孟锐,陈云瑶,李彬权,肖洋,张汇明,张涛涛,李匡

• 1:江西省赣抚尾闾整治有限公司
• 2:河海大学流域水循环与水安全全国重点实验室
• 3:河海大学水文水资源学院
• 4:河海大学水利部水循环与水动力系统重点实验室

摘要(Abstract)：

【目的】降水输入误差是洪水预报误差的主要来源，融合多源降水信息是降低降水输入误差的重要手段。高时空分辨率卫星降水产品能够更好地捕捉降水事件的时空分布信息，但因其点估计误差较大导致其应用受限。提出一种基于机器学习和贝叶斯模型平均的多源降水融合方法，以提高降水数据在时空尺度上的精度。【方法】首先采用双线性插值方法将3种卫星降水产品(GSMaP、IMERG和PERSIANN)进行空间降尺度，再利用轻量梯度增强机(LGBM)算法进行降水偏差校正，最后基于季节尺度贝叶斯模型平均(BMA)融合校正后的降水产品，得到精度更高的降水数据。【结果】选择赣江上游峡山站以上流域进行实例验证，结果表明：(1)融合后降水在6个评价指标上均明显优于原始卫星产品(均方根误差为4.73 mm、相关系数为0.92、误报率为0.28);(2)与原始卫星产品相比，融合后降水空间分布的准确性显著提高，与地面观测站的一致性更好；(3)单卫星降水校正的结果和多卫星降水融合后的结果在小雨、中雨、大雨、暴雨和大暴雨等5种量级下的均方根误差值均显著低于原始卫星产品。【结论】总体上，多卫星降水融合数据综合了各校正降水产品的优势，在不同降水量级方面均表现较好，成果可为水文模拟和预报提供准确降雨输入数据支撑。

关键词(KeyWords)： 多源降水融合;机器学习;贝叶斯模型平均;赣江流域;影响因素

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(42471049);; 赣江下游尾闾综合整治工程科研课题研究项目(JXTC2023020257C1)

