[1]胡若轩,郑丽虹,李涛,等.基于不同插值方法的遥感土壤湿度数据重建精度比较[J].江苏水利,2025,(11):34-38.
　HU Ruoxuan,ZHENG Lihong,LI Tao,et al.Comparison of reconstruction accuracy for remote sensing soil moisture data based on different interpolation methods[J].JIANGSU WATER RESOURCES,2025,(11):34-38.
点击复制

基于不同插值方法的遥感土壤湿度数据重建精度比较()

《江苏水利》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年11期
页码:
34-38
栏目:
水文水资源
出版日期:
2025-11-01

文章信息/Info

Title:
Comparison of reconstruction accuracy for remote sensing soil moisture data based on different interpolation methods
文章编号:
1007-7839（2025）11-0034-0005
作者:
胡若轩1; 郑丽虹2; 李涛1; 刘睿璇1
（1.南京市滁河河道管理处，江苏 南京 210044；2.江苏省水利科学研究院，江苏 南京 210017）
Author(s):
HU Ruoxuan1;  ZHENG Lihong2;  LI Tao1;  LIURuixuan1
（1. Nanjing Chuhe River Channel Management Office, Nanjing 210044, China; 2. Jiangsu Hydraulic Research Institute, Nanjing 210017, China）
关键词:
土壤湿度; 插值法; 神经网络; 线性回归
Keywords:
soil moisture;  interpolation method;  neural network;  linear regression
分类号:
TV123
文献标志码:
B
摘要:
为重构缺测的遥感土壤湿度信息，基于气象、地形、植被、土壤等数据，采用统计空间插值（普通克里金法）、线性回归模型（多元线性回归法）、机器学习模型（人工神经网络、随机森林法）不同类型方法，模拟构建了多套数据模型。结合其他土壤湿度产品，从统计特征、空间分布规律等方面评估不同方法对重建精度的影响。结果显示：在数据质量优、缺测比例低的情形下，普通克里金法优势显著；而数据缺测比例高、缺测空间分布不均时，多元线性回归法和机器学习模型精度更高。
Abstract:
To reconstruct the missing remote sensing soil moisture information, multiple sets of data models were simulated and constructed using different types of methods—including statistical spatial interpolation （ordinary Kriging）, linear regression models （multiple linear regression）, and machine learning models （artificial neural networks, random forest）—based on data such as meteorology, topography, vegetation, and soil. Combined with other soil moisture products, the impact of different methods on reconstruction accuracy was evaluated in terms of statistical characteristics and spatial distribution patterns. The results show that ordinary Kriging has significant advantages when data quality is high and the missing data ratio is low; however, when the missing data ratio is high and the spatial distribution of missing data is uneven, multiple linear regression and machine learning models achieve higher accuracy.

参考文献/References:

[1]ILLSTON B G，BASARA J B，FIEBRICH C A，et al. Mesoscale monitoring of soil moisture across a statewide network[J]. Journal of Atmospheric and Oceanic Technology，2008，25（2）：167-182.
[2]KERR Y H. Soil moisture from space：Where are we[J]. Hydrogeology Journal，2007，15（1）：117-120.
[3]WANG C，FU B，ZHANG L，et al. Soil moisture-plant interactions：an ecohydrological review[J]. Journal of Soilsand Sediments，2019，19（1）：1-9.
[4]何涯舟，张珂，晁丽君，等. 基于多源遥感土壤湿度与模型数据同化的流域径流模拟[J]. 水资源保护，2023，39（2）：145-151，189.
[5]DOBRIYAL P，QURESHI A，BADOLA R，et al. A review of the methods available for estimating soil moisture andits implications for water resource management[J]. Journalof Hydrology，2012（458）：110-117.
[6]MAO K，SHI J，TANG H，et al. A neural network technique for separating land surface emissivity and temperature from ASTER imagery[J]. IEEE Transactions on Geoscience & Remote Sensing，2007，46（1）：200-208.
[7]ROBINSON D A，CAMPBELL C S，HOPMANS J W，et al. Soil moisture measurement for ecological and hydrological watershed-scale observatories：A review[J]. Vadose Zone Journal，2008，7（1）：358-389.
[8]AGHAKOUCHAK A，FARAHMAND A，MELYON F S，et al. Remote sensing of drought：Progress, challenges and opportunities[J]. Reviews of Geophysics，2015，53（2）：452-480.
[9]BINDLISH R，CROW W T，JACKSON T J. Role of Passive Microwave Remote Sensing in Improving Flood Forecasts[J]. IEEE Geoscience & Remote Sensing Letters，2009，6（1）：0-116.
[10]CHEN C F，SON N T，CHANG L Y，et al. Monitoring of soil moisture variability in relation to rice cropping systems in the Vietnamese Mekong Delta using MODIS data[J]. Applied Geography，2011，31（2）：463-475.
[11]DAI A，TRENBERTH K E，QIAN T. A global dataset of Palmer Drought Severity Index for 1870—2002：Relation-ship with soil moisture and effects of surface warming[J]. Journal of Hydrometeorology，2004，5（6）：1117-1130.
[12]ANDERSON M C，NORMAN J M，MECIKALSKI J R，et al. A climatological study of evapotranspiration andmoisture stress across the continental United States based on thermal remote sensing：1. Model formulation[J]. Journal of Geophysical Research：Atmospheres，2007，112（10）：73-84.
[13]SHEN H，LI X，CHENG Q，et al. Missing information reconstruction of remote sensing data：A technical review[J]. IEEE Geoscience and Remote Sensing Magazine，2015，3（3）：61-85.
[14]LIN C H，LAI K H，CHEN Z B，et al. Patch-based information reconstruction of cloud-contaminated multi-temporal images[J]. IEEE Transactions on Geoscience and Remote Sensing，2013，52（1）：163-174.
[15]MELGANI F. Contextual reconstruction of cloud-conta-minated multitemporal multispectral images[J]. IEEE Transactions on Geoscience and Remote Sensing，2006，44（2）：442-455.
[16] XIAO Z，JIANG L，ZHU Z，et al. Spatially and temporally complete satellite soil moisture data based on a data assimilation method[J]. Remote Sensing，2016，8（1）：49.
[17]WANG G，GARCIA D，LIU Y，et al. A three-dimensional gap filling method for large geophysical datasets：Application to global satellite soil moisture observations [J]. Environmental Modelling & Software，2012（30）：139-142.
[18]FATHOLOLOUMI S，VAEZI A R，ALAVIPANAH S K，etal. Comparison of spectral and spatial-based approaches for mapping the local variation of soil moisture in a semi-arid mountainous area[J]. Science of the Total Environment，2020（724）：138319.
[19]ZHANG L Q，LIU Y，REN L L，et al. Reconstruction of ESA CCI satellite-derived soil moisture using an artificial neural network technology[J]. Science of the Total Environment，2021（782）：146602.
[20]刘娣，孙佳倩，余钟波. 基于机器学习模型的多层土壤湿度反演[J]. 河海大学学报（自然科学版），2024，52（3）：7-14.

备注/Memo

备注/Memo:
收稿日期：2025-08-04
作者简介：胡若轩（1997—），男，硕士，研究方向为干旱监测与评估。15094302022。E-mail：779730312@qq.com
通信作者：郑丽虹（1996—），女，助理工程师，研究方向为干旱监测与评估。E-mail：rainbow0428@163.com
更新日期/Last Update: 2025-11-01