| 689 | 14 | 280 |
| 下载次数 | 被引频次 | 阅读次数 |
地表温度(Land Surface Temperature, LST)是热环境监测中的重要参数之一。针对LST降尺度,开展了极端梯度提升树(Extreme Gradient Boost, XGBoost)用于LST的空间降尺度研究,对比分析了地表反射率、光谱指数、地形因子、大气再分析数据、经纬度以及地表覆盖类型6种回归核在不同组合形式条件下将1 km分辨率的MODISLST产品降尺度至100 m分辨率的LST的模型性能。研究结果表明,选取group2(光谱指数)、group4(光谱指数、地形)、group7(光谱指数、经纬度)作为回归核时,模型表现能力最好,此时均方根误差在2 K左右,且能保持清晰的图像纹理。光谱指数对于LST降尺度的作用较为重要。单个局部研究区数据训练的降尺度模型泛化能力还是不够,为保证降尺度图像的准确性和相似性,XGBoost模型在训练过程中仍需选择更具代表性的训练数据。
Abstract：Land Surface Temperature(LST) is one of the important parameters in thermal environment monitoring.The downscaling method of land surface temperature by using the Extreme Gradient Boosting Tree(XGBoost) model is studied.The performance of the LST model for downscaling MODISLST product of 1 km resolution to 100 m resolution is compared and analyzed under different combinations of six regression kernels including surface reflectance, spectral index, topographic factors, atmospheric reanalysis data, longitude and latitude information, and surface coverage types.The results show that when group2(spectral index),group4(spectral index, terrain) and group7(spectral index, longitude and latitude information) are selected as the regression kernel, the performance of the model is the best, the RMSE is about 2 K,and clear texture can be maintained.The spectral index plays an important role in the downscaling of surface temperature.However, the generalization capability of downscaling model trained by local data itself is still insufficient.To ensure the accuracy and similarity of the downscaled images, training data with higher representativeness should be selected for the XGBoost model in the training process.
[1] VOOGT J A,OKE T R.Thermal Remote Sensing of Urban Climates[J].Remote Sensing of Environment,2003,86(3):370-384.
[2] GIGLIO L,CSISZAR I,RESTáS á,et al.Active Fire Detection and Characterization with the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)[J].Remote Sensing of Environment,2008,112(6):3055-3063.
[3] DIN S U,MAK H W L.Retrieval of Land-Use/Land Cover Change (LUCC) Maps and Urban Expansion Dynamics of Hyderabad,Pakistan via Landsat Datasets and Support Vector Machine Framework[J].Remote Sensing,2021,13(16):3337.
[4] MUSTAFA E K,EL-HAMID H T A,TARAWALLY M.Spatial and Temporal Monitoring of Drought Based on Land Surface Temperature,Freetown City,Sierra Leone,West Africa[J].Arabian Journal of Geosciences,2021,14(11):1013-1108.
[5] ANDERSON M C,ALLEN R G,MORSE A,et al.Use of Landsat Thermal Imagery in Monitoring Evapotranspiration and Managing Water Resources[J].Remote Sensing of Environment,2012,122:50-65.
[6] GAO F,MASEK J,SCHWALLER M,et al.On the Blending of the Landsat and MODIS Surface Reflectance:Predicting Daily Landsat Surface Reflectance[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(8):2207-2218.
[7] KUSTAS W P,NORMAN J M,ANDERSON M C,et al.Estimating Subpixel Surface Temperatures and Energy Fluxes from the Vegetation Index-radiometric Temperature Relationship[J].Remote Sensing of Environment,2003,85(4):429-440.
[8] AGAM N,KUSTAS W P,ANDERSON M C,et al.A Vegetation Index Based Technique for Spatial Sharpening of Thermal Imagery[J].Remote Sensing of Environment,2007,107(4):545-558.
[9] DOMINGUEZ A,KLEISSL J,LUVALL J C,et al.High-resolution Urban Thermal Sharpener (HUTS)[J].Remote Sensing of Environment,2011,115(7):1772-1780.
[10] ESSA W,VERBEIREN B,VAN DER KWAST J,et al.Evaluation of the DisTrad Thermal Sharpening Methodology for Urban Areas[J].International Journal of Applied Earth Observation & Geoinformation,2012,19:163-172.
[11] DUAN S B,LI Z L.Spatial Downscaling of MODIS Land Surface Temperatures Using Geographically Weighted Regression:Case Study in Northern China[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(11):6458-6469.
[12] GAO F,KUSTAT W P,ANDERSON M C.A Data Mining Approach for Sharpening Thermal Satellite Imagery over Land[J].Remote Sensing,2012,4(11):3287-3319.
[13] HUTENGS C,VOHLAND M.Downscaling Land Surface Temperatures at Regional Scales with Random Forest Regression[J].Remote Sensing of Environment,2016,178:127-141.
[14] 李婉，牛陆，陈虹，等.基于随机森林算法的地表温度鲁棒降尺度方法[J].地球信息科学学报，2020,22(8):1666-1678.
[15] CHEN T Q,GUESTRIN C.XGBoost:A Scalable Tree Boosting System[J].arXiv preprint arXiv,1603.02754,2016.
[16] XIA H P,CHEN Y H,LI Y,et al.Combining Kernel-driven and Fusion-based Methods to Generate Daily High-spatial-resolution Land Surface Temperatures[J].Remote Sensing of Environment,2019,224:259-274.
[17] WAN Z,DOZIER J.A Generalized Split-window Algorithm for Retrieving Land-surface Temperature from Space[J].IEEE Transactions on Geoscience and Remote Sensing,1996,34(4):892-905.
[18] REUTER H I,NELSON A,JARVIS A.An Evaluation of Void Filling Interpolation Methods for SRTM Data[J].International Journal of Geographic Information Science,2007,21(9):983-1008.
[19] MARIA B,MONIA M,EMAN H,et al.The First Comprehensive Accuracy Assessment of GlobeLand30 at a National Level:Methodology and Results[J].Remote Sensing,2015,7(4):4191-4212.
[20] HERSBACH H,BELL B,BERRISFORD P,et al.The ERA5 Global Reanalysis[J].Quarterly Journal of the Royal Meteorological Society,2020,146(730):1999-2049.
基本信息:
中图分类号:P407
引用信息:
[1]颜佳楠,陈虹,姚光林,等.基于XGBoost的LST空间降尺度方法[J].无线电工程,2021,51(12):1508-1516.
基金信息:
国家自然科学基金资助项目(41901308); 国家重点研究发展计划(2018YFB0504800)~~