大气科学学报2025，Vol.48Issue(3)：463-475,13.DOI:10.13878/j.cnki.dqkxxb.20240829002
基于机器学习和自适应卡尔曼滤波的WRF预报气温降尺度研究——以河北崇礼为例
Downscaling of the WRF-forecast air temperature based on machine learning and adaptive Kalman filtering:a case study of Chongli in Hebei Province
摘要
Abstract
High-accuracy and high-resolution air temperature forecasts are essential for both theoretical research and practical applications.Mountainous terrain presents significant challenges due to its complex topography and pronounced spatial heterogeneity in air temperature distribution.Conventional numerical weather prediction mod-els,including global and regional forecast systems,is typically operate at a spatial resolution of kilometer scale,limiting their ability to capture local-scale air temperature variations in complex mountainous terrains.Therefore,downscaling numerical model outputs is crucial for enhancing the spatial resolution and accuracy of air tempera-ture forecasts in such areas.This study introduces the DOWN+BC method,a novel approach for downscale and bias-correcting air temperature forecasts generated by the Weather Research and Forecasting(WRF)model.This method integrates random forest downscaling,first-order adaptive Kalman filtering,and Extreme Gradient Boos-ting(XGBoost)models to produce high resolution(30 m)hourly air temperature forecasts with a lead time of up to 24 hours.The downscaling process begins with training a Random Forest model using WRF-forecasted air temperature as the dependent variable and 1 km resolution land surface parameters as independent variables.This trained model is then used to downscale the hourly WRF-forecasted air temperatures to a finer 30 m resolution.Finally,a first-order adaptive Kalman filter model is applied for bias correction,where the key parameters w and n are optimized through calibration.Results indicate that the DOWN+BC method effectively enhances the spatial resolution and accuracy of forecasted air temperatures in mountainous regions.The Random Forest model captures fine-scale spatial distribution patterns of near-surface air temperature more accurately,while the subsequent bias correction aligns the forecasts more closely with the actual terrain and underlying surface characteristics.Com-pared to the WRF forecasts,the root mean square error(RMSE)and mean absolute error(MAE)of the DOWN+BC-corrected air temperature forecasts at AWS locations decreased by 1.39 ℃ and 1.13 ℃,respectively.Addi-tionally,in comparison with the air temperature distribution estimated by the XGBoost model,the DOWN+BC method achieved a spatial RMSE and MAE reduction of 1.19℃ and 0.97 ℃,respectively.The method also ac-curately forecasts air temperature inversions that typically occur during nighttime.Overall,the DOWN+BC meth-od,which combines machine learning and adaptive Kalman filtering,significantly improves the spatial resolution and accuracy of WRF model forecasts in mountainous terrain.Moreover,its relatively simple implementation makes it adaptable to other regions.However,its predictive performance may be affected by abrupt and extreme temperature fluctuations,which could lead to a decrease in forecast accuracy to a certain extent.关键词
机器学习/气温/偏差订正/降尺度/山区地形Key words
machine learning/temperature/bias correction/downscaling/mountainous terrain引用本文复制引用
梁晶鹏,祝善友,张楠,张桂欣,徐永明..基于机器学习和自适应卡尔曼滤波的WRF预报气温降尺度研究——以河北崇礼为例[J].大气科学学报,2025,48(3):463-475,13.基金项目
国家自然科学基金项目(42171101 （）
42271351) （）
