论文标题
在流动持续曲线和输入选择集合建模的Ungaig区域的预测
Prediction in ungauged regions with sparse flow duration curves and input-selection ensemble modeling
论文作者
论文摘要
尽管长期的短期内存（LSTM）模型已经证明了具有流量预测的出色性能，但在没有仪表的连续区域应用这些模型存在主要风险，或者在未衡量的区域（PUR）问题中进行预测。但是，诸如流持续时间曲线（FDC）之类的较软数据可能已经从附近的车站可用，也可以可用。在这里，我们证明了稀疏的FDC数据可以通过基于LSTM的网络通过编码来迁移和同化。一个严格的基于区域的持有测试显示，美国数据集的Kling-Gupta效率（KGE）为0.62，大大高于以前最先进的全球尺度Ungaig盆地测试。没有FDC的基线模型已经具有竞争力（KGE中位数为0.56），但是集成的FDC具有很大的价值。由于输入的不准确表示，基线模型有时可能会产生灾难性的结果。但是，通过基于具有不同输入选择的模型来编译集合，可以进一步提高模型的推广性。
While long short-term memory (LSTM) models have demonstrated stellar performance with streamflow predictions, there are major risks in applying these models in contiguous regions with no gauges, or predictions in ungauged regions (PUR) problems. However, softer data such as the flow duration curve (FDC) may be already available from nearby stations, or may become available. Here we demonstrate that sparse FDC data can be migrated and assimilated by an LSTM-based network, via an encoder. A stringent region-based holdout test showed a median Kling-Gupta efficiency (KGE) of 0.62 for a US dataset, substantially higher than previous state-of-the-art global-scale ungauged basin tests. The baseline model without FDC was already competitive (median KGE 0.56), but integrating FDCs had substantial value. Because of the inaccurate representation of inputs, the baseline models might sometimes produce catastrophic results. However, model generalizability was further meaningfully improved by compiling an ensemble based on models with different input selections.
