基于Catboost的AMSR-2半经验地表温度降尺度

doi:10.13866/j.azr.2021.06.15

干旱区研究 ›› 2021, Vol. 38 ›› Issue (6): 1637-1649.doi: 10.13866/j.azr.2021.06.15

基于Catboost的AMSR-2半经验地表温度降尺度

李永康^1,²(),王新军¹(),马燕飞³,胡贵锋¹,桂海月¹,张冠宏¹

1.新疆农业大学草业与环境科学学院,新疆土壤与植物生态过程实验室,新疆乌鲁木齐 830052
2.中国科学院空天信息创新研究院,数字地球重点实验室,北京 100094
3.邯郸学院经济管理学院地理系,河北邯郸 056005

收稿日期:2020-12-10 修回日期:2021-05-05 出版日期:2021-11-15 发布日期:2021-11-29
通讯作者: 王新军
作者简介:李永康（1995-）,男,硕士研究生,主要从事陆面数据同化研究. E-mail: yongkang_xau@163.com
基金资助:
国家自然科学基金项目(41761085);国家自然科学基金项目(41301205);自治区研究生科研创新项目(lXJ2020G152)

Downscaling land surface temperature through AMSR-2 passive microwave observations by Catboost semiempirical algorithms

LI Yongkang^1,²(),WANG Xinjun¹(),MA Yanfei³,HU Guifeng¹,GUI Haiyue¹,ZHANG Guanhong¹

1. College of Grassland and Environment Sciences of Xinjiang Agricultural University, Xinjiang Key Laboratory of Soil and Plant Ecological Processes, Urumqi 830052, Xinjiang, China
2. Key Laboratory of Digital Earth Science,Aerospace Information Research Institute, Chinese Academy of Sciences,Beijing 100094, China
3. Department of Geography of Handan University, Handan 056005, Hebei, China

Received:2020-12-10 Revised:2021-05-05 Online:2021-11-15 Published:2021-11-29
Contact: Xinjun WANG

摘要/Abstract

摘要：

以古尔班通古特沙漠为研究对象,采用2019年AMSR-2的4通道被动微波亮温及MODIS植被指数,探索Catboost算法对被动微波地表温度空间降尺度的可行性,填补古尔班通古特沙漠MYD11A1的缺失像元,为获取全天候日、夜间多层土壤温度提供数据参考。结果表明：（1）古尔班通古特沙漠日、夜间用于降尺度研究的特征向量（23.8 GHz V、36.5 GHz V、18.7 GHz H、89 GHz V、36.5-23.8 GHz V、36.5 V-18.7 GHz H、EVI、NDVI）与地表温度的相关性空间分异特征明显,显示沙漠相关性高,绿洲相关性低,且日间分异性更强;而盐矿覆盖会降低微波与地表温度相关性。（2） Catboost 4通道模型建立的被动微波亮温与地表温度间映射关系表现出鲁棒性。降尺度结果精度较高,日夜间R²分别为0.977、0.980,RMSE分别为3.69 K、2.38 K,MAE分别为2.71 K、1.70 K。（3）单通道相关性统计结果与重要性分析结果存在差异,表明特征因子相关性统计结果不能直接作为Catboost被动微波反演地表温度特征选择依据。（4）降尺度结果与站点6层土壤温度均呈极显著正相关,并随着深度的增加相关系数r总体呈下降趋势,RMSE呈增加趋势。

关键词: 地表温度, AMSR-2, Catboost, 降尺度, 古尔班通古特沙漠

Abstract:

This study aimed to fill in the missing pixels of MYD11A1 in the Gurbantunggut Desert and provide a theoretical basis for obtaining all-weather and multilayer soil temperatures during daytime and nighttime. We explored the feasibility of the CatBoost algorithm for the spatial downscaling of passive microwave surface temperature by using the four-channel passive microwave brightness temperature and MODIS vegetation index of the 2019 AMSR-2. Results show that (1) the spatial differentiation between feature vectors and surface temperature is evident during daytime and nighttime in the Gurbantunggut Desert. It indicates high desert correlation, low oasis correlation, and strong daytime differentiation. The salt mine coverage reduces the correlation between passive microwave brightness temperature and surface temperature. (2) The mapping relation between the passive microwave brightness temperature and surface temperature from the four-channel CatBoost model is robust. The accuracy of the downscaled results is high, with daytime-nighttime R² of 0.977 and 0.980, RMSE of 3.69 and 2.38 K, and MAE of 2.71 K and 1.70 K, respectively. (3) Single-channel correlation and importance analysis results are different, suggesting that feature correlation results cannot be directly used as a basis for selecting surface temperature features with the CatBoost passive microwave inversion of LST. (4) Downscaling LST is significantly and positively correlated with the soil temperature in six layers from the Fukang site. The correlation coefficient decreases, and RMSE increases as depth increases.

