神经网络在气象领域中的应用
Application of Neural Network in Meteorology
摘要: 神经网络一直是气象领域重要的研究方法之一，但是，由于数据的缺乏及相关理论不完善等因素，在实际应用中有诸多局限。近年来，随着数据资料质量的提升及深度学习研究的兴起，研究者们尝试在气象领域应用神经网络的相关方法，提高天气预报的准确性，更加深入地研究天气现象背后的物理规律。本文介绍了应用于气象领域的几种常见的神经网络模型，回顾了近些年来神经网络模型在数值模式后处理、图像特征提取及天气预报三个方面的应用，并提出在以后研究中的几点期望。以目前的研究成果而言，神经网络模型可以在一定程度上弥补数值预报模式的缺陷，但是不能完全取代数值预报模式。因此，需要更加深入地尝试将数值预报模式及神经网络模型相结合，发挥两种方法的优势，共同推动气象行业的发展。
Abstract: Neutral network has always been one of the most important methods in the field of meteorology. However, many limitations will be found when it used in practical applications due to the lack of data and its imperfect theory. In recent years, the researchers have tried to apply the neutral network models in the field of meteorology in many ways with the improvement of data quality and the appearance of deep learning theory, to improve the weather forecast accuracy and find the physical laws behind the weather phenomena. This paper introduce several neutral network models that most used in the field of meteorology, review the application of neutral network models in the field of numerical forecast post-processing, image feature extraction and weather forecast, Then give some expectations in future research. According to the current research, the neutral network model can make up for some defects of weather numerical forecast to some extent instead, but cannot completely replace it. Therefore, it is necessary to combine them in a deeper degree and take advantage of them, to promote the development of meteorological industry.
文章引用：张珂珺, 金旭峰, 牛海林, 吕艺影, 陈丹丹, 熊雪清. 神经网络在气象领域中的应用[J]. 自然科学, 2024, 12(3): 624-634. https://doi.org/10.12677/ojns.2024.123073

参考文献

[1] Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986) Learning Representations by Back-Propagating Errors. Nature, 323, 533-536. [Google Scholar] [CrossRef] 
[2] Cortes, C. and Vapnik, V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297. [Google Scholar] [CrossRef] 
[3] Breiman, L. (1996) Bagging Preditors. Machine Learning, 24, 123-140. [Google Scholar] [CrossRef] 
[4] 张军阳, 王慧丽, 郭阳, 等. 深度学习相关研究综述[J]. 计算机应用研究, 2018, 35(7): 1-12.
[5] 朱光辉, 王喜文. ChatGPT的运行模式、关键技术及未来图景[J]. 新疆师范大学学报(哲学社会科学版), 2023, 44(4): 113-122.
[6] Bartok, J., Habala, O., Bednar, P., et al. (2010) Data Mining and Integration for Predicting Significant Meteorological Phenomena. Procedia Computer Science, 1, 37-46. [Google Scholar] [CrossRef] 
[7] 智协飞, 彭婷, 李刚, 等. 多模式集成的概率天气预报和气候预测研究进展[J]. 大气科学学报, 2014, 37(2): 248-256.
[8] 陈浩, 宁忱, 南卓铜, 等. 基于机器学习模型的青藏高原日降水数据的订正研究[J]. 冰川冻土, 2017(3): 133-142.
[9] 韩旭明. Elman神经网络的应用研究[D]: [硕士学位论文]. 天津: 天津大学, 2006.
[10] 夏瑜潞. 人工神经网络的发展综述[J]. 电脑知识与技术, 2019, 15(20): 227-229.
[11] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251.
[12] 贺丰收, 何友, 刘准钆, 等. 卷积神经网络在雷达自动目标识别中的研究进展[J]. 电子与信息学报, 2020, 42(1): 119-131.
[13] Mao, J. and Xu, W. (2014) Explain Images with Multimodal Recurrent Neural Networks.
[14] 夏瑜潞. 循环神经网络的发展综述[J]. 电脑知识与技术, 2019, 15(21): 182-184.
[15] Hsieh, W.W. and Tang, B. (1998) Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography. Bulletin of the American Meteorological Society, 79, 1855-1870. [Google Scholar] [CrossRef] 
[16] Moghim, S. and Bras, R.L. (2017) Bias Correction of Climate Modeled Temperature and Precipitation Using Artificial Neural Networks. Journal of Hydrometeorology, 18, 1867-1884. [Google Scholar] [CrossRef] 
[17] 朱延和. 基于U-Net神经网络的新疆地面气温和风的预报订正研究[D]: [硕士学位论文]. 南京: 南京信息工程大学, 2023.
