Prediction of ENSO Based on NCEP Reanalysis Datasets
DOI:
https://doi.org/10.54097/p2q6qw15Keywords:
ENSO; prediction; NCEP.Abstract
In recent years, ENSO has been a climate phenomenon that has profound effects on global climate patterns and extreme events. Nino3.4 is a data representation of ENSO. In this study, CNN and LSTM were used to fit and foresee the data in the NCEP reanalysis data set. The findings demonstrate that while the LSTM model can also accurately forecast the changing tendency, it is relatively the effect of CNN is poor, and there is a situation where the simulation value is generally small, CNN does a good job of forecasting the Nino3.4 index, which reflects ENSO. When the index fluctuates significantly, the selection, however, has a tendency to be conservative. Additionally, this study's sample size was quite high, which led to more precise prediction results than in earlier research. To help the ENSO forecasting model forecast more precisely and timely, this study offers various references for its improvement of further study.
Downloads
References
Bjerknes J. (1969). Atmospheric teleconnections from the equatorial Pacific. Monthly Weather Review, 1969, 97(3): 163–172.
McPhaden M J, Busalacchi A J, Anderson D L. A toga retrospective. Oceanography, 2010, 23(3): 86–103.
Ham Y G, Kim, J H, Luo J J. Deep learning for multi-year ENSO forecasts. Nature, 2019, 573(7775): 568–572.
Petersik P J, Dijkstra H A. Probabilistic Forecasting of El Niño Using Neural Network Models. Geophysical Research Letters, 2020, 47: 6.
Rayner N A, Parker D E, Horton E B, et al. Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century. Journal of Geophysical Research: Atmospheres, 2003, 108(D14).
Yang Y, Fu Q, Wan D. A prediction model for time series based on deep recurrent. Computer Technology and Development, 2017, 27(3): 35–38.
Chen Y, Zhang S, Zhang W, Peng J, Cai Y. Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting. Energy Conversion and Management, 2019, 185: 783–799.
Broni-Bedaiko C, Katsriku F A, Unemi T, et al. El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks. Artificial Life and Robotics, 2019, 24(4): 445–451.
Zha W, Li X, Xing Y, He L, Li D. Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty. Advances in Geo-Energy Research, 2020, 4(1): 1.
Zha W, Liu Y, Wan Y, Luo R, Li D, Yang S, Xu Y. Forecasting monthly gas field production based on the CNN-LSTM model. Energy, 2022, 260: 124889.
Krishnamurti T N, Kishtawal C M, LaRow T E, et al. Improved Weather and Seasonal Climate Forecasts from Multimodel Superensemble. Science, 1999, 285(5433): 1548–1550.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
