一种顾及空间异质性和噪声的遥感缺失数据重建方法

doi:10.13474/j.cnki.11-2246.2024.1207

摘要/Abstract

摘要： 针对光学遥感数据常存在大量缺失数据和噪声,以及现有光学遥感缺失数据重建算法大都未充分顾及地理数据空间相关密切程度的问题,本文充分利用地理空间数据间的时空关联性,提出了一种协同随机森林(RF)和地理加权回归(GWR)的重建方法(RF+GWR),分别以GF-4归一化植被指数(NDVI)、MODIS地表温度(LST)和GF-4反射率数据为试验材料,对RF+GWR方法的普适性和缺失重建性能进行了评估。试验结果表明,在所设不同云量掩膜水平下,相比于KNN和RF,RF+GWR方法在GF-4 NDVI、MODIS LST和GF-4波段反射率缺失数据方面的重建性能均有不同程度的改善,均方根误差、平均绝对误差和决定系数最大提升分别为33.07%、30.19%和7.06%。

关键词: 光学遥感, 缺失数据重建, 地理加权回归, 随机森林, K最近邻

Abstract: In response to the common issue of extensive missing data in optical remote sensing data and the insufficient consideration of the spatial correlation of geographic data in existing algorithms for data reconstruction, this paper fully utilizes the spatio-temporal correlation between geographic spatial data and proposes a reconstruction method that combines random forest(RF) and geographically weighted regression(GWR), termed as RF+GWR. Using normalized difference vegetation index (NDVI) from GF-4, MODIS land surface temperature (LST), and GF-4 reflectance data as experimental materials, the universality and missing data reconstruction performance of the RF+GWR method are evaluated. Experimental results show that, under different cloud masking levels as set in the paper, compared to K-nearest neighbor (KNN) and RF methods, the RF+GWR method exhibits varying degrees of improvement in reconstructing missing data of GF-4 NDVI, MODIS LST, and GF-4 band reflectance data. The maximum improvements in root mean square error, mean absolute error, and coefficient of determination are 33.07%, 30.19%, and 7.06%.

Key words: optical remote sensing, missing data reconstruction, geographically weighted regression, random forest, K-nearest neighbor

中图分类号:

P237

雷楷烨, 张显云, 刘晶晖, 吴雪. 一种顾及空间异质性和噪声的遥感缺失数据重建方法[J]. 测绘通报, 2024, 0(12): 40-47.

LEI Kaiye, ZHANG Xianyun, LIU Jinghui, WU Xue. A reconstruction method for remote sensing missing data considering spatial heterogeneity and noise[J]. Bulletin of Surveying and Mapping, 2024, 0(12): 40-47.