Key words: land surface temperature, AMSR-2, Catboost, downscale, Gurbantunggut Desert

李永康,王新军,马燕飞,胡贵锋,桂海月,张冠宏. 基于Catboost的AMSR-2半经验地表温度降尺度[J]. 干旱区研究, 2021, 38(6): 1637-1649.

LI Yongkang,WANG Xinjun,MA Yanfei,HU Guifeng,GUI Haiyue,ZHANG Guanhong. Downscaling land surface temperature through AMSR-2 passive microwave observations by Catboost semiempirical algorithms[J]. Arid Zone Research, 2021, 38(6): 1637-1649.

图/表 10

图1

表1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 41

[1]	Li Z L, Tang B H, Wu H, et al. Satellite-derived land surface temperature: Current status and perspectives[J]. Remote Sensing of Environment, 2013, 131:14-37. doi: 10.1016/j.rse.2012.12.008
[2]	Anderson M, Norman J, Kustas W, et al. A thermal-based remote sensing technique for routine mapping of land-surface carbon, water and energy fluxes from field to regional scales[J]. Remote Sensing of Environment, 2008, 112(12):4227-4241. doi: 10.1016/j.rse.2008.07.009
[3]	Kalma J D, McVicar T R, McCabe M F. Estimating land surface evaporation: A review of methods using remotely sensed surface temperature data[J]. Surveys in Geophysics, 2008, 29(4):421-469. doi: 10.1007/s10712-008-9037-z
[4]	Wang K, Li Z, Cribb M. Estimation of evaporative fraction from a combination of day and night land surface temperatures and NDVI: A new method to determine the Priestley-Taylor parameter[J]. Remote Sensing of Environment, 2006, 102(3):293-305. doi: 10.1016/j.rse.2006.02.007
[5]	Faqe I G. Urban Land Use land cover changes and their effect on land surface temperature: Case study using dohuk city in the Kurdistan Region of Iraq[J]. Climate, 2017, 5(1):13-31. doi: 10.3390/cli5010013
[6]	Wan Z, Wang P, Li X. Using MODIS land surface temperature and normalized difference vegetation index products for monitoring drought in the southern Great Plains, USA[J]. International Journal of Remote Sensing, 2010, 25(1):61-72. doi: 10.1080/0143116031000115328
[7]	Hain C R, Anderson M C. Estimating morning change in land surface temperature from MODIS day/night observations: applications for surface energy balance modeling[J]. Geophysical Research Letters, 2017, 44(19):9723-9733. doi: 10.1002/grl.v44.19
[8]	Neteler M. Estimating daily land surface temperatures in mountainous environments by reconstructed MODIS LST data[J]. Remote Sensing, 2010, 2(1):333-351. doi: 10.3390/rs1020333
[9]	Wang F, Qin Z, Song C, et al. An improved mono-window algorithm for land surface temperature retrieval from Landsat 8 thermal infrared sensor data[J]. Remote Sensing, 2015, 7(4):4268-4289. doi: 10.3390/rs70404268
[10]	Duan S B, Li Z L, Wang C, et al. Land-surface temperature retrieval from Landsat 8 single-channel thermal infrared data in combination with NCEP reanalysis data and ASTER GED product[J]. International Journal of Remote Sensing, 2018, 40(5-6):1763-1778. doi: 10.1080/01431161.2018.1460513
[11]	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 and Remote Sensing, 2008, 46(1):200-208. doi: 10.1109/TGRS.2007.907333
[12]	何文英, 陈洪滨, 李军. 陆面微波比辐射率的卫星观测研究进展[J]. 地球物理学报, 2020, 63(10):3573-3584.
	[ He Wenying, Chen Hongbin, Li Jun. Development of land surface microwave emissivity retrieval using satellite observations[J]. Chinese Journal of Geophysics, 2020, 63(10):3573-3584. ]
