浏览全部资源
扫码关注微信
纸质出版日期： 2021-08-07 ，
扫 描 看 全 文
何坤龙，赵伟，刘晓辉，刘蛟.2021.云雾覆盖下地表温度重建机器学习模型的训练集敏感性分析.遥感学报，25（8）： 1722-1734
He K L，Zhao W，Liu X H and Liu J. 2021. Sensitivity analysis of the training set to the performance of the machine learning-based land surface temperature reconstruction for cloud covered pixels. National Remote Sensing Bulletin， 25（8）：1722-1734
热红外遥感是监测地表温度的重要技术手段。然而，由于其易受云雾影响，热红外遥感反演地表温度存在大量的观测空白区域，严重影响地表温度产品的应用。近年来，机器学习算法的发展为实现地表温度无缝观测提供了新的技术手段。然而，基于机器学习的云雾覆盖像元重建方法与训练样本的数量和分布有着直接的联系，其应用条件在现有研究中还鲜有讨论。为深入探究重建过程中训练数据量和数值分布对重建精度的影响，本文选择基于随机森林的地表温度重建模型开展样本敏感性分析，采用美国MODIS陆地产品和欧洲第二代静止气象卫星（MSG）入射短波辐射产品重建不同训练样本集下的地表温度，并与真实地表温度数据比较，定量评估重建结果精度与样本数量和分布之间关系。研究结果表明：（1）地表温度重建精度随着训练样本数据量增加显著转好。（2）在数据量一定的情况下，随机采样方式因为具有空间代表性比区域取样方式具有更精确更稳定的精度，能将重建后的均方根误差降到2.1 K以下，相关系数达到0.93以上。即使数据量较小，随机取样方式的重建精度较稳定的特点使得模型对因数据量不足造成的重建精度降低的负面效应具有减弱作用。（3）进一步划分不同高程带和植被覆盖条件下的训练集，当训练集所处范围与重建集所处范围一致或者训练集覆盖范围越广时，重建精度越好。总体而言，上述研究成果为今后采用机器学习方法重建地表温度应用中训练样本选择以及获取高精度地表温度重建结果提供了重要的科学参考。
Land Surface Temperature (LST) represents integrated features of land atmosphere physical and dynamic processe
It is a key element in the fields of climate change
the land–atmosphere energy budget
and the global hydrological cycle
vegetation monitoring urban climate and environmental studies. Thermal infrared remote sensing is an important technique for monitoring LST. However
the Moderate Resolution Imaging Spectroradiometer (MODIS) data are severely contaminated by cloud cover
which limits the applications of LST products. In recent years
the development of machine learning algorithms provides a promising technique for the reconstruction of LST under clouds. However
the accuracy of the cloud cover pixel reconstruction method based on machine learning is directly related to the number and regional distribution of training samples. In order to quantitatively evaluate the impact of the number and regional distribution of training samples on the LST reconstruction accuracy
based on MODIS land products and Meteosat Second Generation (MSG) incident short-wave radiation products
the LST reconstruction model depending on random forest method to construct an LST linking model for LSTs and a range of influencing factors were fitted based on clear-sky observations
which was then applied to cloud-covered pixels to obtain an LST reconstruction
the proposed reconstruction model was applied to carry out the influence of different training samples on the reconstruction accuracy of LST. The results show that: (1) A visual comparison with daily LST observations from (MSG) incident short-wave radiation products indicated that the LSTs reconstructed using this method were representative of LST patterns resulting from the influence of key variables including solar radiation intensity
vegetation cover
and geographical factor. (2) The accuracy of LST reconstruction improves significantly with the increase of the amount of training sample data
and the reconstruction accuracy is also different in different seasons. When the amount of training data increases from 5% to 95%
there are seasonal differences between summer and autumn due to the differences in vegetation and solar radiation. The variation range of correlation coefficient and root mean square error in summer is larger than that in autumn. (3) The random sampling method has higher and stabler accuracy than the regional sampling method because of its spatial representativeness
which can reduce the root mean square error to less than 2.1 k and increase the correlation coefficient to more than 0.93. Even if the amount of data is small
the reconstruction accuracy with the random sampling method is relatively stable
the negative effect of the insufficient number of training samples on the reduction of reconstruction accuracy is weakened. (4) The training sets were divided according to different elevations and vegetation coverage ranges to reconstruct the LST
and the results showed that the reconstruction accuracy was better when the range of the training sets included the range of the reconstruction area
that is
when the training set contains enough data features
it has a satisfactory spatial representation. The research results show that the proposed reconstruction model has a strong potential to reconstruct LSTs under cloud-covered conditions
and can also accurately describe the spatial distributions of LST. It also can provide a reference for future machine learning methods to select appropriate training samples and reconstruct the LST with high accuracy.
