您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Granulation-based LSTM-RF combination model for hourly sea surface temperature prediction

文献类型： 外文期刊

作者： Cao, Mengmeng 1 ; Mao, Kebiao 1 ; Bateni, Sayed M. 4 ; Jun, Changhyun 6 ; Shi, Jiancheng 7 ; Du, Yongming 2 ; Du, Guoming 8 ;

作者机构： 1.Chinese Acad Agr Sci, Inst Agr Resources & Regional Planning, Hulunbeir Grassland Ecosyst Res Stn, Beijing, Peoples R China

2.Chinese Acad Sci, Aerosp Informat Res Inst, State Key Lab Remote Sensing Sci, Beijing, Peoples R China

3.Ningxia Univ, Sch Phys & Elect Engn, Ningxia 750021, Peoples R China

4.Univ Hawaii Manoa, Dept Civil & Environm Engn, Honolulu, HI USA

5.Univ Hawaii Manoa, Water Resources Res Ctr, Honolulu, HI USA

6.Chung Ang Univ, Coll Engn, Dept Civil & Environm Engn, Seoul, South Korea

7.Chinese Acad Sci, Natl Space Sci Ctr, Beijing, Peoples R China

8.Northeast Agr Univ, Sch Publ Adm & Law, Harbin, Peoples R China

9.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, Hulunbeir Grassland Ecosyst Res Stn, Beijing 100081, Peoples R China

关键词： SST prediction; adaptive granulation method; LSTM; RF; error reciprocal method

期刊名称：INTERNATIONAL JOURNAL OF DIGITAL EARTH （ 影响因子：5.1； 五年影响因子：4.5 ）

ISSN： 1753-8947

年卷期： 2023 年 16 卷 1 期

页码：

收录情况： SCI

摘要： Accurate predictions of sea surface temperature (SST) are crucial due to the significant impact of SST on the global ocean-atmospheric system and its potential to trigger extreme weather events. Many existing machine-learning-based SST predictions adapt the traditional iterative point-wise prediction mechanism, whose predicting horizons and accuracy are limited owing to the high sensitivity to cumulative errors during iterative predictions. Therefore, this paper proposes a novel granulation-based long short-term memory (LSTM)-random forest (RF) combination model that can fully capture the feature dependencies involved in the fluctuation of SST sequences, reduce the cumulative error in the iteration process, and extend the prediction horizons, which includes two sub-models (adaptive granulation model and hybrid prediction model). They can restack the one-dimensional SST time-series into multidimensional feature variables, and achieve a strong forecasting ability. The analysis shows that the proposed model can achieve more accurate prediction-hours in nearly all prediction ranges from 1 to 125 h. The average prediction error of the proposed model in 25-125 h is 0.07 K, similar to that (0.067 K) in the first 24 h, which exhibits a high generalization performance and robustness and isthus a promising platform for the medium- and long-term forecasting of hourly SSTs.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台