文献类型：期刊文献

中文题名：基于随机森林的黄河流域地下水储量降尺度研究

英文题名：Downscaling of Groundwater Storage in the Yellow River Basin based on Random Forest

作者：刘梦然[1] 曹艳萍[2,3] 王少坤[2] 庞营军[4]

第一作者：刘梦然

机构：[1]河南大学数学与统计学院,河南开封475004;[2]河南大学地理科学与工程学部,河南郑州450046;[3]黄河中下游数字地理技术教育部重点实验室,河南开封475004;[4]中国林业科学研究院生态保护与修复研究所,北京100091

年份：2025

卷号：40

期号：3

起止页码：671-680

中文期刊名：遥感技术与应用

外文期刊名：Remote Sensing Technology and Application

收录：;北大核心:【北大核心2023】；

基金：国家自然科学基金项目“时空大数据支持下的黄河地区河南段生态系统过程模拟与服务”(U21A2014);河南省自然科学基金项“中国粮食主产区地下水时空演变及其驱动机制研究”(232300420160);“科技兴蒙”行动重点专项课题“毛乌素沙地荒漠化动态及荒漠化防治优化模式”(KJXM-EEDS-2020006)。

语种：中文

中文关键词：随机森林;特征筛选;地下水储量;降尺度;黄河流域

外文关键词：Random forest;Feature screening;Groundwater storage;Downscaling;Yellow River Basin

分类号：P641.8;TP75

摘要：GRACE卫星开创了遥感定量反演地下水变化量的新纪元,但存在空间分辨率低的问题。高分辨率地下水数据的获取将显著提升对局部水文过程的认识精度,为制定科学合理的地下水资源管理策略提供关键数据支撑。研究整理了黄河流域降水、气温、蒸散发、地表温度、归一化植被指数、土壤水等特征因子,首先采用偏最小二乘回归法针对1~12月份分别进行特征因子筛选,构建逐月最优特征因子集;之后,运用随机森林算法对黄河流域地下水数据进行由0.25°×0.25°降尺度至1 km×1 km的研究,并结合实测地下水位数据进行对比验证。结果表明:(1)除了蒸散发和地表温度以外,其余因子的重要性随月份的改变而改变;(2)时间序列上,降尺度前后地下水数据的相关系数和纳什系数均高达0.95,均方根误差为3.17 mm;(3)空间上,与降尺度前对比,降尺度后的地下水储量变化数据与实测地下水位的相关系数提高了47.67%。研究结果能够满足实际应用对高分辨率地下水数据的需求,并为地下水降尺度研究的特征因子筛选提供参考。
GRACE satellite has opened a new era of quantitative retrieval of groundwater change by remote sensing,but it has the problem of low spatial resolution.High-resolution groundwater observations will significantly improve the accuracy of local-scale hydrological process understanding,thereby offering essential data support for the development of scientifically based groundwater management policies.After sorting out the characteristic factors such as precipitation,air temperature,evapotranspiration,surface temperature,normalized vegetation index and soil water in the Yellow River Basin,partial least squares regression method was used to screen the characteristic factors respectively from January to December,and the optimal monthly characteristic factor subset was constructed.Then,the random forest algorithm was used to downscale the groundwater data of the Yellow River Basin from 0.25°×0.25°to 1 km×1 km,and compared and verified with the measured groundwater level data.The results show that:(1)Except evapotranspiration and surface temperature,the importance of other factors changes with the change of month;(2)In the time series,the correlation coefficient and Nash coefficient of groundwater data before and after downscaling are as high as 0.95,and the root-mean-square error is 3.17 mm;(3)Spatially,compared with before downscaling,the correlation coefficient between the change data of groundwater reserves and the measured groundwater level after downscaling increased by 47.67%.The research results can meet the demand for high-resolution groundwater data in practical applications,and provide reference for the feature factor screening of groundwater downscaling research.