[1]邢立亭,李 净*.基于遥感数据和随机森林算法的黄土高原地区气温模拟及时空变化[J].山地学报,2020,(6):873-880.[doi:10.16089/j.cnki.1008-2786.000563]
　XING Liting,LI Jing*.Temperature Simulation and Temporal Variation Based on Remote Sensing Data and Random Forest Algorithm: A Case Study in the Loess Plateau Region, China[J].Mountain Research,2020,(6):873-880.[doi:10.16089/j.cnki.1008-2786.000563]
点击复制

基于遥感数据和随机森林算法的黄土高原地区气温模拟及时空变化
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2020年第6期
页码:
873-880
栏目:
山地环境
出版日期:
2020-12-25

文章信息/Info

Title:
Temperature Simulation and Temporal Variation Based on Remote Sensing Data and Random Forest Algorithm: A Case Study in the Loess Plateau Region, China
文章编号:
1008-2786-(2020)6-873-08
作者:
邢立亭; 李 净*
西北师范大学 地理与环境科学学院,甘肃 兰州 730070
Author(s):
XING Liting;  LI Jing*
College of Geographical and Environmental Science, Northwest Normal University, Lanzhou 730070, China
关键词:
MODIS;  随机森林算法;  近地表气温;  黄土高原
Keywords:
MODIS;  Random forest algorithm;  Near surface temperature;  Loess Plateau
分类号:
P407.8
DOI:
10.16089/j.cnki.1008-2786.000563
文献标志码:
A
摘要:
气温是影响区域热环境的重要表征和引起气候变化的关键因素,依靠少量气象站点的内插或者外推获得的空间连续分布的气温无法准确表示大区域气温的空间变化特征。本文利用遥感数据结合随机森林算法模拟了2003—2016年黄土高原地区长时空序列的气温数据,并分析了11个输入变量的重要性,验证了随机森林模型的性能。结果表明:使用随机森林算法结合遥感数据模拟得到的近地表气温的平均绝对误差为0.91 ℃,均方根误差为1.06 ℃,结果精度较高。根据模拟出来的近地表气温分析了黄土高原地区2003—2016年气温的时空变化特征及趋势,发现2003—2016年黄土高原大部分区域气温整体上呈现缓慢上升的趋势。结果表明使用遥感数据结合随机森林算法的气温模拟在黄土高原地区具有很好的适用性,对研究黄土高原地区的气温演变规律及水热变化具有重要意义。
Abstract:
Air temperature is an integral representation of regional thermal environment and one of key factors that cause climate change. A continuous distribution of air temperature derived by spatial interpolation or extrapolation based on observations merely at several scattered meteorological stations cannot accurately characterize the spatial variation of air temperature over a large area. In this paper, an improved approach to model the variation of air temperature was exemplified by a case study in the Loess Plateau region, which used remote sensing data combined with random forest machine learning to analyze the monthly mean air temperature from 2003 to 2016 to obtain its continuous spatio-temporal distribution. The significances of 11 variables related to air temperature were analyzed and the performance of the random forest model was examined. Then these 11 verified variables and random forest model were used to simulate air temperature in the Loess Plateau from 2003 to 2016. The research found that the average absolute error of near-surface air temperature obtained by our proposed approach was 0.91 ℃, with a mean square error 1.06 ℃, exhibiting a higher accuracy; According to the simulation, in most areas of the Loess Plateau from 2003 to 2016, the near-surface temperature had presented a slow rising trend, which is consistent with past research. Conclusively, the air temperature simulation using remote sensing data combined with the random forest algorithm has good applicability in the Loess Plateau region, and is of significance to the study of the law of temperature evolution and water and heat changes in the Loess Plateau.

参考文献/References:

