrograph metrics (Nash–Sutcliffe model efficiency coefficient, etc.) and predicted decadal streamflow trends. For prediction in ungauged basins (PUB; randomly sampled ungauged basins representing spatial interpolation), δ models either approached or surpassed the performance of LSTM in daily hydrograph metrics, depending on the meteorological forcing data used. They presented a comparable trend performance to LSTM for annual mean flow and high flow but worse trends for low flow. For prediction in ungauged regions (PUR; regional holdout test representing spatial extrapolation in a highly data-sparse scenario), δ models surpassed LSTM in daily hydrograph metrics, and their advantages in mean and high flow trends became prominent. In addition, an untrained variable, evapotranspiration, retained good seasonality even for extrapolated cases. The δ models' deep-network-based parameterization pipeline produced parameter fields that maintain remarkably stable spatial patterns even in highly data-scarce scenarios, which explains their robustness. Combined with their interpretability and ability to assimilate multi-source observations, the δ models are strong candidates for regional and global-scale hydrologic simulations and climate change impact assessment.