地理科学进展 ›› 2008, Vol. 27 ›› Issue (3): 161-165.doi: 10.11820/dlkxjz.2008.03.022

• 遥感技术与模型应用 • 上一篇    下一篇

水文时间序列解析-集成预测模型研究

赵长森1,2,3, 夏军1, 沈冰2, 张惠潼4, 孙常磊5, 侯志强6, 亚力昆7   

  1. 1. 中国科学院地理科学与资源研究所,北京100101;
    2. 西安理工大学水利水电学院,西安710048;
    3. 中山大学水资源与环境系, 广州510275;
    4. 济南水文水资源勘测局,济南250000;
    5. 山东省水利勘测设计院,济南250013;
    6. 潍坊水文水资源勘测局,潍坊261000;
    7. 新疆和田水文水资源勘测局,和田848000
  • 收稿日期:2008-01-01 修回日期:2008-04-01 出版日期:2008-05-25 发布日期:2008-05-25
  • 作者简介:赵长森(1977- ),男(汉族),山东淄博人,博士生,主要从事变化环境下水循环研究.Email:zhaocs.05b@igsnrr.ac.cn
  • 基金资助:

    国家自然科学基金(40671035,50579063);世界银行贷款项目HTJ1.

Study on Pr ediction Model Based on Segr egation and Aggr egation of Hydrologic Time Ser ies

ZHAO Changsen1,2,3, XIA Jun1, SHEN Bing2, ZHANG Huitong4, SUN Changlei5, HOU Zhiqiang6, Ya Likun7   

  1. 1. Institute of Geographical Science and Natural Resources Research,CAS, Beijing 100101, China;
    2. Xi'an University of Technology, Xi'an 710048, China;
    3. Department of water resource and environments, Sun Yat- sen University, Guangzhou 510275, China;
    4. Jinan Survey Bureau of Hydrology and Water Resources, Jinan 250000, China;
    5. Shandong Survey and Design Institute of Water Conservancy, Jinan 250013, China;
    6. Weifang Survey Bureau of Hydrology and Water Resources, Weifang 261000, China;
    7. Hotan Survey Bureau of Hydrology and Water Resources, Hotan 848000, China
  • Received:2008-01-01 Revised:2008-04-01 Online:2008-05-25 Published:2008-05-25

摘要:

为了克服实际工作中常规预测模型的弊端,本文提出了水文序列解析- 集成预测模型(Prediction Model based on Segregation and Aggregation of Hydrological Time Series, PMSAHTS),通过分离水文序列中的趋势信号和周 期信号得到消除了人类活动影响的序列纯随机信号,然后通过随机因子预测预报方法(如BP 神经网络)使用这些 随机信号进行训练和仿真预测,将预测结果与趋势、周期预测结果重新集成,得到水文序列的预测值。将该模型应 用到和田子项目区进行年内月平均蒸发量的预测,结果表明,PMSAHTS 模型达到了水文情报预报规范的合格要 求,可以用于实际预测。

关键词: 趋势, 水文序列解析- 集成预测模型(PMSAHTS), 随机, 预测, 周期

Abstract:

To overcome the shortcomings in conventional forecast methods, a new Prediction Model based on Segregation and Aggregation of Hydrological Time Series (PMSAHTS) was put forward. Impacts of human activities on hydrological data sequences were firstly eliminated through segregation of trend and period signals in the data sequences. Secondly, the remaining random sequences were used as inputs to train BP Neutral Network, and then the trained network was used to predict random sequences in the future. Finally, the predicted random sequences were aggregated with the prediction results of trend and period terms. Thus the predicted hydrological sequences were obtained. To demonstrate this model, PMSAHTS was applied to predict the annual month- average evaporation in the Hotan Sub- project Area. It was shown by the results, among all comparisons of predicted values with measured ones, 62.5% of then have a prediction relative error less than 20%, which suggests that the PMSAHTS was qualified for hydrological prediction in practice.

Key words: periodic, PMSAHTS, prediction, random, trend