[1] LI Long, ZHA Yong. Estimating monthly average temperature by remote sensing in China[J]. Advances in Space Research, 2019, 63(8): 2345-2357.
[2] 邢立亭,李净,焦文慧.基于MODIS和随机森林的兰州市日最高气温和最低气温估算[J].干旱区研究,2020,37(3):689-695.[XING Liting, LI Jing, JIAO Wenhui. Estimation of daily maximum and minimum temperature of Lanzhou City based on MODIS and random forest[J]. Arid Zone Research, 2020, 37(3): 689-695]
[3] MAO K B, TANG H J, WANG X F, et al. Near-surface air temperature estimation from ASTER data based on neural network algorithm[J]. International Journal of Remote Sensing, 2008, 29(20): 6021-6028.
[4] PEDE T, MOUNTRAKIS G, SHAW S B. Improving corn yield prediction across the US Corn Belt by replacing air temperature with daily MODIS land surface temperature[J]. Agricultural and Forest Meteorology, 2019, 276-277:107615.
[5] 韩秀珍,李三妹,窦芳丽.气象卫星遥感地表温度推算近地表气温方法研究[J].气象学报,2012,70(5):1107-1118.[HAN Xiuzhen, LI Sanmei, DOU Fangli. Study of obtaining high resolution near-surface atmosphere temperature by using the land surface temperature from meteorological satellite data[J]. Acta Meteorologica Sinica, 2012, 70(5): 1107-1118]
[6] 祝善友,张桂欣.近地表气温遥感反演研究进展[J].地球科学进展,2011,26(7):724-730.[ZHU Shanyou, ZHANG Guixin. Progress in near surface air temperature retrieved by remote sensing technology[J]. Advances in Earth Science, 2011, 26(7): 724-730]
[7] 张丽文,黄敬峰,王秀珍.气温遥感估算方法研究综述[J].自然资源学报,2014,29(3):540-552.[ZHANG Liwen, HUANG Jingfeng, WANG Xiuzhen. A review on air temperature estimation by satellite thermal infrared remote sensing[J]. Journal of Natural Resources, 2014, 29(3): 540-552]
[8] DAVIS F A, TARPLEY J D. Estimation of Shelter temperatures from operational satellite sounder data[J]. Journal of Applied Meteorology, 2010, 22(3): 369-376.
[9] CRESSWELL M P. Estimating surface air temperatures, from Meteosat land surface temperatures, using an empirical solar zenith angle model[J]. International Journal of Remote Sensing, 1999, 20(6): 1125-1132.
[10] 李斌,王慧敏,秦明周,等.NDVI、NDMI与地表温度关系的对比研究[J].地理科学进展,2017,36(5):585-596.[LI Bin, WANG Huimin, QIN Mingzhou, et al. Comparative study on the correlations between NDVI, NDMI and LST[J]. Progress in Geography, 2017, 36(5): 585-596]
[11] 丁海勇,李往华.基于TVX方法的南京市城区时空格局与地表温度的研究[J].长江流域资源与环境,2018,27(4):735-744.[DING Haiyong, LI Wanghua. Analysis of land use land cover temporal-spatial distribution and land surface temperature in Nanjing City using TVX method[J]. Resources and Environment in the Yangtze Basin, 2018, 27(4): 735-744]
[12] STISEN S, SANDHOLT I, NØRGAARD A, et al. Estimation of diurnal air temperature using MSG SEVIRI data in West Africa[J]. Remote Sensing of Environment, 2007, 110(2): 262-274.
[13] PAPE R, LÖFFLER J. Modelling spatio-temporal near-surface temperature variation in high mountain landscapes[J]. Ecological Modelling, 2004, 178(3): 483-501.
[14] 白琳,徐永明,何苗,等.基于随机森林算法的近地表气温遥感反演研究[J].地球信息科学学报,2017,19(3):390-397.[BAI Lin, XU Yongming, HE Miao, et al. Remote sensing inversion of near surface air temperature based on random forest[J]. Journal of Geo-Information Science, 2017, 19(3): 390-397]
[15] YOO C, IM J, PARK S, et al. Estimation of daily maximum and minimum air temperatures in urban landscapes using MODIS time series satellite data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 137:149-162.
[16] FU Peng, WENG Qihao. Variability in annual temperature cycle in the urban areas of the United States as revealed by MODIS imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 146:65-73.
[17] 翟丹平,白红英,冯海鹏,等.基于气象数据和遥感影像的太白山气温直减率[J].山地学报,2016,34(4):496-503.[ZHAI Danping, BAI Hongying, FENG Haipeng, et al. Temperature lapse rates in the taibai mountain based on meteorological data and remote sensing image[J]. Journal of Mountain Research Science, 2016, 34(4): 496-503]
[18] BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[19] 周屹,冯兆祥,白熙卓,等.基于随机森林算法的数据分析软件设计[J].黑龙江工程学院学报,2017,31(3):38-41.[ZHOU Yi, FENG Zhaoxiang, BAI Xizhuo, et al. Design of data analysis software based on random forest algorithm[J]. Journal of Heilongjiang Institute of Technology, 2017, 31(3): 38-41]
[20] 刘剑,曹美燕,高治军,等.一种基于随机森林的太阳能辐射预测模型[J].控制工程,2017,24(12):2472-2477.[LIU Jian, CAO Meiyan, GAO Zhijun, et al. A solar radiation prediction model based on random forest[J]. Control Engineering of China, 2017, 24(12): 2472-2477]
[21] BREIMAN L. Bagging preditors[J]. Machine Learning, 1996, 24(2): 123-140.
[22] 方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.[FANG Kuangnan, WU Jianbin, ZHU Jianping, et al. A review of technologies on random forests[J]. Statistics & Information Forum, 2011, 26(3): 32-38]
[23] 梅静,王建,何亮,等.川西甘孜州1961—2015年气温和降水时空变化特征研究[J].山地学报,2019,37(2):161-172.[MEI Jing, WANG Jian, HE Liang, et al. Spatio-temporal variations of temperature and precipitation in Ganzi of Western Sichuan in China during 1961-2015[J]. Mountain Research, 2019, 37(2): 161-172]
[24] 张定全,王毅荣.中国黄土高原地区春季气温时空特征分析[J].高原气象,2005(6):898-904.[ZHANG Dingquan, WANG Yirong. Spatial and temporal characteristics of cir temperature in China Loess Plateau in spring [J]. Plateau Meteorology, 2005(6):898-904.]
[25] 顾朝军,穆兴民,高鹏,等.1961—2014年黄土高原地区降水和气温时间变化特征研究[J].干旱区资源与环境,2017,31(3):136-143.[GU Chaojun, MU Xingmin, GAO Peng, et al. Characteristics of temporal variation in precipitation and temperature in the Loess Plateau from 1961 to 2014[J]. Journal of Arid Land Resources and Environment, 2017, 31(3): 136-143]
[26] 晏利斌.1961—2014年黄土高原气温和降水变化趋势[J].地球环境学报,2015,6(5):276-282.[YAN Libin. Characteristics of temperature and precipitation on the Loess Plateau from 1961 to 2014[J]. Journal of Earth Environment, 2015, 6(5): 276-282]

