基于机器学习的青藏高原天然草地盖度时空变化特征研究

doi:10.11733/j.issn.1007-0435.2022.10.015

草地学报 ›› 2022, Vol. 30 ›› Issue (10): 2652-2662.DOI: 10.11733/j.issn.1007-0435.2022.10.015

• • 上一篇

基于机器学习的青藏高原天然草地盖度时空变化特征研究

孟新月, 葛静, 侯蒙京, 冯琦胜, 金哲人, 高金龙, 梁天刚

草地农业生态系统国家重点实验室, 兰州大学草地农业科技学院, 甘肃兰州 730020

收稿日期:2022-03-09 修回日期:2022-05-23 发布日期:2022-11-05
通讯作者: 梁天刚,E-mail:tgliang@lzu.edu.cn
作者简介:孟新月(1999-),女,满族,河北承德人,硕士研究生,主要从事草地遥感与地理信息系统研究,E-mail:mengxy20@lzu.edu.cn
基金资助:
国家重点研发计划(2019YFC0507701)；国家自然科学基金(31672484，41805086，41801191)；中国工程院咨询研究项目(2021-HZ-5，2020-XZ-29)；兰州大学中央高校基本科研业务费专项资金(lzujbky-2021-kb13)；财政部和农业农村部：国家现代农业产业技术体系；国家重点研发计划(2021YFD1300504);甘肃省科技计划重大项目(21ZD4FA020)共同资助

Spatio-temporal Variation of Natural Grassland Coverage on the Tibetan Plateau based on Machine Learning Algorithm

MENG Xin-yue, GE Jing, HOU Meng-jing, FENG Qi-sheng, JIN Zhe-ren, GAO Jin-long, LIANG Tian-gang

State Key Laboratory of Grassland Agro-ecosystems, College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou, Gansu Province 730020, China

Received:2022-03-09 Revised:2022-05-23 Published:2022-11-05

摘要/Abstract

摘要： 草地盖度是评价草地生长状况的重要指标，构建高精度的盖度估测模型是开展天然草地动态监测的关键。本文利用2003—2018年实测数据和地形、土壤等55个指标，建立了4种草地盖度遥感估测模型，通过比较得到研究区草地盖度遥感估测最优模型，并分析了2001—2019年研究区草地盖度时空动态变化。结果表明：由最小绝对压缩变量筛选方法选出10个有较高重要性的变量。其中，比值植被指数与草地植被盖度间的相关性优于其他单因素模型与草地植被盖度间的相关性。在3种机器学习模型中，随机森林优于人工神经网络与支持向量机模型，其R²和均方根误差分别为0.68和12.75%。机器学习方法构建的草地盖度模型优于单因素模型，其R²可提高0.09~0.16，RMSE降低1.52%~2.81%；2001—2019年，研究区草地盖度整体上呈现出自西向东、自北向南增加的趋势，呈增加趋势的面积占比为55.4%，呈减少趋势的面积占比为44.6%。

关键词: 草地盖度, 随机森林, MODIS, 变量筛选

Abstract: Grassland coverage is an important index to evaluate grassland growth status,and the establishment of high-precision coverage estimation model is the key to carry out dynamic monitoring of natural grassland. In this study,we established four remote sensing estimation models of grassland coverage based on the measured data from 2003 to 2018 and 55 indices including topography and soil. The optimal models were obtained by comparison,and the spatial-temporal dynamic changes of grassland coverage in the study area from 2001 to 2019 were analyzed. The results showed as follows:Ten variables with high importance were selected by minimum absolute compression variable screening method. Among them,the correlation between Ratio Vegetation Index and grassland vegetation coverage is better than that between other single-factor models and grassland vegetation coverage. Among the three machine learning models,random forest is superior to artificial neural network and support vector machine,with R² and root mean square errors of 0.68 and 12.75%,respectively. The grassland coverage model constructed by machine learning was superior to the single-factor model,with R² increased by 0.09~0.16 and RMSE decreased by 1.52%~2.81%. From 2001 to 2019,grassland coverage increased from west to east and from north to south in the study area,with 55.4% of the areas showing an increasing trend and 44.6% of the areas showing a decreasing trend.

Key words: Grassland coverage, Random forest, Moderate-resolution Imaging Spectroradiometer, Variable selection

中图分类号:

S812

孟新月, 葛静, 侯蒙京, 冯琦胜, 金哲人, 高金龙, 梁天刚. 基于机器学习的青藏高原天然草地盖度时空变化特征研究[J]. 草地学报, 2022, 30(10): 2652-2662.