[13]	钱博, 陆其峰, 杨素英, 等. 卫星遥感微波地表发射率研究综述[J]. 地球物理学进展, 2016, 31(3):960-964.
	[ Qian Bo, Lu Qifeng, Yang Suying, et al. Review on microwave land surface emissivity by satellite remote sensing[J]. Progress in Geophysics, 2016, 31(3):960-964. ]
[14]	汪子豪, 秦其明, 孙元亨, 等. 基于BP神经网络的地表温度空间降尺度方法[J]. 遥感技术与应用, 2018, 33(5):793-802.
	[ Wang Zihao, Qin Qiming, Sun Yuanheng, et al. Downscaling of remotely sensed land surface temperature with the bp neural network[J]. Remote Sensing Technology and Application, 2018, 33(5):793-802. ]
[15]	McFarland M J, Miller R L, Neale C M U. Land surface temperature derived from the SSM/I passive microwave brightness temperatures[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(5):839-845. doi: 10.1109/36.58971
[16]	Fily M. A simple retrieval method for land surface temperature and fraction of water surface determination from satellite microwave brightness temperatures in sub-arctic areas[J]. Remote Sensing of Environment, 2003, 85(3):328-338. doi: 10.1016/S0034-4257(03)00011-7
[17]	Gao H, Fu R, Dickinson R E, et al. A practical method for retrieving land surface temperature from AMSR-E over the Amazon Forest[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(1):193-199. doi: 10.1109/TGRS.2007.906478
[18]	Njoku E G, Li L. Retrieval of land surface parameters using passive microwave measurements at 6-18 GHz[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(1):79-93. doi: 10.1109/36.739125
[19]	Mao K, Shi J, Li Z, et al. A physics-based statistical algorithm for retrieving land surface temperature from AMSR-E passive microwave data[J]. Science in China Series D: Earth Sciences, 2007, 50(7):1115-1120.
[20]	毛克彪, 王道龙, 李滋睿, 等. 利用AMSR-E被动微波数据反演地表温度的神经网络算法[J]. 高技术通讯, 2009, 19(11):1195-1200.
	[ Mao Kebiao, Wang Daolong, Li Zirui, et al. A neural network method for retrieving land-surface temperature from AMSR-E data[J]. Chinese High Technology Letters, 2009, 19(11):1195-1200. ]
[21]	Sun D, Li Y, Zhan X, et al. Land surface temperature derivation under all sky conditions through integrating AMSR-E/AMSR-2 and MODIS/GOES observations[J]. Remote Sensing, 2019, 11(14):1704. doi: 10.3390/rs11141704
[22]	Tan J, Esmaeel N, Mao K, et al. Deep learning convolutional neural network for the retrieval of land surface temperature from AMSR2 data in China[J]. Sensors, 2019, 19(1):2987-3007. doi: 10.3390/s19132987
[23]	Huang G, Wu L, Ma X, et al. Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions[J]. Journal of Hydrology, 2019, 574:1029-1041. doi: 10.1016/j.jhydrol.2019.04.085
[24]	Zhang Y, Zhao Z, Zheng J. CatBoost: A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China[J]. Journal of Hydrology, 2020, 588(125):87-99.
[25]	姜琦刚, 杨秀艳, 杨长保, 等. 基于CatBoost算法的面向对象土地利用分类[J]. 吉林大学学报(信息科学版), 2020, 38(2):185-191.
	[ Jiang Qigang, Yang Xiuyan, Yang Changbao, et al. Object-oriented land use classification based on CatBoost algorithm[J]. Journal of Jilin University(Information Science Edition), 2020, 38(2):185-191. ]
[26]	王新军, 赵成义, 杨瑞红, 等. 古尔班通古特沙漠南缘荒漠化过程演变的景观格局特征分析[J]. 干旱区地理, 2015, 38(6):1213-1225.
	[ Wang Xinjun, Zhao Chengyi, Yang Ruihong, et al. Landscape pattern characteristics of desertification evolution in southern Gurbantunggut Desert[J]. Arid Land Geography, 2015, 38(6):1213-1225. ]