[18] Yuan, H., Gao, X., Mullen, S.L., et al. (2007) Calibration of Probabilistic Quantitative Precipitation Forecasts with an Artificial Neural Network. Weather and Forecasting, 22, 1287-1303. [Google Scholar] [CrossRef] 
[19] Roebber, P.J., Bruening, S.L., Schultz, D.M., et al. (2003) Improving Snowfall Forecasting by Diagnosing Snow Density. Weather and Forecasting, 18, 264-287. [Google Scholar] [CrossRef] 
[20] Kretzschmar, R., Eckert, P., Cattani, D., et al. (2004) Neural Network Classifiers for Local Wind Prediction. Journal of Applied Meteorology, 43, 727-738. [Google Scholar] [CrossRef] 
[21] Rasp, S. and Lerch, S. (2018) Neural Networks for Post-Processing Ensemble Weather Forecasts. Monthly Weather Review, 146, 3885-3900. [Google Scholar] [CrossRef] 
[22] Peng, T., Zhi, X.F., Ji, Y., et al. (2020) Prediction Skill of Extended Range 2-M Maximum Air Temperature Probabilistic Forecasts Using Machine Learning Post-Processing Methods. Atmosphere, 11, 823-835. [Google Scholar] [CrossRef] 
[23] 许锋, 卢建刚, 孙优贤. 神经网络在图像处理中的应用[J]. 信息与控制, 2003, 32(4): 344-351.
[24] Nolan, D.S. and Mcgauley, M.G. (2012) Tropical Cyclogenesis in Wind Shear: Climatological Relationships and Physical Processes. In: Oouchi, K. and Fudeyasu, H., Eds., Cyclones: Formation, Triggers, and Control, Nova Science Publishers, Hauppauge, 1-36.
[25] Liu, Y., Racah, E., Prabhat, et al. (2016) Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets.
[26] Racah, E., Beckham, C., Maharaj, T., et al. (2016) Semi-Supervised Detection of Extreme Weather Events in Large Climate Datasets.
[27] Ojala, T., Pietikäinen, M. and Mäenpää, T. (2000) Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns. Computer Vision-ECCV 2000, 6th European Conference on Computer Vision, Dublin, 26 June-1 July 2000, 404-420.
[28] Buch, K.A. and Sun, C.H. (1995) Cloud Classification Using Whole-Sky Imager Data. 9th Symposium on Meteorological Observations & Instrumentation, Vol. 16, 353-358.
[29] Zhang, J.L., Liu, P., Zhang, F., et al. (2018) CloudNet: Ground-Based Cloud Classification with Deep Convolutional Neural Network. Geophysical Research Letters, 45, 8665-8672. [Google Scholar] [CrossRef] 
[30] Zhang, X., Wang, T., Chen, G., et al. (2019) Convective Clouds Extraction from Himawari-8 Satellite Images Based on Double-Stream Fully Convolutional Networks. IEEE Geoscience and Remote Sensing Letters, 17, 553-557. [Google Scholar] [CrossRef] 
[31] 孔祥羽. 基于域迁移的气象卫星图像云分类技术研究[D]: [硕士学位论文]. 北京: 北京邮电大学, 2023.
[32] Sapiano, M.R.P. and Arkin, P.A. (2009) An Intercomparison and Validation of High-Resolution Satellite Precipitation Estimates with 3-Hourly Gauge Data. Journal of Hydrometeorology, 10, 149-166. [Google Scholar] [CrossRef] 
[33] Behrangi, A., Hsu, K.L., Imam, B., et al. (2009) PERSIANN-MSA: A Precipitation Estimation Method from Satellite-Based Multispectral Analysis. Journal of Hydrometeorology, 10, 1414-1429. [Google Scholar] [CrossRef] 
[34] Hsu, K.L., Gao, X., Sorooshian, S., et al. (1997) Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks. Journal of Applied Meteorology, 36, 1176-1190. [Google Scholar] [CrossRef] 
[35] Aghakouchak, A., Behrangi, A., Sorooshian, S., et al. (2011) Evaluation of Satellite-Retrieved Extreme Precipitation Rates across the Central United States. Journal of Geophysical Research Atmospheres, 116, D02115. [Google Scholar] [CrossRef] 
[36] Katiraie-Boroujerdy, P.S., Nasrollahi, N., Hsu, K.L., et al. (2013) Evaluation of Satellite-Based Precipitation Estimation Over Iran. Journal of Arid Environments, 97, 205-219. [Google Scholar] [CrossRef] 
[37] Tao, Y., Gao, X., Hsu, K., et al. (2016) A Deep Neural Network Modeling Framework to Reduce Bias in Satellite Precipitation Products. Journal of Hydrometeorology, 17, 931-945. [Google Scholar] [CrossRef] 
[38] 杨函. 基于深度学习的气象预测研究[D]: [硕士学位论文]. 哈尔滨: 哈尔滨工业大学, 2017.
