...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Hydroinformatics >Tools for the assessment of hydrological ensemble forecasts obtained by neural networks
【24h】

Tools for the assessment of hydrological ensemble forecasts obtained by neural networks

机译：通过神经网络获得的评估水文总体预报的工具

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The increasing demand for uncertainty assessment in streamflow forecasts has drawn thenhydrological community’s interest toward ensemble forecasting techniques. The widespreadndeterministic hydrological forecasting point of view focuses to a great extent on the search for anhydrological model that would come as close as possible to “perfection” (i.e. the aim is tonimplement a model that produces a point forecast that is as close as possible as the observednoutcome). On the other hand, ensemble forecasting departs from the deterministic point of viewnby avoiding the assumption that the “perfect” model exists and instead focuses on issuing a typenof forecast that accounts explicitly for the uncertainty inherent to the forecasting process as anwhole. In this paper, one-day-ahead hydrological ensemble forecasts obtained by stacked neuralnnetworks are presented and analysed. To do so, three simple performance assessment criterianare presented. Those criteria were originally developed in the meteorological and statisticalncommunities to accommodate the need for a quality assessment methodology that is coherentnwith the probabilistic nature of ensemble weather forecasts. It will be shown that, even thoughnthe ensemble forecasts suffer from underdispersion, they outperform point forecasts.
机译：流量预测中对不确定性评估的需求不断增长，这引起了水文学界对整体预报技术的兴趣。广泛的确定性水文预报观点在很大程度上集中于寻找尽可能接近“完美”的水文模型（即，目的是实现一个模型，该模型所产生的点预报应尽可能接近“完美”）。观察到的结果）。另一方面，整体预测从确定性观点出发，避免了存在“完美”模型的假设，而是着重于发布typenof预测，该预测明确地说明了整个预测过程所固有的不确定性。本文提出并分析了通过堆叠神经元网络获得的提前一天的水文总体预报。为此，提出了三个简单的绩效评估标准。这些标准最初是在气象和统计社区中制定的，以适应对与整体天气预报的概率性质相一致的质量评估方法的需求。结果表明，即使整体预报受分散性的影响，它们的性能仍优于点预报。

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