当前位置: X-MOL 学术Water Resources Management › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting
Water Resources Management ( IF 3.9 ) Pub Date : 2021-08-16 , DOI: 10.1007/s11269-021-02937-w
Maryam Rahimzad 1 , Alireza Moghaddam Nia 2 , Hosam Zolfonoon 3 , Jaber Soltani 4 , Ali Danandeh Mehr 5 , Hyun-Han Kwon 6
Affiliation  

Streamflow forecasting plays a key role in improvement of water resource allocation, management and planning, flood warning and forecasting, and mitigation of flood damages. There are a considerable number of forecasting models and techniques that have been employed in streamflow forecasting and gained importance in hydrological studies in recent decades. In this study, the main objective was to compare the accuracy of four data-driven techniques of Linear Regression (LR), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) network in daily streamflow forecasting. For this purpose, three scenarios were defined based on historical precipitation and streamflow series for 26 years of the Kentucky River basin located in eastern Kentucky, US. Statistical criteria including the coefficient of correlation (\(R\)), Nash-Sutcliff coefficient of efficiency (\(E\)), Nash-Sutcliff for High flow (\({E}_{H}\)), Nash-Sutcliff for Low flow (\({E}_{L}\)), normalized root mean square error (\(NRMSE\)), relative error in estimating maximum flow (\(REmax\)), threshold statistics (\(TS\)), and average absolute relative error (\(AARE\)) were employed to compare the performances of these methods. The results show that the LSTM network outperforms the other models in forecasting daily streamflow with the lowest values of \(NRMSE\) and the highest values of\({E}_{H}\),\({E}_{L}\), and \(R\) under all scenarios. These findings indicated that the LSTM is a robust data-driven technique to characterize the time series behaviors in hydrological modeling applications.



中文翻译:

基于 LSTM 的深度学习模型与用于流预测的传统机器学习算法的性能比较

流量预测在改进水资源配置、管理和规划、洪水预警和预测以及减轻洪水损失方面发挥着关键作用。近几十年来,有相当多的预测模型和技术已用于流量预测,并在水文研究中变得越来越重要。在这项研究中,主要目的是比较线性回归 (LR)、多层感知器 (MLP)、支持向量机 (SVM) 和长短期记忆 (LSTM) 网络四种数据驱动技术在日常工作中的准确性。流量预测。为此,根据位于美国肯塔基州东部的肯塔基河流域 26 年的历史降水和流量序列定义了三种情景。统计标准包括相关系数(\(R\) ),Nash-Sutcliff 效率系数 ( \(E\) ),高流量的 Nash-Sutcliff ( \({E}_{H}\) ),低流量的 Nash-Sutcliff ( \( {E}_{L}\) )、归一化均方根误差 ( \(NRMSE\) )、估计最大流量的相对误差 ( \(REmax\) )、阈值统计 ( \(TS\) ) 和平均值绝对相对误差 ( \(AARE\) ) 被用来比较这些方法的性能。结果表明,LSTM 网络在预测每日流量方面优于其他模型,其中\(NRMSE\)的最低值和\({E}_{H}\)的最高值,\({E}_{L }\),和\(R\)在所有情况下。这些发现表明,LSTM 是一种强大的数据驱动技术,可以表征水文建模应用中的时间序列行为。

更新日期:2021-08-20
down
wechat
bug