当前位置>主页 > 期刊在线 > 信息技术 >

信息技术21年17期

基于机器学习的宁海县气温降尺度推算研究
申子彬 ¹,郁懋楠 ²,吴泽亮 ²,岳梦琦 ²
(1. 宁波市镇海区气象局,浙江 宁波 315206;2. 宁海县气象局,浙江 宁波 315699)

摘  要:针对当前气温预报精细化程度无法满足经济发展及人民群众的需求,利用宁海县 22 个气象站 2013—2016 年的逐日气温资料、EC 数值模式气温预报资料以及各站点的地理信息资料,实况资料作为输出,数值预报、地理信息资料作为输入,构建 DBN 神经网络气温预报模型。经过训练的神经网络模型对数值预报气温资料有正的订正作用,对站点平均预报准确度缩小1.18 ℃,该模型可以用于气温降尺度业务实际。


关键词:机器学习;EC 数值预报模式;地理信息资料;气温降尺度



DOI:10.19850/j.cnki.2096-4706.2021.17.005


中图分类号:TP181                                          文献标识码:A                                       文章编号:2096-4706(2021)17-0022-04


Research on Temperature Downscaling Prediction in Ninghai County Based on Machine Learning

SHEN Zibin1 , YU Maonan2 , WU Zeliang2 , YUE Mengqi 2

(1. Meteorological Bureau of Zhenhai District, Ningbo 315206, China; 2. Ninghai County Meteorological Bureau, Ningbo 315699, China)

Abstract: In view of the fact that the current refinement of temperature forecast can not meet the needs of economic development and the people, the daily temperature data of 22 meteorological stations in Ninghai County from 2013 to 2016, the EC numerical mode temperature forecast data, the geographic information materials of each station and factual information are used as the output, and the numerical forecast and geographic information materials are used as the input, the temperature prediction model based on DBN neural network is constructed. The trained neural network model has a positive correction effect on the numerical temperature prediction data, and the average prediction accuracy of the station is reduced by 1.18 ℃ . This model can be used in the practice of temperature downscaling.

Keywords: machine learning; EC numerical prediction model; geographic information materials; temperature downscaling


参考文献:

[1] HOFER M ,MÖLG T,MARZELON B,et al. Empiricalstatistical downscaling of reanalysis data to high-resolution air temperature and specific humidity above a glacier surface (Cordillera Blanca,Peru) [J/OL].Journal of Geophysical Research:Atmospheres,2010,115(D12):[2021- 07-24].https://doi.org/10.1029/2009JD012556.

[2] RADAN H. Statistical Downscaling of Daily Temperature in Central Europe [J].Journal of Climate,2002,15(13):1731-1742.

[3] 钞振华 . 中国西部地区气温资料的统计降尺度研究 [J]. 干旱区研究,2011,28(5):879-884.

[4] 翁笃鸣,罗哲贤 . 山区地形气候 [M]. 北京:气象出版社,1990.

[5] 杨青,史玉光,袁玉江,等 . 基于 DEM 的天山山区气温和降水序列推算方法研究 [J]. 冰川冻土,2006(3):337-342.

[6] 蔡迪花,郭铌,李崇伟.基于DEM的气温插值方法研究 [J]. 干旱气象,2009,27(1):10-17+28.

[7] 杨昕,汤国安,王春,等 . 基于 DEM 的山区气温地形修正模型——以陕西省耀县为例 [J]. 地理科学,2007(4):525-530.

[8] 张洪亮,倪绍祥,邓自旺,等 . 基于 DEM 的山区气温空间模拟方法 [J]. 山地学报,2002(3):360-364.


作者简介:申子彬(1992—),男,汉族,湖南邵东人,科员,工程师,理学学士学位,研究方向:天气预报与应用气象。