作者(Author): 孟锐,陈云瑶,李彬权,肖洋,张汇明,张涛涛,李匡

DOI: 10.13928/j.cnki.wrahe.2026.03.012

参考文献(References)：

• [1] 黄雨，何正迎.气候变化背景下降雨滑坡风险评估研究进展[J].中国地质灾害与防治学报，2025,36(2):13-27.HUANG Y,HE Z Y.Research progress on rainfall-triggered landslide risk assessment under the context of climate change[J].The Chinese Journal of Geological Hazard and Control,2025,36(2):13-27.
• [2] 张裕，侯精明，王正发，等.降雨时间分辨率与插值方法对城市内涝模拟影响研究[J].水力发电学报，2024,43(11):27-38.ZHANG Y,HOU J M,WANG Z F,et al.Effect of rainfall time resolutions and interpolation methods on urban waterlogging simulations[J].Journal of Hydroelectric Engineering,2024,43(11):27-38.
• [3] 秦鼎超，张行南，张自航，等.基于多源融合降水数据的雨量站网适用性评估方法[J].人民长江，2025,56(3):106-115.QIN D C,ZHANG X N,ZHANG Z H,et al.Applicability evaluation method for rainfall gauge networks based on multi-source integrated rainfall data[J].Yangtze River,2025,56(3):106-115.
• [4] LI Z Y,HUANG S Z,ZHOU S,et al.Clarifying the propagation dynamics from meteorological to hydrological drought induced by climate change and direct human activities[J].Journal of Hydrometeorology,2021,22(9):2359-2378.
• [5] TANG G Q,MA Y Z,LONG D,et al.Evaluation of GPM Day-1 IMERG and TMPA Version-7 legacy products over China's mainland at multiple spatiotemporal scales[J].Journal of Hydrology,2016,533:152-167.
• [6] PANG J Z,ZHANG H L,XU Q X,et al.Hydrological evaluation of open-access precipitation data using SWAT at multiple temporal and spatial scales[J].Hydrology and Earth System Sciences,2020,24(7):3603-3626.
• [7] CHIANG Y M,HAO R N,XU Y P,et al.Multi-source rainfall merging and reservoir inflow forecasting by ensemble technique and artificial intelligence[J].Journal of Hydrology:Regional Studies,2022,44:101204.
• [8] 雷晓辉，王浩，廖卫红，等.变化环境下气象水文预报研究进展[J].水利学报，2018,49(1):9-18.LEI X H,WANG H,LIAO W H,et al.Advances in hydro-meteorological forecast under changing environment[J].Journal of Hydraulic Engineering,2018,49(1):9-18.
• [9] CHEN C,HE M N,CHEN Q W,et al.Triple collocation-based error estimation and data fusion of global gridded precipitation products over the Yangtze River basin[J].Journal of Hydrology,2022,605:127307.
• [10] WEI L Y,JIANG S H,DONG J Z,et al.Fusion of gauge-based,reanalysis,and satellite precipitation products using Bayesian model averaging approach:Determination of the influence of different input sources[J].Journal of Hydrology,2023,618:129234.
• [11] 李伶杰，王银堂，唐国强，等.考虑有雨无雨辨识的多源降水融合方法[J].水科学进展，2022,33(5):780-793.LI L J,WANG Y T,TANG G Q,et al.An innovative multi-source precipitation merging method with the identification of rain and no rain[J].Advances in Water Science,2022,33(5):780-793.
• [12] 张婷，李怡，李建柱，等.多源降雨数据融合及其水文应用研究进展[J].自然灾害学报，2022,31(1):15-28.ZHANG T,LI Y,LI J Z,et al.Research progress on multi-source rainfall data fusion and their hydrological application[J].Journal of Natural Disasters,2022,31(1):15-28.
• [13] 张航，宋松柏，刘允龙，等.基于 Prony 算法和卡尔曼滤波的月降水随机预报模型[J].南水北调与水利科技(中英文),2025,23(2):343-353.ZHANG H,SONG S B,LIU Y L,et al.A stochastic forecasting model for monthly precipitation based on the Prony algorithm and Kalman filter[J].South-to-North Water Transfers and Water Science & Technology,2025,23(2):343-353.
• [14] MA Y Z,HONG Y,CHEN Y,et al.Performance of optimally merged multisatellite precipitation products using the dynamic Bayesian model averaging scheme over the Tibetan Plateau[J].Journal of Geophysical Research:Atmospheres,2018,123(2):814-834.
• [15] KOLLURU V,KOLLURU S,WAGLE N,et al.Secondary precipitation estimate merging using machine learning:Development and evaluation over Krishna River Basin,India[J].Remote Sensing,2020,12(18):3013.
• [16] ZHANG T T,LIANG Z M,WANG H J,et al.Merging multisatellite precipitation products using stacking method and the censored-shifted gamma ensemble model output statistics in China’s Beimiaoji basin[J].Journal of Hydrology,2023,618:129263.
• [17] MENG C C,MO X G,LIU S X,et al.Improving near-real-time satellite precipitation products through multistage modified schemes[J].Atmospheric Research,2023,292:106875.
• [18] GUDMUNDSSON L,BREMNES J B,HAUGEN J E,et al.Technical Note:Downscaling RCM precipitation to the station scale using statistical transformations:A comparison of methods[J].Hydrology and Earth System Sciences,2012,16(9):3383-3390.
• [19] LIU J G,XIE Z H.BMA probabilistic quantitative precipitation forecasting over the Huaihe Basin using TIGGE multimodel ensemble forecasts[J].Monthly Weather Review,2014,142(4):1542-1555.
• [20] YANG Q Y,LI X G,SUN J,et al.Performance evaluation of multi-precipitation products fusion based on a novel dynamic K-nearest neighbour Bayesian ensemble calibration framework[J].International Journal of Climatology,2024,44(10):3427-3444.
