MAO Bo,YANG Hao,ZHOU Shijie,et al.A Deep Learning Method for Wind Speed Grid Point Forecasting Data Correction based on CMA-REPS[J].Journal of Chengdu University of Information Technology,2023,38(03):264-270.[doi:10.16836/j.cnki.jcuit.2023.03.003]
基于CMA-REPS格点预报数据的深度学习风速订正方法
- Title:
- A Deep Learning Method for Wind Speed Grid Point Forecasting Data Correction based on CMA-REPS
- 文章编号:
- 2096-1618(2023)03-0264-07
- Keywords:
- CMA-REPS; ensemble forecast; bias correction; deep learning; wind speed
- 分类号:
- TP183
- 文献标志码:
- A
- 摘要:
- 准确的风速预测对风能资源的充分利用和风电场的经济效益提升具有显著的意义。为提高集合数值预报的风速预报能力,弥补现有深度学习集合预报订正模型对格点预报数据时间特征提取的不足,引入ConvLSTM深度学习模型,对CMA-REPS(中国气象局区域集合预报模式)预测的华北地区近地面10 m风速格点数据进行偏差订正实验,以均方根误差(RMSE)作为评分标准将订正结果与CMA-REPS原始预报数据和Unet深度学习模型方法得到的订正结果进行对比。结果表明,ConvLSTM模型的订正效果相比Unet模型有进一步的提升,经ConvLSTM模型订正后的近地面10 m风速预报数据整体上更趋近于实况数据。
- Abstract:
- Accurate wind speed prediction is of great significance for the full utilization of wind energy resources and the improvement of the economic benefits of wind farms. To improve the wind speed forecasting capability of ensemble numerical forecasting, this paper introduces the ConvLSTM deep learning model to perform a bias correction test on the grid point data of near-surface10 m wind speed predicted by CMA-REPS(China Meteorological Administration-Regional Ensemble Prediction System), and the root mean square error(RMSE)was used as the scoring criterion to compare the correction results with the original prediction data of CMA-REPS and the correction results obtained by the Unet deep learning model method. The results show that the correction effect of the ConvLSTM model can be further improved than that of the Unet model, and the prediction data of 10 m wind speed near the surface after the modification of the ConvLSTM model is closer to the real data.
参考文献/References:
[1] Deng Y,Wang B,Lu Z.A hybrid model based on data preprocessing strategy and error correction system for wind speed forecasting[J].Energy Conversion and Management,2020,212(8):112779.
[2] 代刊,朱跃建,毕宝贵.集合模式定量降水预报的统计后处理技术研究综述[J].气象学报,2018,76(4):493-510.
[3] 任晨辰,段明铿.ECMWF全风速场集合预报结果的偏差订正与预报不一致性分析[J].大气科学,2019,42(3):360-369.
[4] Gneiting T,Raftery A E,Westveld A H,et al.Calibrated Probabilistic Forecasting Using Ensemble Model Output Statistics and Minimum CRPS Estimation[J].Monthly Weather Review,2005,133(5):1098-1118.
[5] Bao L,Gneiting T,Grimit E P,et al.Bias Correction and Bayesian Model Averaging for Ensemble Forecasts of Surface Wind Direction[J].Mon.Wea.Rev.2010,138(5):1811-1821.
[6] Lahouar A,Slama J B H. Hour-ahead wind power forecast based on random forests[J].Renewable Energy,2017,109:529-541.
[7] 孙全德,焦瑞莉,夏江江,等.基于机器学习的数值天气预报风速订正研究[J].气象,2019,45(3):426-436.
[8] Rasp S,Lerch S.Neural networks for postprocessing ensemble weather forecasts[J].Monthly Weather Review,2018,146(11):3885-3900.
[9] Shelhamer Evan,Long Jonathan,Darrell Trevor. Fully Convolutional Networks for Semantic Segmentation[J].IEEE transactions on pattern analysis and machine intelligence,2017,39(4).
[10] Grnquist P,Yao C,Ben-Nun T,et al.Deep Learning for Post-Processing Ensemble Weather Forecasts[J].Philosophical Transactions of the Royal Society A,2021,379(2194):20200092.
[11] Han L,Chen M,Chen K,et al.A Deep Learning Method for Bias Correction of ECMWF 24-240 h Forecasts[J].Advances in Atmospheric Sciences,2021,38(9):1444-1459.
[12] 张延彪,陈明轩,韩雷,等.数值天气预报多要素深度学习融合订正方法[J].气象学报,2022,80(1):153-167.
[13] Huang G,Liu Z,Laurens V,et al.Densely Connected Convolutional Networks[J].CoRR,2016.
[14] Shi X,Chen Z,Wang H,et al.Convolutional LSTM network: A machine learning approach for precipitation nowcasting[J].Advances in neural information processing systems,2015,28.
[15] 陈静,李晓莉.GRAPES全球/区域集合预报系统10年发展回顾及展望[J].气象科技进展,2020,10(2):9-18.
[16] 沈学顺,王建捷,李泽椿,等.中国数值天气预报的自主创新发展[J].气象学报,2020,78(3):451-47.
[17] 王婧卓,陈静,庄照荣,等.GRAPES区域集合预报模式的初值扰动增长特征[J].大气科学,2018,42(2):367-382.
[18] 袁月,李晓莉,陈静,等.GRAPES区域集合预报系统模式不确定性的随机扰动技术研究[J].气象,2016,42(10):1161-1175.
[19] 王婧卓,陈法敬,陈静,等.GRAPES区域集合预报对2019年中国汛期降水预报评估[J].大气科学,2021,45(3):664-682.
[20] 吴政秋,张进,陈静,等.GRAPES区域集合预报条件性台风涡旋重定位方法研究[J].气象学报,2020,78(2):163-176.
[21] 谭晓光,罗兵.天气预报分析型数据模型及生成[J].应用气象学报,2014,25(1):120-128.
[22] Diederik P Kingma,Jimmy Ba.Adam:A Method for Stochastic Optimization[J].CoRR,2014.
[23] Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[J].Advances in neural information processing systems,2017:30.
相似文献/References:
[1]马芸萌,刘海文,石鹏翔,等.2012年7月21日重庆暴雨集合预报试验[J].成都信息工程大学学报,2019,(06):650.[doi:10.16836/j.cnki.jcuit.2019.06.014]
MA Yunmeng,LIU Haiwen,SHI Pengxiang,et al.Rainstorm Ensemble Forecast Experiment in Chongqing on July 21, 2012[J].Journal of Chengdu University of Information Technology,2019,(03):650.[doi:10.16836/j.cnki.jcuit.2019.06.014]
备注/Memo
收稿日期:2022-10-21
基金项目:国家重点研发计划资助项目(2021YFC3000902); 四川省科技计划重点研发专项资助项目(2022YFS0542)