AMSR2亮温轨道间隙时空谱随机森林重建

陈家楠; 张丽; 张贺; 储栋; 殷志祥; 吴鹏海

doi:10.11834/jrs.20265233

模型与方法 | 浏览量 : 0 下载量: 15 CSCD: 0

R-PDF
PDF
导出
分享
收藏
专辑

AMSR2亮温轨道间隙时空谱随机森林重建
Spatiotemporal-spectral random forest reconstruction of orbital gaps in AMSR2 brightness temperature
2026年30卷第6期页码：1856-1870
收稿：2025-06-27，

网络首发：2026-06-17，

纸质出版：2026-06-07
DOI： 10.11834/jrs.20265233
稿件说明：

移动端阅览

陈家楠，张丽，张贺，储栋，殷志祥，吴鹏海.2026.AMSR2亮温轨道间隙时空谱随机森林重建.遥感学报，30（6）： 1856-1870 DOI： 10.11834/jrs.20265233.

Chen J N，Zhang L，Zhang H，Chu D，Yin Z X and Wu P H. 2026. Spatiotemporal-spectral random forest reconstruction of orbital gaps in AMSR2 brightness temperature. National Remote Sensing Bulletin， 30（6）：1856-1870 DOI： 10.11834/jrs.20265233.

摘要

亮温是被动微波遥感的重要基础观测量，是反演地表温度、土壤湿度、雪水当量等关键地表参量的重要输入数据，在气象、气候与环境遥感领域具有重要的科学价值与应用潜力。被动微波传感器AMSR2（Advanced Microwave Scanning Radiometer 2）可获得全天候、全球覆盖的亮温数据，但受轨道设计与传感器特性限制，AMSR2亮温数据存在轨道间隙，影响数据的完整性和应用精度。本文在分析轨道间隙时空特征及亮温数据与环境变量广义谱的非线性关系基础上，提出一种时空谱随机森林STSRF（Spatio-Temporal Spectral Random Forest）多维度重建模型。以2020年中国区域AMSR2亮温数据为例，按月份及昼夜独立构建训练和验证数据集；开展模拟实验和真实实验，并评估重建前后数据的降尺度效果。在模拟实验中，STSRF重建亮温具有较高精度，昼、夜场景下均方根误差分别为0.78—2.21 K和0.73—2.35 K），且在高海拔地区整体重建精度优于其他区域；在真实实验中，STSRF重建亮温在空间分布上与AMSR2观测数据高度吻合，无明显重建痕迹。此外，降尺度对比分析表明，与直接降尺度方案相比，基于重建数据的降尺度结果在空间细节保持和数值精度方面更具优势，进一步验证了重建策略的有效性。因此，STSRF方法不仅能有效重建AMSR2亮温轨道间隙数据，还有助于后续降尺度处理，为大范围高分辨率微波遥感应用提供技术支持。

Abstract

Brightness Temperature (BT) serves as a critical geophysical parameter reflecting the Earth’s surface energy budget and holds substantial significance in meteorological monitoring

climate change studies

and environmental remote sensing. The Advanced Microwave Scanning Radiometer 2 (AMSR2) enables global

all-weather acquisition of BT data. However

because of orbital design constraints and sensor-specific characteristics

the AMSR2 BT product suffers from orbital data gaps

which hinder its continuity and limit its effectiveness in quantitative applications. This study aims to develop a robust reconstruction framework to address these data discontinuities and improve the spatiotemporal integrity of AMSR2 BT datasets.

To reconstruct the missing orbital BT data

we propose a novel multidimensional model termed spatiotemporal-spectral random forest (STSRF). The model integrates spatiotemporal patterns with generalized spectral features that characterize the nonlinear relationships between BT and multiple environmental variables. Using the 2020 AMSR2 BT dataset over China as a case study

we separately constructed training and validation datasets on a monthly basis for daytime and nighttime observations. Simulated data masking and real-missing data scenarios were applied to evaluate reconstruction accuracy. Moreover

downscaling experiments were conducted before and after reconstruction to assess the influence of data integrity on spatial detail restoration.

In the simulation experiments

the STSRF model demonstrated high reconstruction accuracy

with root-mean-square errors ranging from 0.78 K to 2.21 K during the day and from 0.73 K to 2.35 K at night. Notably

the model achieved superior performance in high-altitude regions. In real experiments

the spatial distribution of reconstructed BT closely matched original AMSR2 observations

showing no discernible reconstruction artifacts. Downscaling evaluation revealed that the STSRF-based reconstruction significantly enhanced numerical precision and spatial feature retention compared with the direct downscaling applied to incomplete datasets. The enhanced numerical precision and spatial feature retention observed in the downscaling evaluation confirm the added value of gap filling prior to resolution enhancement.