[39] Vojtěch, B., Zbyněk, S. and Petr, Z. (2017) Nowcasting of Deep Convective Clouds and Heavy Precipitation: Comparison Study between NWP Model Simulation and Extrapolation. Atmospheric Research, 184, 24-34. [Google Scholar] [CrossRef] 
[40] Sun, J., Xue, M., Wilson, J.W., et al. (2014) Use of NWP for Nowcasting Convective Precipitation: Recent Progress and Challenges. Bulletin of the American Meteorological Society, 95, 409-426. [Google Scholar] [CrossRef] 
[41] Gall, R., Franklin, J., Marks, F., et al. (2013) The Hurricane Forecast Improvement Project. Bulletin of the American Meteorological Society, 94, 329-343. [Google Scholar] [CrossRef] 
[42] Jiang, G.Q., Xu, J. and Wei, J. (2018) A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon-Ocean Feedback in Typhoon Forecast Models. Geophysical Research Letters, 45, 3706-3716. [Google Scholar] [CrossRef] 
[43] Chen, H., Zhang, D.L., Carton, J., et al. (2011) On the Rapid Intensification of Hurricane Wilma. Part I: Model Prediction and Structural Changes. Weather and Forecasting, 26, 885-901. [Google Scholar] [CrossRef] 
[44] Zhu, T. and Zhang, D.L. (2006) The Impact of the Storm-Induced SST Cooling on Hurricane Intensity. Advances in Atmospheric Sciences, 23, 14-22. [Google Scholar] [CrossRef] 
[45] Wang, G., Yang, J., Wang, D., et al. (2016) A Quantitative Comparison of Precipitation Forecasts between the Storm-Scale Numerical Weather Prediction Model and Auto-Nowcast System in Jiangsu, China. Atmospheric Research, 181, 1-11. [Google Scholar] [CrossRef] 
[46] Zahraei, A., Hsu, K.L., Sorooshian, S., et al. (2012) Quantitative Precipitation Nowcasting: A Lagrangian Pixel-Based Approach. Atmospheric Research, 118, 418-434. [Google Scholar] [CrossRef] 
[47] Kuligowski, R.J. and Barros, A.P. (1998) Experiments in Short-Term Precipitation Forecasting Using Artificial Neural Networks. Monthly Weather Review, 126, 470-482. [Google Scholar] [CrossRef] 
[48] 张乐坚, 程明虎, 田付友, 等. 人工神经网络及支持向量机在降雨量预报中的应用[J]. 高原气象, 2010, 29(4): 982-991.
[49] Asanjan, A.A., Yang, T.T., Hsu, K.L., et al. (2018) Short-Term Precipitation Forecast Based on the PERSIANN System and the Long Short-Term Memory (LSTM) Deep Learning Algorithm. Journal of Geophysical Research Atmospheres, 123, 12543-12563. [Google Scholar] [CrossRef] 
[50] Shi, X.J., Chen, Z., Wang, H., et al. (2015) Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting.
[51] 郭瀚阳, 陈明轩, 韩雷, 等. 基于深度学习的强对流高分辨率临近预报试验[J]. 气象学报, 2019, 77(4): 715-727.
[52] 韩丰, 龙明盛, 李月安, 等. 循环神经网络在雷达临近预报中的应用[J]. 应用气象学报, 2019, 30(1): 63-71.
[53] Wang, Y.B., Gao, Z.F., Long, M.S., et al. (2018) PredRNN : Towards a Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning. International Conference on Machine Learning, Stockholm, 10-15 July 2018, 5110-5119.
[54] Wang, Y.B., Wu, H.X., Zhang, J.J., et al. (2023) PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45, 2208-2225. [Google Scholar] [CrossRef] 
[55] Dueben, P.D. and Bauer, P. (2018) Challenges and Design Choices for Global Weather and Climate Models Based on Machine Learning. Geoscientific Model Development, 11, 3999-4009. [Google Scholar] [CrossRef]