参考文献

[1] 陈媛媛,孙丽,杜英坤,等.农业干旱遥感监测研究进展与展望[J].遥感信息,2022,37(6): 1-7.
[2] 董春媛,乔荣荣,杨智程,等.基于改进遥感生态指数的宁夏沿黄平原区生态环境质量评价[J].生态学报,2023,43(16): 6706-6715.
[3] 许强,郭晨,董秀军.地质灾害航空遥感技术应用现状及展望[J].测绘学报,2022,51(10): 2020-2033.
[4] 曹春萍,李昂.融合多尺度信息和混合注意力的遥感图像重建[J].软件工程,2023,26(11): 5-10.
[5] 胡欣,刘瑞杰.基于光谱重建技术的遥感图像复原方法[J].激光杂志,2023,44(11): 72-76.
[6] 莫亚萍.遥感反演近地表气温的全天候重建研究[D].南京: 南京信息工程大学,2023.
[7] 陈彦军,张玉红.无参考图条件下的Landsat-7 SLC-off图像缺失像素填充算法研究[J].地理科学,2021,41(7): 1276-1284.
[8] 周芳成,唐世浩,韩秀珍,等.云下遥感地表温度重构方法研究[J].国土资源遥感,2021,33(1): 78-85.
[9] 王一明,蒙继华,程志强.关键物候期遥感数据缺失条件下的数据同化研究[J].遥感技术与应用,2017,32(4): 615-623.
[10] 俞晓群,马翱慧.基于Kriging空间插补海表叶绿素遥感缺失数据的研究[J].测绘通报,2013(12): 47-50.
[11] LIU Hua,WENG Qihao.Scaling effect of fused ASTER-MODIS land surface temperature in an urban environment[J].Sensors,2018,18(11): 4058.
[12] OZELKAN E,BAGIS S,OZELKAN E C,et al.Spatial interpolation of climatic variables using land surface temperature and modified inverse distance weighting[J].International Journal of Remote Sensing,2015,36(4): 1000-1025.
[13] WU Penghai,YIN Zhixiang,ZENG Chao,et al.Spatially continuous and high-resolution land surface temperature product generation: a review of reconstruction and spatiotemporal fusion techniques[J].IEEE Geoscience and Remote Sensing Magazine,2021,9(3): 112-137.
[14] ZHU Wenquan,PAN Yaozhong,HE Hao,et al.A changing-weight filter method for reconstructing a high-quality NDVI time series to preserve the integrity of vegetation phenology[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(4): 1085-1094.
[15] FU Peng,XIE Yanhua,WENG Qihao,et al.A physical model-based method for retrieving urban land surface temperatures under cloudy conditions[J].Remote Sensing of Environment,2019,230: 111191.
[16] ZHANG Xiaodong,ZHOU Ji,LIANG Shunlin,et al.A practical reanalysis data and thermal infrared remote sensing data merging (RTM) method for reconstruction of a 1-km all-weather land surface temperature[J].Remote Sensing of Environment,2021,260: 112437.
[17] LI Xiaoma,ZHOU Yuyu,ASRAR G R,et al.Creating a seamless 1 km resolution daily land surface temperature dataset for urban and surrounding areas in the conterminous United States[J].Remote Sensing of Environment,2018,206: 84-97.
[18] JIA Aolin,MA Han,LIANG Shunlin,et al.Cloudy-sky land surface temperature from VIIRS and MODIS satellite data using a surface energy balance-based method[J].Remote Sensing of Environment,2021,263: 112566.
[19] CHEN Aoxuan,YANG Jin,HE Yan,et al.High spatiotemporal resolution estimation of AOD from Himawari-8 using an ensemble machine learning gap-filling method[J].The Science of the Total Environment,2023,857(3): 159673.
[20] WU Penghai,SU Yang,DUAN Sibo,et al.A two-step deep learning framework for mapping gapless all-weather land surface temperature using thermal infrared and passive microwave data[J].Remote Sensing of Environment,2022,277: 113070.
[21] ZHANG Xiaodong,ZHOU Ji,LIANG S,et al.Estimation of 1-km all-weather remotely sensed land surface temperature based on reconstructed spatial-seamless satellite passive microwave brightness temperature and thermal infrared data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,167:321-344.
[22] 杨泽航,王文,鲍健雄.融合多源遥感数据的黑河中游地区生长季早期作物识别[J].地球信息科学学报,2022,24(5): 996-1008.
[23] DUAN Sibo,LI Zhaoliang,LENG Pei.A framework for the retrieval of all-weather land surface temperature at a high spatial resolution from polar-orbiting thermal infrared and passive microwave data[J].Remote Sensing of Environment,2017,195: 107-117.
[24] ZHU Xiaolin,LIU Desheng,CHEN Jin.A new geostatistical approach for filling gaps in Landsat ETM+SLC-off images[J].Remote Sensing of Environment,2012,124: 49-60.
[25] WEISS D J,ATKINSON P M,BHATT S,et al.An effective approach for gap-filling continental scale remotely sensed time-series[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,98: 106-118.
[26] GERBER F,DE JONG R,SCHAEPMAN M E,et al.Predicting missing values in spatio-temporal remote sensing data[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(5): 2841-2853.
[27] SARAFANOV M,KAZAKOV E,NIKITIN N O,et al.A machine learning approach for remote sensing data gap-filling with open-source implementation: an example regarding land surface temperature,surface albedo and NDVI[J].Remote Sensing,2020,12(23): 3865.
[28] TOBLER W R.A computer movie simulating urban growth in the Detroit Region[J].Economic Geography,1970,46: 234.
[29] BRUNSDON C,FOTHERINGHAM A S,CHARLTON M E.Geographically weighted regression: a method for exploring spatial nonstationarity[J].Geographical Analysis,1996,28(4): 281-298.
[30] MEYER H,LEHNERT L W,WANG Yun,et al.From local spectral measurements to maps of vegetation cover and biomass on the Qinghai-Tibet-Plateau: do we need hyperspectral information？[J].International Journal of Applied Earth Observation and Geoinformation,2017,55: 21-31.
[31] 熊艳,高仁强,徐战亚.机载LiDAR点云数据降维与分类的随机森林方法[J].测绘学报,2018,47(4): 508-518.
[32] KNIPLING E B.Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation[J].Remote Sensing of Environment,1970,1(3): 155-159.
[33] PRICE J C.Examples of high resolution visible to near-infrared reflectance spectra and a standardized collection for remote sensing studies[J].International Journal of Remote Sensing,1995,16(6): 993-1000.