相似文献/References:

[1]张华伟,童海刚,鲁安新,等.精河到伊宁公路沿线积雪及其影响[J].山地学报,2012,(01):48.
　ZHANG Huawei,TONG Haigang,LU Anxin,et al.Snow Cover along the Jinghe to Yining Highway and Its Impact[J].Mountain Research,2012,(6):48.
[2]延昊,张佳华.基于SSM/I被动微波数据的中国积雪深度遥感研究[J].山地学报,2008,(01):59.
[3]庄宇娇,贾 翔*,陈孟禹,等.提孜那甫河流域冰-草生态交错带MODZS动态特征[J].山地学报,2016,(06):780.[doi:10.16089/j.cnki.1008-2786.000186]
　ZHUANG Yujiao,JIA Xiang,CHEN Mengyu,et al.Dynamic Features of the Ice-Grass Ecotone in Tizinafu River Basin based on MODIS Data[J].Mountain Research,2016,(6):780.[doi:10.16089/j.cnki.1008-2786.000186]
[4]唐志光,王 建,王 欣,等.基于MODIS数据的青藏高原积雪日数提取与时空变化分析[J].山地学报,2017,(03):412.[doi:10.16089/j.cnki.1008-2786.000237]
　TANG Zhiguang,WANG Jian,WANG Xin,et al.Extraction and Spatiotemporal Analysis of Snow Covered Days over Tibetan Plateau Based on MODIS Data[J].Mountain Research,2017,(6):412.[doi:10.16089/j.cnki.1008-2786.000237]
[5]刘永垚,第宝锋*,詹 宇,等.基于随机森林模型的泥石流易发性评价--以汶川地震重灾区为例[J].山地学报,2018,(05):765.[doi:10.16089/j.cnki.1008-2786.000372]
　LIU Yongyao,DI Baofeng*,ZHAN Yu,et al.Debris Flows Susceptibility Assessment in Wenchuan Earthquake Areas Based on Random Forest Algorithm Model[J].Mountain Research,2018,(6):765.[doi:10.16089/j.cnki.1008-2786.000372]
[6]黄 萍,卢 远*,王丹媛,等.广西森林转型与森林扰动遥感监测研究[J].山地学报,2019,(01):118.[doi:10.16089/j.cnki.1008-2786.000405]
　HUANG Ping,LU Yuan*,WANG Danyuan,et al.Remote Sensing Monitoring of Forest Transition and Forest Disturbance in Guangxi, China[J].Mountain Research,2019,(6):118.[doi:10.16089/j.cnki.1008-2786.000405]
[7]拉 巴,拉 珍,拉巴卓玛*,等.2000-2018年那曲市植被NDVI变化及气候变化响应[J].山地学报,2019,(04):499.[doi:10.16089/j.cnki.1008-2786.000442]
　LA Ba,LA Zhen,LA Ba Droma*,et al.NDVI Change and Its Response to Climate Change in Nag Qu City during 2000-2018[J].Mountain Research,2019,(6):499.[doi:10.16089/j.cnki.1008-2786.000442]
[8]谭红梅,贺中华*,陈莉会,等.贵州省极端降雨特征及其影响因子[J].山地学报,2023,(5):748.[doi:10.16089/j.cnki.1008-2786.000784]
　TAN Hongmei,HE Zhonghua,*,et al.Characteristics of Extreme Rainfall and Its Influencing Factors in Guizhou Province, China[J].Mountain Research,2023,(6):748.[doi:10.16089/j.cnki.1008-2786.000784]

备注/Memo

备注/Memo:
收稿日期(Received date):2020-05-15; 改回日期(Accepted date):2020-11-09
基金项目(Foundation item):国家自然科学基金项目(41861013; 41761083; 41561016)。[National Natural Science Foundation of China(41861013; 41761083; 41561016)]
作者简介(Biography):邢立亭(1996-),男,山东济南人,硕士研究生,主要研究方向:定量遥感与气温模拟。[XING Liting(1996 -), male, born in Jinan, Shandong Province, M.Sc. candidate, research on quantitative remote sensing and temperature simulation] E-mail:15117290383@163.com
*通讯作者(Corresponding author):李净(1978-),女,甘肃会宁人,博士,主要研究方向:定量遥感与辐射模拟。[LI Jing(1978-), female, born in Huining, Gansu Province, Ph.D., engaged in quantitative remote sensing and radiation simulation] E-mail: li_jinger@nwnu.edu.cn
更新日期/Last Update: 2020-11-30