Suspended sediment concentration (SSC) is a crucial indicator for aquatic ecosystems and reservoir management but is challenging to predict at large scales. It is unclear whether SSC is predictable using macroscopic environmental attributes and forcings. This study tested the feasibility of deep-network-based models to predict daily SSC at basin outlets given only basin-averaged forcings, readily-available physiographic attributes, and streamflow (from observation or model). We trained long short-term memory (LSTM) deep networks both separately for each of the 377 sites across the conterminous United States (CONUS) (termed “local models”), and on all the sites collectively (Whole-CONUS). The Whole-CONUS and local models presented median coefficient of determination (R) values of 0.63 and 0.52, respectively. This comparison agrees with previously acknowledged “data synergy” effects for LSTM models, where more data from more sites can help improve predictions overall. Furthermore, the continental-scale analysis provided a wealth of insights about SSC patterns. Both local and Whole-CONUS models tended to be more successful where SSC-streamflow correlations () were high − typically in the humid Eastern US − and with lower SSC. Low basins were often found in the arid Southwest with higher SSC. The highly-nonlinear SSC-streamflow relationships seem related to seasonality, basin size, and heterogeneity of land cover and rainfall within the basins, suggesting these basins need to be simulated at higher spatial resolution and may require additional inputs related to SSC induced by seasonality. The Whole-CONUS model also performed well for spatial extrapolation (basins not included in the training dataset, median R = 0.55), supporting large-scale modeling efforts. These state-of-the-art results using only minimal inputs suggest data-driven approaches can exploit the natural coevolution of sediment processes and the environment to support sediment modeling.

中文翻译：

---

对美国本土悬浮沉积物浓度的深度学习见解：优势和局限性


悬浮沉积物浓度（SSC）是水生生态系统和水库管理的重要指标，但大规模预测具有挑战性。目前尚不清楚SSC是否可以利用宏观环境属性和强迫进行预测。本研究测试了基于深层网络的模型在仅考虑流域平均强迫、现成的地形属性和水流（来自观测或模型）的情况下预测流域出口每日 SSC 的可行性。我们分别为美国本土 (CONUS) 的 377 个站点（称为“本地模型”）和所有站点（整个 CONUS）单独训练了长短期记忆 (LSTM) 深度网络。 Whole-CONUS 和局部模型的中位决定系数 (R) 值分别为 0.63 和 0.52。这种比较与之前承认的 LSTM 模型的“数据协同”效应一致，即来自更多站点的更多数据可以帮助改善整体预测。此外，大陆范围的分析提供了关于南南合作模式的丰富见解。在 SSC-径流相关性 () 较高（通常是在潮湿的美国东部）且 SSC 较低的情况下，局部模型和整个 CONUS 模型往往更成功。低盆地经常出现在干旱的西南地区，SSC 较高。高度非线性的SSC-径流关系似乎与季节性、流域大小以及流域内土地覆盖和降雨的异质性有关，这表明这些流域需要以更高的空间分辨率进行模拟，并且可能需要与季节性引起的SSC相关的额外输入。 Whole-CONUS 模型在空间外推方面也表现良好（训练数据集中不包含盆地，中值 R = 0.55），支持大规模建模工作。 这些仅使用最少输入的最先进的结果表明数据驱动的方法可以利用沉积物过程和环境的自然共同进化来支持沉积物建模。