MENG Xin-yue, GE Jing, HOU Meng-jing, FENG Qi-sheng, JIN Zhe-ren, GAO Jin-long, LIANG Tian-gang. Spatio-temporal Variation of Natural Grassland Coverage on the Tibetan Plateau based on Machine Learning Algorithm[J]. Acta Agrestia Sinica, 2022, 30(10): 2652-2662.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://manu40.magtech.com.cn/Jweb_cdxb/CN/10.11733/j.issn.1007-0435.2022.10.015

https://manu40.magtech.com.cn/Jweb_cdxb/CN/Y2022/V30/I10/2652

参考文献

[1] 岳胜如,李瑞平,徐冰.内蒙古中部植被覆盖度监测及气象驱动力分析[J].湖北农业科学,2015,54(7):1574-1577
[2] 陈建军,宜树华,任世龙,等.疏勒河上游高寒草地植被盖度反演及精度评价[J].草业科学,2014,31(1):56-65
[3] 陈云浩,李晓兵,史培军,等.北京海淀区植被覆盖的遥感动态研究[J].植物生态学报,2001(5):588-593
[4] 温庆可,张增祥,刘斌,等.草地覆盖度测算方法研究进展[J].草业科学,2009,26(12):30-36
[5] ZHOU Q,DONG M,PILESJO P. On the ground estimation of vegetation cover in australian rangelands[J]. International Journal of Remote Sensing,1998,19(9):1815-1820
[6] 何国兴,柳小妮,张德罡,等.甘肃省高寒草甸植被覆盖度反演及其时空变化研究[J].草地学报,2021,29(3):593-602
[7] 殷建鹏,高金龙,冯琦胜,等.黄河源区高寒草甸群落高度遥感模拟与评价[J].草业科学,2018,35(4):737-748
[8] 吴见,彭建,谷双喜.黄山市近30a植被盖度时空变化遥感分析[J].黑龙江工程学院学报,2020,34(5):6-10
[9] 赵国忱,李招,韩自祥.基于像元二分模型的北票市植被覆盖度动态变化研究[J].测绘与空间地理信息,2019,42(7):5-7
[10] 宋清洁,崔霞,张瑶瑶,等.基于小型无人机与MODIS数据的草地植被覆盖度研究——以甘南州为例[J].草业科学,2017,34(1):40-50
[11] 臧淑英,那晓东,冯仲科.基于植被指数的大庆地区草地退化因子遥感定量反演模型的研制[J].北京林业大学学报,2008,30(S1):98-104
[12] ZHAO F,XU B,YANG X C,et al. Remote sensing estimates of grassland aboveground biomass based on MODIS net primary productivity (NPP):a case study in the Xilingol grassland of North China[J]. Remote Sensing,2014,6(6):5368-5386
[13] MORAIS T G,TEIXEIRA R F M,FIGUEIREDO M,et al. The use of machine learning methods to estimate aboveground biomass of grasslands:A review[J]. Ecological Indicators,2021(130):108081
[14] WU J,LI Y,LI N,et al. Development of an asset value map for disaster risk assessment in China by spatial disaggregation using ancillary remote sensing data[J]. Risk Analysis,2018,38(1):17-30
[15] 陈黔,李晓松,修晓敏,等.基于Google Earth Engine与机器学习的大尺度30 m分辨率沙地灌木覆盖度估算[J].生态学报,2019,39(11):4056-4069
[16] GE J,MENG B,LIANG T G,et al. Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River,China[J]. Remote Sensing of Environment,2018(218):162-173
[17] 邵伟,蔡晓布.西藏高原草地退化及其成因分析[J].中国水土保持科学,2008(1):112-116
[18] 高清竹,李玉娥,林而达,等.藏北地区草地退化的时空分布特征[J].地理学报,2005(6):87-95
[19] 陆晴,吴绍洪,赵东升.1982-2013年青藏高原高寒草地覆盖变化及与气候之间的关系[J].地理科学,2017,37(2):292-300
[20] 曹建军,王雪艳,李梦天,等.青藏高原草地管理方式对土壤养分及其空间分布的影响[J].应用生态学报,2018,29(6):1839-1845
[21] 曹旭娟,干珠扎布,胡国铮,等.基于NDVI3 g数据反演的青藏高原草地退化特征[J].中国农业气象,2019,40(2):86-95
[22] 李重阳,樊文涛,李国梅,等.基于NDVI的2000-2016年青藏高原牧户草场覆盖度变化驱动力分析[J].草业学报,2019,28(10):25-32
[23] 鲁春霞,谢高地,成升魁,等.中国草地资源利用:生产功能与生态功能的冲突与协调[J].自然资源学报,2009,24(10):1685-1696
[24] 兰翔宇,叶冲冲,王毅,等.1995-2014年青藏高原水源涵养功能时空演变特征及其驱动力分析[J].草地学报,2021,29(1):80-92
[25] 葛静,孟宝平,杨淑霞,等.基于UAV技术和MODIS遥感数据的高寒草地盖度动态变化监测研究——以黄河源东部地区为例[J].草业学报,2017,26(3):1-12
[26] 刘洁,孟宝平,葛静,等.基于CASA模型和MODIS数据的甘南草地NPP时空动态变化研究[J].草业学报,2019,28(6):19-32
[27] 梁天刚,崔霞,冯琦胜,等.2001-2008年甘南牧区草地地上生物量与载畜量遥感动态监测[J].草业学报,2009,18(6):12-22
[28] 冉红,黎武,杨晓,等.重庆市地形起伏度的提取及其在水土流失评价中的应用[J].安徽农学通报,2017,23(9):92-94
[29] EPPRECHT C,GUEGAN D,VEIGA Á,et al. Variable selection and forecasting via automated methods for linear models:LASSO/adaLASSO and Autometrics[J]. Communications in Statistics-Simulation and Computation,2021,50(1):103-122