The proposed STSRF model effectively overcomes the limitations of traditional single-feature approaches by incorporating multidimensional information

including temporal dynamics and environmental variability. It provides a reliable strategy for reconstructing AMSR2 BT orbital gaps while enhancing downstream data usability for high-resolution microwave remote sensing applications. The results affirm that spatiotemporal and spectral feature fusion not only improves reconstruction robustness but also supports accurate and complete environmental monitoring over large regions.

关键词

Keywords

references

Chu D , Shen H F , Guan X B , Chen J M , Li X H , Li J and Zhang L P . 2021 . Long time-series NDVI reconstruction in cloud-prone regions via spatio-temporal tensor completion . Remote Sensing of Environment , 264 : 112632 [ DOI: 10.1016/j.rse.2021.112632 http://dx.doi.org/10.1016/j.rse.2021.112632 ]

Ding L R , Zhou J , Zhang X D , Wang S F , Tang W B , Wang Z W , Ma J , Ai L J , Li M S and Wang W . 2023 . Estimation of all-weather land surface temperature with remote sensing: progress and challenges . National Remote Sensing Bulletin , 27 ( 7 ): 1534 - 1553

丁利荣 , 周纪 , 张晓东 , 王韶飞 , 唐文彬 , 王子卫 , 马晋 , 艾丽皎 , 李明松 , 王伟 . 2023 . 全天候地表温度遥感获取进展与挑战 . 遥感学报 , 27 ( 7 ): 1534 - 1553 [ DOI: 10.11834/jrs.20211323 http://dx.doi.org/10.11834/jrs.20211323 ]

Duan S B , Li Z L and Leng P . 2017 . 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 . Remote Sensing of Environment , 195 : 107 - 117 [ DOI: 10.1016/j.rse.2017.04.008 http://dx.doi.org/10.1016/j.rse.2017.04.008 ]

Ghafarian Malamiri H R , Rousta I , Olafsson H , Zare H and Zhang H . 2018 . Gap-filling of MODIS time series land surface temperature (LST) products using singular spectrum analysis (SSA) . Atmosphere , 9 ( 9 ): 334 [ DOI: 10.3390/atmos9090334 http://dx.doi.org/10.3390/atmos9090334 ]

Huang X H , Li C , Yang T , Cao B , Cheng J , Xie G C and Wu P H . 2023 . Seamless reconstruction of AMSR-E land surface temperature swath gaps for China’s landmass . IEEE Transactions on Geoscience and Remote Sensing , 61 : 4411615 [ DOI: 10.1109/TGRS.2023.3335820 http://dx.doi.org/10.1109/TGRS.2023.3335820 ]

Ji W Z , Chen Y H , Xia H P , Gao H and Zhu L . 2025 . Jointing adjacent environmental variation into a deep learning model for gap-filling passive microwave-based land surface temperature . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 18 : 9682 - 9700 [ DOI: 10.1109/JSTARS.2025.3554810 http://dx.doi.org/10.1109/JSTARS.2025.3554810 ]

Jing Y H , Shen H F , Li X H , Wu J G and Qiu Z H . 2024 . Spatial downscaling of remote sensing parameters from perspective of data fusion [J ] . Geomatics and Information Science of Wuhan University , 49 ( 2 ): 175 - 189

景映红 , 沈焕锋 , 李星华 , 吴金橄 , 邱中航 . 2024 . 数据融合视角下的遥感参量空间降尺度 . 武汉大学学报(信息科学版) , 49 ( 2 ): 175 - 189 [ DOI: 10.13203/j.whugis20220549 http://dx.doi.org/10.13203/j.whugis20220549 ]

Kerr Y H , Waldteufel P , Wigneron J P , Delwart S , Cabot F , Boutin J , Escorihuela M J , Font J , Reul N , Gruhier C , Juglea S E , Drinkwater M R , Hahne A , Martín-Neira M and Mecklenburg S . 2010 . The SMOS mission: new tool for monitoring key elements of the global water cycle . Proceedings of the IEEE , 98 ( 5 ): 666 - 687 [ DOI: 10.1109/JPROC.2010.2043032 http://dx.doi.org/10.1109/JPROC.2010.2043032 ]

Lian Y H , Duan S B , Huang C , Han W J and Liu M . 2023 . Generation of spatial-seamless AMSR2 land surface temperature in China during 2012-2020 using a deep neural network . IEEE Transactions on Geoscience and Remote Sensing , 61 : 5300618 [ DOI: 10.1109/TGRS.2023.3247806 http://dx.doi.org/10.1109/TGRS.2023.3247806 ]