[27]	Mamtimin A, Wang Y, Sayit H, et al. Seasonal variations of the near-surface atmospheric boundary layer structure in China’s Gurbantünggüt Desert[J]. Advances in Meteorology, 2020: 6137237.
[28]	段呈, 吴玲, 王绍明, 等. 近30年古尔班通古特沙漠短命植物的时空格局[J]. 生态学报, 2017, 37(8):2642-2652.
	[ Duan Cheng, Wu Ling, Wang Shaoming, et al. Analysis of spatio-temporal patterns of ephemeral plants in the Gurbantünggüt Desert over the last 30 years[J]. Acta Ecologica Sinica, 2017, 37(8):2642-2652. ]
[29]	陈林, 王式功, 王莉莉. 新疆阜康地区秋季大气NO_x和O₃变化特征及影响要素[J]. 干旱气象, 2012, 30(3):345-352.
	[ Chen Lin, Wang Shigong, Wang Lili. Variation characteristics and influencing factors of NO_x and Ozone in autumn in Fukang Region of Xinjiang[J]. Journal of Arid Meteorology, 2012, 30(3):345-352. ]
[30]	范永东. 模型选择中的交叉验证方法综述[D]. 太原: 山西大学, 2013.
	[ Fan Yongdong. A Summary of Cross-Validation in Model Selection[D]. Taiyuan: Shanxi University, 2013. ]
[31]	郝静, 孙成, 郭兴宇, 等. 京津冀内陆平原区PM_2.5浓度时空变化定量模拟[J]. 环境科学, 2018, 39(4):1455-1465.
	[ Hao Jing, Sun Cheng, Guo Xingyu, et al. Simulation of the spatio-temporally resolved PM_2.5 aerosol mass concentration over the inland plain of the Beijing-Tianjin-Hebei region[J]. Environmental Science, 2018, 39(4):1455-1465. ]
[32]	金旭峰, 吴莹, 钱博. 基于AMSR2数据的青藏高原地表温度反演[J]. 地球物理学进展, 2020, 35(4):1269-1275.
	[ Jin Xufeng, Wu Ying, Qian Bo. Retrieval of land surface temperature from AMSR2 data over the Qinghai-Tibetan Plateau[J]. Progress in Geophysics, 2020, 35(4):1269-1275. ]
[33]	Bhagat V S. Space-borne passive microwave remote sensing of soil moisture: A review[J]. Recent Progress in Space Technology, 2015, 4(2):119-150.
[34]	Prokhorenkova L, Gusev G, Vorobev A, et al. CatBoost: Unbiased boosting with categorical features[J]. Advances in Neural Signal Processing, 2018: 6638-6648.
[35]	Zhang K, Schölkopf B, Muandet K, et al. Domain adaptation under target and conditional shift[C]// 30th International Conference on Machine Learning, ICML, 2013: 1856-1864.
[36]	Colliander A, Jackson T J, Bindlish R, et al. Validation of SMAP surface soil moisture products with core validation sites[J]. Remote Sensing of Environment, 2017, 191:215-231. doi: 10.1016/j.rse.2017.01.021
[37]	陶本藻, 邱卫宁, 张书毕, 等. 误差理论与测量平差[M]. 武汉: 武汉大学出版社, 2012.
	[ Tao Benzao, Qiu Weining, Zhang Shubi, et al. Error Theory and Measurement Adjustment[M]. Wuhan: Wuhan University Press, 2012. ]
[38]	毛克彪, 胡德勇, 黄健熙, 等. 针对被动微波AMSR-E数据的土壤水分反演算法[J]. 高技术通讯, 2010, 20(6):651-659.
	[ Mao Kebiao, Hu Deyong, Huang Jianxi, et al. A algorithm for retrieving soil moisture from AMSR-E passive microwave data[J]. Chinese High Technology Letters, 2010, 20(6):651-659. ]
[39]	Wang W, Liang S, Meyers T. Validating MODIS land surface temperature products using long-term nighttime ground measurements[J]. Remote Sensing of Environment, 2008, 112(3):623-635. doi: 10.1016/j.rse.2007.05.024
[40]	于文凭, 马明国. MODIS地表温度产品的验证研究——以黑河流域为例[J]. 遥感技术与应用, 2011, 26(6):705-712.
	[ Yu Wenping, Ma Mingguo. Validation of the MODIS land surface temperature products: A case study of the Heihe River basin[J]. Remote Sensing Technology and Application, 2011, 26(6):705-712. ]
[41]	Huang R, Huang J-x, Zhang C, et al. Soil temperature estimation at different depths, using remotely-sensed data[J]. Journal of Integrative Agriculture, 2020, 19(1):277-290. doi: 10.1016/S2095-3119(19)62657-2

