ENSO prediction model based on integrated GCN-Transformer network

Du Xianjun; Li He

doi:10.12284/hyxb2023155

Volume 45 Issue 12

Dec. 2023

Turn off MathJax

Article Contents

Article Navigation > Haiyang Xuebao > 2023 > 45(12): 156-165

Du Xianjun，Li He. ENSO prediction model based on integrated GCN-Transformer network[J]. Haiyang Xuebao，2023, 45(12)：156–165 doi: 10.12284/hyxb2023155

Citation:

Du Xianjun，Li He. ENSO prediction model based on integrated GCN-Transformer network[J]. Haiyang Xuebao，2023, 45(12)：156–165 doi: 10.12284/hyxb2023155

Citation:

Du Xianjun，Li He. ENSO prediction model based on integrated GCN-Transformer network[J]. Haiyang Xuebao，2023, 45(12)：156–165 doi: 10.12284/hyxb2023155

PDF( 1956 KB)

ENSO prediction model based on integrated GCN-Transformer network

doi: 10.12284/hyxb2023155

Du Xianjun^1
,,
Li He¹

College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China

Received Date: 2023-04-07
Rev Recd Date: 2023-07-02

Available Online: 2023-11-13

Publish Date: 2023-12-01

Abstract

Abstract

El Niño-Southern Oscillation (ENSO) is an anomaly in the Tropical Pacific Ocean sea surface that can lead to extreme weather such as hail, floods, and typhoons, therefore, accurate prediction of ENSO is of great significance. An integrated graph convolutional network-transformer (GCNTR) model is presented in this paper. Firstly, transformer network is used to encode data features based on its strong focus ability of the global feature. Secondly, GCN is employed to extract features from graph data, and finally introduces a gated feature fusion mechanism to fuse the encoded features with the features extracted by GCN to achieve the accurate prediction ENSO. The results indicate that the GCNTR model achieves the prediction of ENSO 20 months in advance, which is 3 months longer than ENSOTR and 5 months longer than Transformer, and most of the prediction accuracy of the model is better than other models. Compared to the existing methods, the GCNTR model enables better prediction of ENSO.
- El Niño-Southern Oscillation (ENSO),
- graph convolutional network (GCN),
- Transformer,
- graph convolutional network-transformer (GCNTR)

FullText(HTML)

References(21)

References

[1]	Luo Jinglia, Masson S, Behera S K, et al. Extended ENSO predictions using a fully coupled ocean–atmosphere model[J]. Journal of Climate, 2008, 21(1): 84−93. doi: 10.1175/2007JCLI1412.1
[2]	Mu Bin, Li Jing, Yuan Shijin, et al. The NAO variability prediction and forecasting with multiple time scales driven by ENSO using machine learning approaches[J]. Computational Intelligence and Neuroscience, 2022, 2022: 6141966.
[3]	Wang Gaige, Cheng Honglei, Zhang Yiming, et al. ENSO analysis and prediction using deep learning: a review[J]. Neurocomputing, 2023, 520: 216−229. doi: 10.1016/j.neucom.2022.11.078
[4]	Tian Zhiqiang, Li Xiaojian, Zheng Yaoyue, et al. Graph-convolutional-network-based interactive prostate segmentation in MR images[J]. Medical Physics, 2020, 47(9): 4164−4176. doi: 10.1002/mp.14327
[5]	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017: 6000−6010.
[6]	Zhang Ronghua, Tian Feng, Wang Xiujun. A new hybrid coupled model of atmosphere, ocean physics, and ocean biogeochemistry to represent biogeophysical feedback effects in the Tropical Pacific[J]. Journal of Advances in Modeling Earth Systems, 2018, 10(8): 1901−1923. doi: 10.1029/2017MS001250
[7]	Shin J, Park S, Shin S I, et al. Enhancing ENSO prediction skill by combining model-analog and linear inverse models (MA-LIM)[J]. Geophysical Research Letters, 2020, 47(1): e2019GL085914. doi: 10.1029/2019GL085914
[8]	Petersik P J, Dijkstra H A. Probabilistic forecasting of El Niño using neural network models[J]. Geophysical Research Letters, 2020, 47(6): e2019GL086423. doi: 10.1029/2019GL086423
[9]	Mahesh A, Evans M, Jain G, et al. Forecasting El Niño with convolutional and recurrent neural networks[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019: 8−14.
[10]	林琪凡, 耿旭朴, 谢婷, 等. 基于长短期记忆神经网络的西太平洋暖池变化预测[J]. 厦门大学学报(自然科学版), 2021, 60(5): 927−936. Lin Qifan, Geng Xupu, Xie Ting, et al. Trend prediction of Western Pacific warm pool based on long short-term memory neural networks[J]. Journal of Xiamen University (Natural Science), 2021, 60(5): 927−936.
[11]	Ham Y G, Kim J H, Luo Jingjia. Deep learning for multi-year ENSO forecasts[J]. Nature, 2019, 573(7775): 568−572. doi: 10.1038/s41586-019-1559-7
[12]	Gupta M, Kodamana H, Sandeep S. Prediction of ENSO beyond spring predictability barrier using deep convolutional LSTM networks[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1501205.
[13]	Fang Wei, Sha Yu, Sheng V S. Survey on the application of artificial intelligence in ENSO forecasting[J]. Mathematics, 2022, 10(20): 22.
[14]	Geng Huantong, Wang Tianlei. Spatiotemporal model based on deep learning for ENSO forecasts[J]. Atmosphere, 2021, 12(7): 810. doi: 10.3390/atmos12070810
[15]	Hu Jie, Weng Bin, Huang Tianqiang, et al. Deep residual convolutional neural network combining dropout and transfer learning for ENSO forecasting[J]. Geophysical Research Letters, 2021, 48(24): e2021GL093531. doi: 10.1029/2021GL093531
[16]	Ham Y G, Kim J H, Kim E S, et al. Unified deep learning model for El Niño/Southern Oscillation forecasts by incorporating seasonality in climate data[J]. Science Bulletin, 2021, 66(13): 1358−1366. doi: 10.1016/j.scib.2021.03.009
[17]	Zhao Jiakun, Luo Hailun, Sang Weiguang, et al. Spatiotemporal semantic network for ENSO forecasting over long time horizon[J]. Applied Intelligence, 2023, 53(6): 6464−6480. doi: 10.1007/s10489-022-03861-1
[18]	Ye Feng, Hu Jie, Huang Tianqiang, et al. Transformer for EI Niño-Southern Oscillation prediction[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 1003305.
[19]	Bellenger H, Guilyardi E, Leloup J, et al. ENSO representation in climate models: from CMIP3 to CMIP5[J]. Climate Dynamics, 2014, 42(7): 1999−2018.
[20]	Giese B S, Ray S. El Niño variability in simple ocean data assimilation (SODA), 1871–2008[J]. Journal of Geophysical Research: Oceans, 2011, 116(C2): C02024.
[21]	Behringer D, Xue Yan. Evaluation of the global ocean data assimilation system at NCEP: The Pacific Ocean[C]//Proceedings of the Eighth Symposium on Integrated Observing and Assimilation Systems for Atmosphere, Oceans, and Land Surface. Seattle: AMS, 2004.