...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Water Resources Management >Reservoir Inflow Forecasting Using Ensemble Models Based on Neural Networks, Wavelet Analysis and Bootstrap Method
【24h】

Reservoir Inflow Forecasting Using Ensemble Models Based on Neural Networks, Wavelet Analysis and Bootstrap Method

机译：基于神经网络，小波分析和Bootstrap方法的集成模型储层流量预测

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Accurate and reliable forecasting of reservoir inflow is necessary for efficient and effective water resources planning and management. The aim of this study is to develop an ensemble modeling approach based on wavelet analysis, bootstrap resampling and neural networks (BWANN) for reservoir inflow forecasting. In this study, performance of BWANN model is also compared with wavelet based ANN (WANN), wavelet based MLR (WMLR), bootstrap and wavelet analysis based multiple linear regression models (BWMLR), standard ANN, and standard multiple linear regression (MLR) models for inflow forecasting. Robust ANN and WANN models are ensured considering state of the art methodologies in the field. For development of WANN models, initially original time series data is decomposed using wavelet transformation, and wavelet sub-time series are considered to develop WANN models instead of standard data used for development of ANN model. To ensure a robust WANN model different types of wavelet functions are utilized. Further, a comparative analysis is carried out among different approaches of WANN model development using wavelet sub time series. Seven years of reservoir inflow data along with outflow data from two upstream reservoirs in the Damodar catchment along with rainfall data of 5 upstream rain gauge stations are considered in this study. Out of 7 years daily data, 5 years data are used for training the model, 1 year data are used for cross-validation and remaining 1 year data are used to evaluate the performance of the developed models. Different performance indices indicated better performance of WANN model in comparison with WMLR, ANN and MLR models for inflow forecasting. This study demonstrated the effectiveness of proper selection of wavelet functions and appropriate methodology for wavelet based model development. Moreover, performance of BWANN models is found better than BWMLR model for uncertainty assessment, and is found that instead of point predictions, range of forecast will be more reliable, accurate and can be very helpful for operational inflow forecasting.
机译：准确而可靠的储层流入预测是有效而有效的水资源规划和管理所必需的。这项研究的目的是开发一种基于小波分析，自举重采样和神经网络（BWANN）的集成模型，用于储层流入预测。在这项研究中，还将BWANN模型的性能与基于小波的ANN（WANN），基于小波的MLR（WMLR），基于自举和小波分析的多元线性回归模型（BWMLR），标准ANN和标准多元线性回归（MLR）进行了比较流量预测模型。考虑到本领域的最新方法，可以确保建立稳健的ANN和WANN模型。为了开发WANN模型，最初使用小波变换分解原始时间序列数据，并考虑使用小波子时间序列来开发WANN模型，而不是使用用于开发ANN模型的标准数据。为了确保鲁棒的WANN模型，使用了不同类型的小波函数。此外，在使用小波子时间序列的WANN模型开发的不同方法之间进行了比较分析。这项研究考虑了七年的水库流入数据，以及来自Damodar流域两个上游水库的流出数据，以及五个上游雨量计站的降雨数据。在7年的每日数据中，5年的数据用于训练模型，1年的数据用于交叉验证，而其余1年的数据用于评估开发模型的性能。与WMLR，ANN和MLR模型进行流量预测相比，不同的性能指标表明WANN模型的性能更好。这项研究证明了适当选择小波函数的有效性和基于小波模型开发的适当方法。此外，在不确定性评估方面，发现BWANN模型的性能优于BWMLR模型，并且发现，预测范围比点预测更可靠，准确，并且对运营流量预测非常有帮助。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号