AMSR-2被动微波亮温数据			MODIS数据
中心频率/GHz	极化方式	空间分辨率/km	数据类型	空间分辨率/km	数据集
18.7	V/H	10	MYD 11A1	1	LST_Day_1 km QC_Day
23.8	V/H	10	MYD 11A1	1	LST_Day_1 km QC_Day
36.5	V/H	10	MYD 13A2	1	1 km_16_days_EVI 1 km_16_days_NDVI
89	V/H	5	MYD 13A2	1	1 km_16_days_EVI 1 km_16_days_NDVI

基于Catboost的AMSR-2半经验地表温度降尺度

Downscaling land surface temperature through AMSR-2 passive microwave observations by Catboost semiempirical algorithms

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 41

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	李永广, 苑广辉. 青海湖流域不同下垫面类型对地表温度的生物物理影响[J]. 干旱区研究, 2024, 41(1): 24-35.
[2]	许毓哲, 林涛, 李君. 替代稳态下阜康北部荒漠生态弹性的时空格局[J]. 干旱区研究, 2023, 40(5): 808-817.
[3]	薛智暄, 张丽, 王新军, 李永康, 张冠宏, 李沛尧. 古尔班通古特沙漠SMAP土壤水分产品降尺度分析[J]. 干旱区研究, 2023, 40(4): 583-593.
[4]	李炎坤,高黎明,张乐乐,吴雪晴,刘轩辰,祁闻. 青海湖流域及周边区域TRMM 3B43降水数据降尺度方法对比分析[J]. 干旱区研究, 2022, 39(6): 1706-1716.
[5]	梁洪武,阿里木江·卡斯木,赵禾苗,赵永玉. 天山北坡城市群地表温度时空差异及贡献度分析[J]. 干旱区研究, 2022, 39(2): 388-399.
[6]	庄伟伟,侯宝林. 古尔班通古特沙漠短命植物的氮素吸收策略[J]. 干旱区研究, 2021, 38(5): 1393-1400.
[7]	李彬,武志芳,陶冶,周晓兵,张丙昌. 古尔班通古特沙漠不同类型生物结皮对草本植物多样性影响[J]. 干旱区研究, 2021, 38(2): 438-449.
[8]	赵美亮,曹广超,曹生奎,刘富刚,袁杰,张卓,刁二龙,付建新. 1980—2017年青海省地表温度时空变化特征[J]. 干旱区研究, 2021, 38(1): 178-187.
[9]	岳跃蒙, 李晨华, 徐柱, 唐立松. 古尔班通古特沙漠降雨过程中梭梭与白梭梭冠层养分的变化特征[J]. 干旱区研究, 2020, 37(5): 1293-1300.
[10]	李浙华, 李生宇, 李丙文, 范敬龙, 蒋进, 李亚萍, 宋春武. 不同植被覆盖度沙垄土壤化学性质的空间分异[J]. 干旱区研究, 2020, 37(1): 160-167.
[11]	杨怡, 吴世新, 庄庆威, 牛雅萱. 2000—2018年古尔班通古特沙漠EVI时空变化特征[J]. 干旱区研究, 2019, 36(6): 1512-1520.
[12]	李晓菲, 徐长春, 李路, 宋佳, 张喜成. 21世纪开都-孔雀河流域未来气候变化情景预估[J]. 干旱区研究, 2019, 36(3): 556-566.
[13]	范连连, 李耀明, Nataliia Terekhina, 马学喜, 马杰. 冷荒漠草本植物数量特征对不同水分输入和气象因子的响应 [J]. 干旱区研究, 2019, 36(1): 139-146.
[14]	周朝彬,王梦瑶,龚伟. 梭梭射线组织特征与非结构性碳水化合物含量的关系[J]. 干旱区研究, 2018, 35(5): 1105-1110.
[15]	吴楠，张静，王玥，殷进飞，张元明. 积雪和丛枝菌根真菌网络对尖喙牻牛儿苗幼苗生长的影响[J]. 干旱区研究, 2018, 35(3): 624-632.