地表温度随机森林重建训练数据高程植被
land surface temperaturerandom forestreconstructiontraining datasetelevationvegetation
Belgiu M and Drăguţ L. 2016. Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114: 24-31 [DOI: 10.1016/j.isprsjprs.2016.01.011http://dx.doi.org/10.1016/j.isprsjprs.2016.01.011]
Corbari C and Mancini M. 2014. Calibration and validation of a distributed energy–water balance model using satellite data of land surface temperature and ground discharge measurements. Journal of Hydrometeorology, 15(1): 376-392 [DOI: 10.1175/JHM-D-12-0173.1http://dx.doi.org/10.1175/JHM-D-12-0173.1]
Dai A G, Fyfe J C, Xie S P and Dai X G. 2015. Decadal modulation of global surface temperature by internal climate variability. Nature Climate Change, 5(6): 555-559 [DOI: 10.1038/nclimate2605http://dx.doi.org/10.1038/nclimate2605]
Duan S B, Ru C, Li Z L, Wang M M, Xu H Q, Li H, Wu P H, Zhan W F, Zhou J, Zhao W, Ren H Z, Wu H, Tang B H, Zhang X, Shang Guo F and Qin Z H. 2021. Reviews of methods for land surface temperature retrieval from Landsat thermal infrared data. National Remote Sensing Bulletin, 25(8): 1591-1617
段四波, 茹晨, 李召良, 王猛猛, 徐涵秋, 历华, 吴鹏海, 占文凤, 周纪, 赵伟, 任华忠, 吴骅, 唐伯惠, 张霞, 尚国琲, 覃志豪. 2021. Landsat卫星热红外数据地表温度遥感反演研究进展. 遥感学报, 25(8): 1591-1617 [DOI: 10.11834/jrs.20211296http://dx.doi.org/10.11834/jrs.20211296]
Fu P, Xie Y H, Weng Q H, Myint S, Meacham-Hensold K and Bernacchi C. 2019. A physical model-based method for retrieving urban land surface temperatures under cloudy conditions. Remote Sensing of Environment, 230: 111191 [DOI: 10.1016/j.rse.2019.05.010http://dx.doi.org/10.1016/j.rse.2019.05.010]
Geiger B, Meurey C, Lajas D, Franchistéguy L, Carrer D and Roujean J L. 2008. Near real‐time provision of downwelling shortwave radiation estimates derived from satellite observations. Meteorological Applications, 15(3): 411-420 [DOI: 10.1002/met.84http://dx.doi.org/10.1002/met.84]
Hong F L, Zhan W F, Göttsche F M, Liu Z H, Zhou J, Huang F, Lai J M and Li M C. 2018. Comprehensive assessment of four-parameter diurnal land surface temperature cycle models under clear-sky. ISPRS Journal of Photogrammetry and Remote Sensing, 142: 190-204 [DOI: 10.1016/j.isprsjprs.2018.06.008http://dx.doi.org/10.1016/j.isprsjprs.2018.06.008]
Im J, Park S, Rhee J, Baik J and Choi M. 2016. Downscaling of AMSR-E soil moisture with MODIS products using machine learning approaches. Environmental Earth Sciences, 75(15): 1120 [DOI: 10.1007/s12665-016-5917-6http://dx.doi.org/10.1007/s12665-016-5917-6]
Liu M, Tang R L, Li Z L, Gao M F and Yao Y J. 2021. Progress of data-driven remotely sensed retrieval methods and products on land surface evapotranspiration. National Remote Sensing Bulletin, 25(8): 1517-1537
刘萌, 唐荣林, 李召良, 高懋芳, 姚云军. 2021. 数据驱动的蒸散发遥感反演方法及产品研究进展. 遥感学报, 25(8): 1517-1537 [DOI: 10.11834/jrs.20211310http://dx.doi.org/10.11834/jrs.20211310]
Jin M L and Dickinson R E. 1999. Interpolation of surface radiative temperature measured from polar orbiting satellites to a diurnal cycle: 1. Without clouds. Journal of Geophysical Research, 104(D2): 2105-2116 [DOI: 10.1029/1998JD200005http://dx.doi.org/10.1029/1998JD200005]
Jin M L and Dickinson R E. 2000. A generalized algorithm for retrieving cloudy sky skin temperature from satellite thermal infrared radiances. Journal of Geophysical Research, 105(D22): 27037-27047 [DOI: 10.1029/2000JD900318http://dx.doi.org/10.1029/2000JD900318]
Kang J, Tan J L, Jin R, Li X and Zhang Y. 2018. Reconstruction of MODIS land surface temperature products based on multi-temporal information. Remote Sensing, 10(7): 1112 [DOI: 10.3390/rs10071112http://dx.doi.org/10.3390/rs10071112]