Njoku E G , Jackson T J , Lakshmi V , Chan T K and Nghiem S V . 2003 . Soil moisture retrieval from AMSR-E . IEEE Transactions on Geoscience and Remote Sensing , 41 ( 2 ): 215 - 229 [ DOI: 10.1109/TGRS.2002.808243 http://dx.doi.org/10.1109/TGRS.2002.808243 ]

Owe M , de Jeu R and Holmes T . 2008 . Multisensor historical climatology of satellite-derived global land surface moisture . Journal of Geophysical Research: Earth Surface , 113 ( F1 ): F 01002 [ DOI: 10.1029/2007JF000769 http://dx.doi.org/10.1029/2007JF000769 ]

Peng J , Loew A , Zhang S Q , Wang J and Niesel J . 2016 . Spatial downscaling of satellite soil moisture data using a vegetation temperature condition index . IEEE Transactions on Geoscience and Remote Sensing , 54 ( 1 ): 558 - 566 [ DOI: 10.1109/TGRS.2015.2462074 http://dx.doi.org/10.1109/TGRS.2015.2462074 ]

Prigent C , Aires F , Rossow W B and Robock A . 2005 . Sensitivity of satellite microwave and infrared observations to soil moisture at a global scale: relationship of satellite observations to in situ soil moisture measurements . Journal of Geophysical Research: Atmospheres , 110 ( D7 ): D 07110 [ DOI: 10.1029/2004JD005087 http://dx.doi.org/10.1029/2004JD005087 ]

Prigent C , Rossow W B and Matthews E . 1997 . Microwave land surface emissivities estimated from SSM/I observations . Journal of Geophysical Research: Atmospheres , 102 ( D18 ): 21867 - 21890 [ DOI: 10.1029/97JD01360 http://dx.doi.org/10.1029/97JD01360 ]

Su Y , Wu P H , Cheng J , Yin Z X , Ma X S and Yang H . 2022 . Research on deep learning methods for AMSR-E land surface temperature data reconstruction . National Remote Sensing Bulletin , 26 ( 4 ): 739 - 751

苏扬 , 吴鹏海 , 程洁 , 殷志祥 , 马晓双 , 杨辉 . 2022 . AMSR-E地表温度数据重建深度学习方法 . 遥感学报 , 26 ( 4 ): 739 - 751 [ DOI: 10.11834/jrs.20220426 http://dx.doi.org/10.11834/jrs.20220426 ]

Sun R , Rong Y , Su H B and Chen S H . 2016 . NDVI time-series reconstruction based on MODIS and HJ-1 CCD data spatial-temporal fusion . Journal of Remote Sensing (in Chinese) , 20 ( 3 ): 361 - 373

孙锐 , 荣媛 , 苏红波 , 陈少辉 . 2016 . MODIS和HJ-1CCD数据时空融合重构NDVI时间序列 . 遥感学报 , 20 ( 3 ): 361 - 373 [ DOI: 10.11834/jrs.20165173 http://dx.doi.org/10.11834/jrs.20165173 ]

Tang W B , Xue D J , Long Z Y , Zhang X D and Zhou J . 2022 . Near-real-time estimation of 1-km all-weather land surface temperature by integrating satellite passive microwave and thermal infrared observations . IEEE Geoscience and Remote Sensing Letters , 19 : 7001305 [ DOI: 10.1109/LGRS.2021.3067908 http://dx.doi.org/10.1109/LGRS.2021.3067908 ]

Tang W B , Zhou J , Ma J , Wang Z W , Ding L R , Zhang X D , and Zhang X . 2024 . TRIMS LST: a daily 1 km all-weather land surface temperature dataset for China’s landmass and surrounding areas (2000-2022) . Earth System Science Data , 16 ( 1 ): 387 - 419 [ DOI: 10.5194/essd-16-387-2024 http://dx.doi.org/10.5194/essd-16-387-2024 ]

Tong C , Wang H Q , Zhu L Y , Deng X D and Wang K . 2022 . Reconstruct SMAP brightness temperature scanning gaps over Qinghai-Tibet Plateau . International Journal of Applied Earth Observation and Geoinformation , 115 : 103090 [ DOI: 10.1016/j.jag.2022.103090 http://dx.doi.org/10.1016/j.jag.2022.103090 ]

