Quantifying the Uncertainties in Data-Driven Models for Reservoir Inflow Prediction

Quantifying the Uncertainties in Data-Driven Models for Reservoir Inflow Prediction
复制标题

量化油藏流入预测数据驱动模型的不确定性

DOI:
10.1007/s11269-020-02514-7
复制
发表时间:
2020-03
影响因子:
4.3
通讯作者:
Huang Xudong
Huang Xudong
中科院分区:
环境科学与生态学3区
文献类型:
--
作者:
Zhang Xiaoli;Wang Haixia;Peng Anbang;Wang Wenchuan;Li Baojian;Huang Xudong

文献摘要

参考文献

相似文献

在数据驱动的建模中,水库流入预测受到高度不确定性的影响。在这项研究中,提出了一个分解方案,以评估输入集和数据驱动模型的不确定性的单独和组合的贡献,总的预测不确定性。六个变量(即,流入量(Q)、降水量(P)、相对湿度(H)、最低温度(Tmin)、最高温度(Tmax)和降水量预报(F)),以及三个数据驱动模型(即,采用人工神经网络(ANN)、支持向量机(SVM)和自适应神经模糊推理系统(ANFIS)对中国桓仁水库10天入库流量进行集成预报,并采用方差分析(ANOVA)方法对预报的不确定性进行分解。集合预报结果表明,当三个变量,Q,PandF,数据驱动模型的预测精度非常高,并且添加其他三个变量,即。例如,H、Tmin和Tmax对预测精度有一定的改善作用。分解结果表明,输入集是不确定性的主要来源,数据驱动模型的贡献有限,且具有较强的季节变化:冬夏较大,春秋较小。最重要的是,输入数据集和数据驱动模型对总预测不确定性的交互贡献非常大,比模型本身的单独贡献更重要,这意味着在建模过程中应仔细考虑输入数据集和数据驱动模型的综合影响。
Reservoir inflow prediction is subject to high uncertainties in data-driven modelling. In this study, a decomposition scheme is proposed to evaluate the individual and combined contributions of uncertainties from input sets and data-driven models to the total predictive uncertainty. Six variables (i.e., inflow (Q), precipitation (P), relative humidity (H), minimum temperature (Tmin), maximum temperature (Tmax) and precipitation forecast (F)), and three data-driven models (i.e., artificial neural network (ANN), support vector machine (SVM), and adaptive neuro fuzzy inference systems (ANFIS)) are used to produce an ensemble of 10-day inflow forecast for Huanren reservoir in China, and the analysis of variance (ANOVA) method is employed to decompose the uncertainty. The ensemble forecast results show that when the three variables, i.e.,Q,PandF, are used only, the predictive accuracy of the data-driven models is very high and the addition of the other three variables, i. e.,H,Tmin andTmax, can slightly improve the predictive accuracy. The decomposition results indicate that the input set is the dominant source of uncertainty, the contribution of the data-driven model is limited and has a strong seasonal variation: larger in winter and summer, smaller in spring and autumn. Most importantly, the interactive contribution of the input set and the data-driven model to the total predictive uncertainty is very high and is more significant than the individual contribution from the model itself, implying that the combined effects of the input set and the data-driven model should be carefully considered in the modelling process.
DOI: 10.1016/j.jhydrol.2012.04.045
发表时间: 2012-07
影响因子: 6.4
作者:
V. Jothiprakash;R. Magar
通讯作者: V. Jothiprakash;R. Magar
DOI: 10.1002/1099-1085(20000815/30)14:11/12
发表时间: 2000-08
影响因子: 3.2
作者:
J. Kroes;J. Wesseling;J. Dam
通讯作者: J. Kroes;J. Wesseling;J. Dam
DOI: 10.1016/j.jhydrol.2013.03.047
发表时间: 2013-04
影响因子: 6.4
作者:
U. Spank;K. Schwärzel;M. Renner;Uta Moderow;C. Bernhofer
通讯作者: U. Spank;K. Schwärzel;M. Renner;Uta Moderow;C. Bernhofer
DOI: --
发表时间: 1989
期刊: --
影响因子: --
作者:
通讯作者: --
DOI: 10.1016/j.jhydrol.2015.06.007
发表时间: 2015-09-01
影响因子: 6.4
作者:
Chitsazan, Nima;Nadiri, Ata Allah;Tsai, Frank T. -C.
通讯作者: Tsai, Frank T. -C.