Real-time forecasting of suspended sediment concentrations reservoirs by the optimal integration of multiple machine learning techniques
Real-time forecasting of suspended sediment concentrations reservoirs by the optimal integration of multiple machine learning techniques
复制标题
DOI：
10.1016/j.ejrh.2021.100804
复制
发表时间：
2021-03-19
影响因子：
4.7
通讯作者：
Wang, Po-Hsiang
中科院分区：
文献类型：
--
作者：
Huang, Cheng-Chia;Chang, Ming-Jui;Wang, Po-Hsiang
研究区域：石门水库是台湾第二大设计库容。研究重点：台风期间悬浮泥沙浓度(SSCs)的准确预测是有效的水库管理的关键。本文提出了一种基于两步切换机器学习(ML)的方法来构建有效的储层SSCS预测模型。在第一个最大似然算法中，采用不同的最大似然算法建立了多个基于最大似然比的预测模型，包括多层感知器、随机森林、支持向量机、深度神经网络、递归神经网络、长短期记忆(LSTM)网络和门控递归单元。为了弥补实测SSC资料的不足，历史台风采用经过验证的SRH-2D数值模式进行模拟。第二步提出了一种切换预报策略，将多个基于最大似然模型的预报进行最优集成，以提供更准确的计算。新的水文洞察：从支持向量机和最小二乘支持向量机得到的固体悬浮物预报被证实优于其他基于最大似然模型的预报。所提出的模型(从多个基于ML的模型中优化集成)的性能优于其他模型，特别是当预测提前1小时和3小时时。该模型提高了SCC预报的精度，可用于台风期间水库的泥沙管理。
Study region: Shihmen Reservoir is ranked the second largest designed storage capacity in Taiwan.Study focus: The accurate forecasting of suspended sediment concentrations (SSCs) during typhoons is critical for effective reservoir management. This paper proposes a two-step switched machine learning (ML)-based approach for constructing an effective model to forecast reservoir SSCs. Different ML algorithms are adopted in the first ML step to build multiple ML-based SSC forecasting models, including multilayer perceptrons, random forest, support vector machines (SVMs), deep neural networks, recurrent neural networks, long short-term memory (LSTM) networks, and gated recurrent units. To compensate for a deficiency in measured SSC data, historical typhoons are modeled using the well-validated SRH-2D numerical model. The second step develops a switched forecasting strategy to optimally integrate forecasts from multiple ML-based models to provide more accurate calculations.New hydrological insights: The SSC forecasts obtained from the SVM and LSTM are confirmed to be superior to those from other ML-based models. The proposed model (optimally integrated from multiple ML-based models) outperforms the others, particularly when forecasting 1 and 3 h ahead. The proposed model improves the accuracy of SCC forecasts and can be used for sedimentation management in reservoirs during typhoons.