• [21] 潘旸，谷军霞，宇婧婧，等.中国区域高分辨率多源降水观测产品的融合方法试验[J].气象学报，2018,76(5):755-766.PAN Y,GU J X,YU J J,et al.Test of merging methods for multi-source observed precipitation products at high resolution over China[J].Acta Meteorologica Sinica,2018,76(5):755-766.
• [22] 黄建刚，刘惠英.赣江主源贡水流域1957—2016年降雨特性[J].水土保持研究，2020,27(3):91-100.HUANG J G,LIU H Y.Precipitation characteristics of Gongshui Basin in the primary source of Ganjiang Basin during the period 1957—2016[J].Research of Soil and Water Conservation,2020,27(3):91-100.
• [23] 戴中山，李海峰.2011—2020年赣江上游主要支流水沙变化特征[J].水土保持研究，2024,31(1):178-186.DAI Z S,LI H F.Variation of runoff and sediment in the main tributaries of the upper Ganjiang River in the period from 2011 to 2020[J].Research of Soil and Water Conservation,2024,31(1):178-186.
• [24] 夏志明，廖凯涛，郭利平，等.基于EOF和MK趋势分析的赣江流域降水时空分布格局[J].水土保持研究，2023,30(5):223-233.XIA Z M,LIAO K T,GUO L P,et al.Spatiotemporal distribution pattern of precipitation in Ganjiang River Basin based on EOF and MK trend analysis[J].Research of Soil and Water Conservation,2023,30(5):223-233.
• [25] 袁飞，赵晶晶，任立良，等.TRMM多卫星测雨数据在赣江上游径流模拟中的应用[J].天津大学学报(自然科学与工程技术版),2013,46(7):611-616.YUAN F,ZHAO J J,REN L L,et al.Streamflow simulation in the upper Ganjiang River Basin using the TRMM multi-satellite precipitation data[J].Journal of Tianjin University (Science and Technology),2013,46(7):611-616.
• [26] 张余庆，项瑛，陈昌春，等.赣江流域旱涝时空变化特征研究[J].气象科学，2015,35(3):346-352.ZHANG Y Q,XIANG Y,CHEN C C,et al.Research on spatial-temporal variation of drought and flood events over Ganjiang basin[J].Journal of the Meteorological Sciences,2015,35(3):346-352.
• [27] 周瑜佳，袁飞，任立良，等.赣江上游土地覆被变化的水文响应研究[J].水电能源科学，2012,30(4):12-15.ZHOU Y J,YUAN F,REN L L,et al.Hydrologic responses of land cover change in upper reaches of Ganjiang River[J].Water Resources and Power,2012,30(4):12-15.
• [28] USHIO T,SASASHIGE K,KUBOTA T,et al.A Kalman filter approach to the global satellite mapping of precipitation (GSMaP) from combined passive microwave and infrared radiometric data[J].Journal of the Meteorological Society of Japan Ser II,2009,87A:137-151.
• [29] KUBOTA T,SHIGE S,HASHIZUME H,et al.Global precipitation map using satellite-borne microwave radiometers by the GSMaP project:Production and validation[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(7):2259-2275.
• [30] HOU A Y,KAKAR R K,NEECK S,et al.The global precipitation measurement mission[J].Bulletin of the American Meteorological Society,2014,95(5):701-722.
• [31] NGUYEN P,OMBADI M,SOROOSHIAN S,et al.The PERSIANN family of global satellite precipitation data:A review and evaluation of products[J].Hydrology and Earth System Sciences,2018,22(11):5801-5816.
• [32] NGUYEN P,OMBADI M,GOROOH V A,et al.PERSIANN dynamic infrared-rain rate (PDIR-now):A near-real-time,quasi-global satellite precipitation dataset[J].Journal of Hydrometeorology,2020,21(12):2893-2906.
• [33] NGUYEN P,SHEARER E J,TRAN H,et al.The CHRS Data Portal,an easily accessible public repository for PERSIANN global satellite precipitation data[J].Scientific Data,2019,6:180296.
• [34] 叶金印，邱旭敏，黄勇，等.气象遥感图像及格点场重采样插值方法[J].计算机工程与应用，2013,49(18):237-241.YE J Y,QIU X M,HUANG Y,et al.Resampling interpolation methods of meteorological remote sensing image and grid point field[J].Computer Engineering and Applications,2013,49(18):237-241.
• [35] MATBOLI M,KHALED A,AHMED M F,et al.Machine learning-based stratification of prediabetes and type 2 diabetes progression[J].Diabetology & Metabolic Syndrome,2025,17(1):227.
• [36] HANCOCK J T,KHOSHGOFTAAR T M.CatBoost for big data:An interdisciplinary review[J].Journal of Big Data,2020,7(1):94.
• [37] LIANG W Z,LUO S Z,ZHAO G Y,et al.Predicting hard rock pillar stability using GBDT,XGBoost,and LightGBM algorithms[J].Mathematics,2020,8(5):765.
• [38] CUI Z J,QING X X,CHAI H X,et al.Real-time rainfall-runoff prediction using light gradient boosting machine coupled with singular spectrum analysis[J].Journal of Hydrology,2021,603:127124.
• [39] ZHANG L,LI X,ZHENG D H,et al.Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach[J].Journal of Hydrology,2021,594:125969.
• [40] RAFTERY A E,GNEITING T,BALABDAOUI F,et al.Using Bayesian model averaging to calibrate forecast ensembles[J].Monthly Weather Review,2005,133(5):1155-1174.
• [41] WU Z Y,ZHANG Y L,SUN Z L,et al.Improvement of a combination of TMPA (or IMERG) and ground-based precipitation and application to a typical region of the East China Plain[J].Science of the Total Environment,2018,640-641:1165-1175.