Kargar K, Samadianfard S, Parsa J, Nabipour N, Shamshirband S, Mosavi A and Chau K W. 2020. Estimating longitudinal dispersion coefficient in natural streams using empirical models and machine learning algorithms. Engineering Applications of Computational Fluid Mechanics, 14(1): 311-322 [DOI: 10.1080/19942060.2020.1712260http://dx.doi.org/10.1080/19942060.2020.1712260]
La Sorte F A, Butchart S H M, Jetz W and Böhning-Gaese K. 2014. Range-wide latitudinal and elevational temperature gradients for the world’s terrestrial birds: implications under global climate change. PLoS One, 9(5): e98361 [DOI: 10.1371/journal.pone.0098361http://dx.doi.org/10.1371/journal.pone.0098361]
Li Y C, Li M Y, Li C and Liu Z Z. 2020. Forest aboveground biomass estimation using Landsat 8 and Sentinel-1A data with machine learning algorithms. Scientific Reports, 10(1): 9952 [DOI: 10.1038/s41598-020-67024-3http://dx.doi.org/10.1038/s41598-020-67024-3]
Li Z L, Duan S B, Tang B H, Wu H, Ren H Z, Yan G J, Tang R L and Leng P. 2016. Review of methods for land surface temperature derived from thermal infrared remotely sensed data. Journal of Remote Sensing, 20(5): 899-920
李召良, 段四波, 唐伯惠, 吴骅, 任华忠, 阎广建, 唐荣林, 冷佩. 2016. 热红外地表温度遥感反演方法研究进展. 遥感学报, 20(5): 899-920 [DOI: 10.11834/jrs.20166192http://dx.doi.org/10.11834/jrs.20166192]
Long D, Bai L L, Yan L, Zhang C J, Yang W T, Lei H M, Quan J L, Meng X Y and Shi C X. 2019. Generation of spatially complete and daily continuous surface soil moisture of high spatial resolution. Remote Sensing of Environment, 233: 111364 [DOI: 10.1016/j.rse.2019.111364http://dx.doi.org/10.1016/j.rse.2019.111364]
Neteler M. 2010. Estimating daily land surface temperatures in mountainous environments by reconstructed MODIS LST data. Remote Sensing, 2(1): 333-351 [DOI: 10.3390/rs1020333http://dx.doi.org/10.3390/rs1020333]
Noi P T, Degener J and Kappas M. 2017. Comparison of multiple linear regression, cubist regression, and random forest algorithms to estimate daily air surface temperature from dynamic combinations of MODIS LST data. Remote Sensing, 9(5): 398 [DOI: 10.3390/rs9050398http://dx.doi.org/10.3390/rs9050398]
Shamshirband S, Hashemi S, Salimi H, Samadianfard S, Asadi E, Shadkani S, Kargar K, Mosavi A, Nabipour N and Chau K W. 2020. Predicting Standardized Streamflow index for hydrological drought using machine learning models. Engineering Applications of Computational Fluid Mechanics, 14(1): 339-350 [DOI: 10.1080/19942060.2020.1715844http://dx.doi.org/10.1080/19942060.2020.1715844]
Shwetha H R and Kumar D N. 2016. Prediction of high spatio-temporal resolution land surface temperature under cloudy conditions using microwave vegetation index and ANN. ISPRS Journal of Photogrammetry and Remote Sensing, 117: 40-55 [DOI: 10.1016/j.isprsjprs.2016.03.011http://dx.doi.org/10.1016/j.isprsjprs.2016.03.011]
Taormina R and Chau K W. 2015. ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS. Engineering Applications of Artificial Intelligence, 45: 429-440 [DOI: 10.1016/j.engappai.2015.07.019http://dx.doi.org/10.1016/j.engappai.2015.07.019]
Tian N M, Lan H X, Wu Y M and Li L P. 2020. Performance comparison of BP artificial neural network and CART decision tree model in landslide susceptibility prediction. Journal of Geo-information Science, 22(12): 2304-2316
田乃满, 兰恒星, 伍宇明, 李郎平. 2020. 人工神经网络和决策树模型在滑坡易发性分析中的性能对比. 地球信息科, 22(12): 2304-2316 [DOI: 10.12082/dqxxkx.2020.190766http://dx.doi.org/10.12082/dqxxkx.2020.190766]
Trigo I F, Dacamara C C, Viterbo P, Roujean J L, Olesen F, Barroso C, Camacho-de-Coca F, Carrer D, Freitas S C, García-Haro J, Geiger B, Gellens-Meulenberghs F, Ghilain N, Meliá J, Pessanha L, Siljamo N and Arboleda A. 2011. The satellite application facility for land surface analysis. International Journal of Remote Sensing, 32(9/10): 2725-2744 [DOI: 10.1080/01431161003743199http://dx.doi.org/10.1080/01431161003743199]
Wang F, Qin Z H, Fan W and Zhang S M. 2019. Quantitative analysis between land surface temperature and radiation covered by clouds. Journal of Remote Sensing, 23(6): 1113-1122
