Application of recurrent neural networks for drought projections in California

被引：37
作者：
Le, J. A. [1 ]
El-Askary, H. M. [1 ,2 ,3 ]
Allali, M. [1 ]
Struppa, D. C. [1 ]
机构：
[1] Chapman Univ, Schmid Coll Sci & Technol, Orange, CA 92866 USA
[2] Chapman Univ, Ctr Excellence Earth Syst Modeling & Observat, Orange, CA 92866 USA
[3] Univ Alexandria, Fac Sci, Dept Environm Sci, Alexandria, Egypt
来源：
ATMOSPHERIC RESEARCH | 2017年 / 188卷
关键词：
Drought; Southern California; El Nino; Palmer Z-Index; Recurrent neural networks; TIME-SERIES; PRECIPITATION; PREDICTION; STREAMFLOW; PATTERNS; WEATHER; ATHENS;
D O I：
10.1016/j.atmosres.2017.01.002
中图分类号：
P4 [大气科学（气象学）];
学科分类号：
0706 ; 070601 ;
摘要：
We use recurrent neural networks (RNNs) to investigate the complex interactions between the long-term trend in dryness and a projected, short but intense, period of wetness due to the 2015-2016 El Nino. Although it was forecasted that this El Nino season would bring significant rainfall to the region, our long-term projections of the Palmer Z Index (PZI) showed a continuing drought trend, contrasting with the 1998-1999 El Nino event. RNN training considered PZI data during 1896-2006 that was validated against the 2006-2015 period to evaluate the potential of extreme precipitation forecast. We achieved a statistically significant correlation of 0.610 between forecasted and observed PZI on the validation set for a lead time of 1 month. This gives strong confidence to the forecasted precipitation indicator. The 2015-2016 El Nino season proved to be relatively weak as compared with the 1997-1998, with a peak PZI anomaly of 0.242 standard deviations below historical averages, continuing drought conditions. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码：100 / 106
页数：7
相关论文
共 54 条
  • [1] [Anonymous], 2013, P IEEE INT C AC SPEE, DOI 10.1109/ICASSP.2013.6638947
  • [2] [Anonymous], 2015, CoRR
  • [3] [Anonymous], 1995, Backpropagation: Theory, architectures, and applications
  • [4] [Anonymous], 2009, Proceedings of the 26th Annual International Conference on Machine Learning
  • [5] [Anonymous], 2011, P 28 INT C MACH LEAR
  • [6] Asner G., 2015, P NATL ACAD SCI USA, V2015, P249
  • [7] Badjate Sanjay L., 2009, WSEAS Transactions on Information Science and Applications, V6, P684
  • [8] Prediction of extreme precipitation using a neural network:: application to summer flood occurrence in Moravia
    Bodri, L
    Cermák, V
    [J]. ADVANCES IN ENGINEERING SOFTWARE, 2000, 31 (05) : 311 - 321
  • [9] Understanding ENSO Diversity
    Capotondi, Antonietta
    Wittenberg, Andrew T.
    Newman, Matthew
    Di Lorenzo, Emanuele
    Yu, Jin-Yi
    Braconnot, Pascale
    Cole, Julia
    Dewitte, Boris
    Giese, Benjamin
    Guilyardi, Eric
    Jin, Fei-Fei
    Karnauskas, Kristopher
    Kirtman, Benjamin
    Lee, Tong
    Schneider, Niklas
    Xue, Yan
    Yeh, Sang-Wook
    [J]. BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY, 2015, 96 (06) : 921 - 938
  • [10] Changnon SA, 1999, B AM METEOROL SOC, V80, P1819, DOI 10.1175/1520-0477(1999)080<1819:IOENOG>2.0.CO
123456