Using data from the Heyuan Meteorological Station and observational records of the "High-Humidity Weather" event in Dongyuan from 2015 to 2021, a Gate Recurrent Unit (GRU) model was developed to predict indoor surface temperatures for the next 24 and 48 hours. The model was evaluated using observation data in 2022. A key innovation of this research lies in combining artificial intelligence with numerical forecasting to improve the prediction accuracy of the"High-Humidity Weather"event. The validation results indicate that the GRU model is significantly better than the multiple linear regression model. Sensitivity experiments further reveal that accurate numerical prediction enhances the robustness of the GRU model. This method of combining artificial intelligence and numerical prediction highly depends on the accuracy of dew point and air temperature prediction.
GUOMeimei, GuanhuaMAI, GAOJunjie,et al.Weather characteristics of spring “Huinantian” in Zhaoqing[J].Guangdong Meteorology,2013,35(1):27-31.(in Chinese)
LUOXiaoli, GUMingyue, ZHONGLihua,et al.Causal analysis of typical “High-Humidity Weather" events in Guangxi in recent years[J].Meteorological Science and Technology,2015,43(4):659-665, 674.(in Chinese)
CHENFangli, LIMinghua, WUWei.Analysis of the circulation characteristics of the "Continuous Wet Weather" during February-March in 2010:a case study of Huizhou City,Guangdong[J].Tropical Geography,2011,31(6):570-574, 603.(in Chinese)
ZHANGDong, WANGYing, FENGYerong,et al.Analysis and forecasting of High-Humidity Weather in Guangdong in February and March[J].Meteorological Science and Technology,2014,42(2):302-308.(in Chinese)
CHENJian, LIJiaying, GAOAnning,et al.Synoptic features and forecast method for continuous wet weather in Guangxi[J].Meteorological Monthly,2015,41(3):372-379.(in Chinese)
GUMingyue.Analysis of High-Humidity Weather during February to April in Nanning[J].Journal of Meteorological Research and Application,2015,36(2):21-25, 30.(in Chinese)
LIQinglan, WUYang, CAOChunyan,et al.Exploration of moistening weather forecast in Shenzhen[J].Journal of Tropical Meteorology,2014,30(5):971-976.(in Chinese)
WANGQingguo, HUANGGuilan, HUANGZengjun,et al.Objective analysis method for “Huinan Weather”[J].Journal of Meteorological Research and Application,2014,35(2):1-6.(in Chinese)
ZHENGJiawei, WANGShigong, YINLi,et al.A study on the relationship between upper respiratory tract infection and meteorological elements and the outbreak risk prediction in two representative cities using machine learning[J].Desert and Oasis Meteorology,2023,17(4):160-168.(in Chinese)
ZHUGuodong, ZHULei, WANGNan,et al.Research on airport temperature forecast method based on automatic machine learning[J].Desert and Oasis Meteorology,2021,15(6):113-119.(in Chinese)
CAIRen, LIRuiqi, TANGYe,et al.Prediction method research of air pollution in Urumqi using support vector machine[J].Desert and Oasis Meteorology,2014,8(3):61-67.(in Chinese)
HUJiahui, LUChuhuan, JIANGYoushan,et al.Application of deep learning model TAGAN in nowcasting of strong convective echo[J].Chinese Journal of Atmospheric Sciences,2022,46(4):805-818.(in Chinese)
CAIRen.Application of Artificial Neural Network(ANN) to forecast of Nanjing's short-term precipitation in autumn[J].Desert and Oasis Meteorology,2007,1(1):49-52.(in Chinese)
YEHaotian, ZOUChunhui, TIANHongwei.A method for PM2.5 concentration monitoring based on machine learning and Himawari-8 satellite data[J].Meteorological and Environmental Sciences,2023,46(3):89-97.(in Chinese)
WUHongxing, HUANGWenjun.Air temperature predication using a dynamic learning rate neural network model based on time series[J].Desert and Oasis Meteorology,2008,2(3):44-47.(in Chinese)
YANGXuan, ZENGYan, QIUXinfa,et al.Examination and evaluation of multi-source monthly scale fusion precipitation product in China based on machine learning algorithm[J].Torrential Rain and Disasters,2023,42(5):595-605.(in Chinese)
SUNZhijun, XUELei, XUYangming,et al.Overview of deep learning[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)
[39]
饶生辉.基于室内地表温度和露点温度的回南天预警预报方法[D].成都:电子科技大学,2017.
[40]
RAOShenghui.Continuous wet weather warning and forecast based on indoor surface temperature and dew point temperature[D].Chengdu:University of Electronic Science and Technology of China,2017.(in Chinese)
[41]
CabessaJ, SiegelmannH T.The computational power of interactive recurrent neural networks[J].Neural Computation,2012,24(4):996-1019.
[42]
ChungJ, GulcehreC, ChoK,et al.Gated feedback recurrent neural networks[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning.Lille:JMLR,2015:2067-2075.
[43]
郝博渊.不同风速下的建筑综合热惰性与采暖负荷特性研究[D].天津:天津大学,2016.
[44]
HAOBoyuan.Study on the building integrated thermal inertia and heating load characteristics under different wind speeds[D].Tianjin:Tianjin University,2016.(in Chinese)
HUPing, RANXianguo, YANGQun,et al.Temperature prediction ability comparison and error analysis of three numerical models[J].Journal of Guizhou Meteorology,2017,41(3):30-34.(in Chinese)