王斐, 覃志豪, 樊伟, 张胜茂. 2019. 云下地表温度与辐射变化关系的定量分析. 遥感学报, 23(6): 1113-1122 [DOI: 10.11834/jrs.20198151http://dx.doi.org/10.11834/jrs.20198151]
Wang X P, Zhang F and Ding J L. 2017. Evaluation of water quality based on a machine learning algorithm and water quality index for the Ebinur Lake Watershed, China. Scientific Reports, 7(1): 12858 [DOI: 10.1038/s41598-017-12853-yhttp://dx.doi.org/10.1038/s41598-017-12853-y]
Weng Q H, Fu P and Gao F. 2014. Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data. Remote Sensing of Environment, 145: 55-67 [DOI: 10.1016/j.rse.2014.02.003http://dx.doi.org/10.1016/j.rse.2014.02.003]
Wu P H, Shen H F, Zhang L P and Göttsche F M. 2015. Integrated fusion of multi-scale polar-orbiting and geostationary satellite observations for the mapping of high spatial and temporal resolution land surface temperature. Remote Sensing of Environment, 156: 169-181 [DOI: 10.1016/j.rse.2014.09.013http://dx.doi.org/10.1016/j.rse.2014.09.013]
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/rs11030300http://dx.doi.org/10.3390/rs11030300]
Wu P H, Yin Z X, Zeng C, Duan S B, Gottsche F M, Li X H, Ma X S, 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 [DOI: 10.1109/MGRS.2021.3050782http://dx.doi.org/10.1109/MGRS.2021.3050782]
Yang G, Sun W W, Shen H F, Meng X C and Li J L. 2019. An integrated method for reconstructing daily MODIS land surface temperature data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(3): 1026-1040 [DOI: 10.1109/JSTARS.2019.2896455http://dx.doi.org/10.1109/JSTARS.2019.2896455]
Ying W M, Liu X J, Fang S F, Li X J, Lai M, Zhang X Z and Wu H. 2020. Retrieval of daily net surface shortwave radiation climatic resources based on machine learning. Resources Science, 42(10): 1998-2009
应王敏, 刘晓洁, 房世峰, 李秀娟, 赖明, 张旭振, 吴骅. 2020. 基于机器学习的日尺度短波净辐射气候资源遥感反演研究. 资源科学, 42(10): 1998-2009 [DOI: 10.18402/resci.2020.10.16http://dx.doi.org/10.18402/resci.2020.10.16]
Yu W P, Tan J L, Ma M G, Li X L, She X J and Song Z J. 2019. An effective similar-pixel reconstruction of the high-frequency cloud-covered areas of Southwest China. Remote Sensing, 11(3): 336 [DOI: 10.3390/rs11030336http://dx.doi.org/10.3390/rs11030336]
Zeng C, Long D, Shen H F, Wu P H, Cui Y K and Hong Y. 2018. A two-step framework for reconstructing remotely sensed land surface temperatures contaminated by cloud. ISPRS Journal of Photogrammetry and Remote Sensing, 141: 30-45 [DOI: 10.1016/j.isprsjprs.2018.04.005http://dx.doi.org/10.1016/j.isprsjprs.2018.04.005]
Zhan C, Tang B H and Li Z L. 2018. Retrieval and validation of land surface temperature for atmospheres with air temperature inversion. Journal of Remote Sensing, 22(1): 28-37
战川, 唐伯惠, 李召良. 近地表大气逆温条件下的地表温度遥感反演与验证[J].遥感学报, 2018, 22(1):28-37 [DOI: 10.11834/jrs.20187043http://dx.doi.org/10.11834/jrs.20187043]
Zhang G L, Xiao X M, Dong J W, Kou W L, Jin C, Qin Y W, Zhou Y T, Wang J, Menarguez M A and Biradar C. 2015. Mapping paddy rice planting areas through time series analysis of MODIS land surface temperature and vegetation index data. ISPRS Journal of Photogrammetry and Remote Sensing, 106: 157-171 [DOI: 10.1016/j.isprsjprs.2015.05.011http://dx.doi.org/10.1016/j.isprsjprs.2015.05.011]
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 [https://doi.org/10.1016/j.rse.2021.112437https://doi.org/10.1016/j.rse.2021.112437]
Zhao W, Duan S B, Li A and Yin G. 2019. A practical method for reducing terrain effect on land surface temperature using random forest regression. Remote Sensing of Environment, 221, 635-649 [https://doi.org/10.1016/j.res.2018.21.008https://doi.org/10.1016/j.res.2018.21.008]
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.2020.111931http://dx.doi.org/10.1016/j.rse.2020.111931]
相关作者
相关机构
京公网安备11010802024621