Department of Environmental Engineering, University of Seoul, Dongdaemun-gu, Seoul, 02504, South Korea.
Water Quality Assessment Research Division, Water Environment Research Department, National Institute of Environmental Research, Incheon, 22689, South Korea.
Sci Rep. 2023 Jun 8;13(1):9296. doi: 10.1038/s41598-023-36439-z.
Recently, weather data have been applied to one of deep learning techniques known as "long short-term memory (LSTM)" to predict streamflow in rainfall-runoff relationships. However, this approach may not be suitable for regions with artificial water management structures such as dams and weirs. Therefore, this study aims to evaluate the prediction accuracy of LSTM for streamflow depending on the availability of dam/weir operational data across South Korea. Four scenarios were prepared for 25 streamflow stations. Scenarios #1 and #2 used weather data and weather and dam/weir operational data, respectively, with the same LSTM model conditions for all stations. Scenarios #3 and #4 used weather data and weather and dam/weir operational data, respectively, with the different LSTM models for individual stations. The Nash-Sutcliffe efficiency (NSE) and the root mean squared error (RMSE) were adopted to assess the LSTM's performance. The results indicated that the mean values of NSE and RMSE were 0.277 and 292.6 (Scenario #1), 0.482 and 214.3 (Scenario #2), 0.410 and 260.7 (Scenario #3), and 0.592 and 181.1 (Scenario #4), respectively. Overall, the model performance was improved by the addition of dam/weir operational data, with an increase in NSE values of 0.182-0.206 and a decrease in RMSE values of 78.2-79.6. Surprisingly, the degree of performance improvement varied according to the operational characteristics of the dam/weir, and the performance tended to increase when the dam/weir with high frequency and great amount of water discharge was included. Our findings showed that the overall LSTM prediction of streamflow was improved by the inclusion of dam/weir operational data. When using dam/weir operational data to predict streamflow using LSTM, understanding of their operational characteristics is important to obtain reliable streamflow predictions.
最近，气象数据已被应用于深度学习技术之一，称为“长短时记忆网络（LSTM）”，以预测降雨径流关系中的流量。然而，这种方法可能不适用于有大坝和堰等人工水管理结构的地区。因此，本研究旨在评估 LSTM 对韩国各地流量预测的准确性，取决于大坝/堰运行数据的可用性。为 25 个流量站准备了四个场景。场景#1 和#2 分别使用气象数据和气象及大坝/堰运行数据，所有站的 LSTM 模型条件相同。场景#3 和#4 分别使用气象数据和气象及大坝/堰运行数据，每个站使用不同的 LSTM 模型。采用纳什效率系数（NSE）和均方根误差（RMSE）来评估 LSTM 的性能。结果表明，NSE 和 RMSE 的平均值分别为 0.277 和 292.6（场景#1）、0.482 和 214.3（场景#2）、0.410 和 260.7（场景#3）和 0.592 和 181.1（场景#4）。总体而言，大坝/堰运行数据的加入提高了模型性能，NSE 值增加了 0.182-0.206，RMSE 值减少了 78.2-79.6。令人惊讶的是，性能提升的程度因大坝/堰的运行特点而异，当包括具有高频率和大量放水的大坝/堰时，性能趋于提高。我们的研究结果表明，通过加入大坝/堰运行数据，LSTM 对流量的整体预测得到了改善。当使用 LSTM 基于大坝/堰运行数据来预测流量时，了解其运行特点对于获得可靠的流量预测非常重要。