Wang Q M , Tang Y J , Tong X H and Atkinson P M . 2024 . Filling gaps in cloudy Landsat LST product by spatial-temporal fusion of multi-scale data . Remote Sensing of Environment , 306 : 114142 [ DOI: 10.1016/j.rse.2024.114142 http://dx.doi.org/10.1016/j.rse.2024.114142 ]

Wang Q M , Wang L X , Zhu X L , Ge Y , Tong X H and Atkinson P M . 2022 . Remote sensing image gap filling based on spatial-spectral random forests . Science of Remote Sensing , 5 : 100048 [ DOI: 10.1016/j.srs.2022.100048 http://dx.doi.org/10.1016/j.srs.2022.100048 ]

Wu P H , Su Y , Duan S B , Li X H , Yang H , Zeng C , Ma X S , Wu Y L and Shen H F . 2022 . A two-step deep learning framework for mapping gapless all-weather land surface temperature using thermal infrared and passive microwave data . Remote Sensing of Environment , 277 : 113070 [ DOI: 10.1016/j.rse.2022.113070 http://dx.doi.org/10.1016/j.rse.2022.113070 ]

Wu P H , Yin Z X , Yang H , Wu Y L and Ma X S . 2019 . Reconstructing geostationary satellite land surface temperature imagery based on a multiscale feature connected convolutional neural network . Remote Sensing , 11 ( 3 ): 300 [ DOI: 10.3390/rs11030300 http://dx.doi.org/10.3390/rs11030300 ]

Wu P H , Yin Z X , Zeng C , Duan S B , Göttsche F M , Ma X S , Li X H , Yang H and Shen H F . 2021 . Spatially continuous and high-resolution land surface temperature product generation: a review of reconstruction and spatiotemporal fusion techniques . IEEE Geoscience and Remote Sensing Magazine , 9 ( 3 ): 112 - 137 [ DOI: 10.1109/MGRS.2021.3050782 http://dx.doi.org/10.1109/MGRS.2021.3050782 ]

Xiao Y , Zhao W , Ma M G and He K L . 2021 . Gap-free LST generation for MODIS/terra LST product using a random forest-based reconstruction method . Remote Sensing , 13 ( 14 ): 2828 [ DOI: 10.3390/rs13142828 http://dx.doi.org/10.3390/rs13142828 ]

Xu S and Cheng J . 2021 . A new land surface temperature fusion strategy based on cumulative distribution function matching and multiresolution Kalman filtering . Remote Sensing of Environment , 254 : 112256 [ DOI: 10.1016/j.rse.2020.112256 http://dx.doi.org/10.1016/j.rse.2020.112256 ]

Zhang X D , Zhou J , Göttsche F M , Zhan W F , Liu S M and Cao R Y . 2019 . A method based on temporal component decomposition for estimating 1-km all-weather land surface temperature by merging satellite thermal infrared and passive microwave observations . IEEE Transactions on Geoscience and Remote Sensing , 57 ( 7 ): 4670 - 4691 [ DOI: 10.1109/TGRS.2019.2892417 http://dx.doi.org/10.1109/TGRS.2019.2892417 ]

Zhang X D , Zhou J , Liang S L , Chai L N , Wang D D and Liu J . 2020 . 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 . ISPRS Journal of Photogrammetry and Remote Sensing , 167 : 321 - 344 [ DOI: 10.1016/j.isprsjprs.2020.07.014 http://dx.doi.org/10.1016/j.isprsjprs.2020.07.014 ]

Zhang X D , Zhou J , Liang S L and Wang D D . 2021 . A practical reanalysis data and thermal infrared remote sensing data merging (RTM) method for reconstruction of a 1-km all-weather land surface temperature . Remote Sensing of Environment , 260 : 112437 [ DOI: 10.1016/j.rse.2021.112437 http://dx.doi.org/10.1016/j.rse.2021.112437 ]

Zhao W and Duan S B . 2020 . Reconstruction of daytime land surface temperatures under cloud-covered conditions using integrated MODIS/Terra land products and MSG geostationary satellite data . Remote Sensing of Environment , 247 : 111931 [ DOI: 10.1016/j.rse.2020.111931 http://dx.doi.org/10.1016/j.rse.2020.111931 ]

Zhou J , Dai F N , Zhang X D , Zhao S J and Li M S . 2015 . Developing a temporally land cover-based look-up table (TL-LUT) method for estimating land surface temperature based on AMSR-E data over the Chinese landmass . International Journal of Applied Earth Observation and Geoinformation , 34 : 35 - 50 [ DOI: 10.1016/j.jag.2014.07.001 http://dx.doi.org/10.1016/j.jag.2014.07.001 ]