[30] YU S,GONG S. A study on grain price prediction based on Lasso and support vector machine[J]. Journal of Hunan University (Social Sciences),2016,30(1):71-75
[31] BENOIT D F,VAN DEN POEL D. Benefits of quantile regression for the analysis of customer lifetime value in a contractual setting:An application in financial services[J]. Expert Systems with Applications,2009,36(7):10475-10484
[32] MIN C Y. Multi-criteria ABC analysis using artificial-intelligence-based classification techniques[J]. Expert Systems with Applications,2011,38(4):3416-3421
[33] XU R,LUO F. Risk prediction and early warning for air traffic controllers'unsafe acts using association rule mining and random forest[J]. Safety Science,2021(135):105125
[34] 熊纬,施勤.神经网络原理用于控制机动伺服平台[J].现代雷达,2011,33(3):63-66
[35] RINALDI M,LOSAVIO N,FLAGELLA Z. Evaluation and application of the OILCROP-SUN model for sunflower in southern Italy[J]. Agricultural Systems,2003,78(1):17-30
[36] LOAGUE K,GREEN R E. Statistical and graphical methods for evaluating solute transport models:overview and application[J]. Journal of contaminant hydrology,1991,7(1-2):51-73
[37] OLDEN J D,JACKSON D A. Torturing data for the sake of generality:how valid are our regression models?[J]. Ecoscience,2000,7(4):501-510
[38] PAN J,ZHU Y,CAO W,et al. Predicting the protein content of grain in winter wheat with meteorological and genotypic factors[J]. Plant Production Science,2006,9(3):323-333
[39] JAMIESON P D,PORTER J R,WILSON D R. A test of computer simulation model ARCWHEAT1 on wheat crops grown in New Zealand[J]. Field Crops Research,1991,27(4):337-350
[40] FENSHOLT R,RASMUSSEN K,NIELSEN T T,et al. Evaluation of earth observation based long term vegetation trends-Intercomparing NDVI time series trend analysis consistency of Sahel from AVHRR GIMMS,Terra MODIS and SPOT VGT data[J]. Remote Sensing of Environment,2009,113(9):1886-1898
[41] STOW D A,HOPE A,MCGUIRE D,et al. Remote sensing of vegetation and land-cover change in Arctic Tundra Ecosystems[J]. Remote Sensing of Environment,2004,89(3):281-308
[42] SONG Y,MA M,VEROUSTRAETE F. Comparison and conversion of AVHRR GIMMS and SPOT VEGETATION NDVI data in China[J]. International Journal of Remote Sensing,2010,31(9):2377-2392
[43] BREIMAN L. Random forests[J]. Machine Learning,2001,45(1):5-32
[44] CUTLER D R,EDWARDS T C,BEARD K H,et al. Random forests for classification in ecology[J]. Ecology,2007,88(11):2783-2792
[45] MEYER H,LEHNERT L W,WANG Y,et al. From local spectral measurements to maps of vegetation cover and biomass on the Qinghai-Tibet-Plateau:Do we need hyperspectral information?[J]. International Journal of Applied Earth Observation and Geoinformation.2017(55):21-31
[46] 柯灵红,王正兴,宋春桥,等.青藏高原东北部MODIS地表温度重建及其与气温对比分析[J].高原气象,2011,30(2):277-287
[47] 唐志光,马金辉,李成六,等.三江源自然保护区植被覆盖度遥感估算[J].兰州大学学报(自然科学版),2010,46(2):11-16
[48] 于伯华,吕昌河,吕婷婷,等.青藏高原植被覆盖变化的地域分异特征[J].地理科学进展,2009,28(3):391-397
[49] 丁明军,张镱锂,刘林山,等.1982-2009年青藏高原草地覆盖度时空变化特征[J].自然资源学报,2010,25(12):2114-2122
[50] 马琳雅,崔霞,冯琦胜,等.2001-2011年甘南草地植被覆盖度动态变化分析[J].草业学报,2014,23(4):1-9
[51] 韩枫.草场生态保护对牧民生活的影响研究[D].北京:中国农业科学院,2016:18-25
[52] 邹长慧,谢晓尧,周忠发.无人机低空航拍遥感系统在贵州高原山区的应用前景探讨[J].贵州师范大学学报(自然科学版),2011,29(2):24-28
[53] 高珍,邓甲昊,孙骥,等.微型无人机图像无线传输系统方案与关键技术[J].北京理工大学学报,2008,28(12):1078-1082

基于机器学习的青藏高原天然草地盖度时空变化特征研究

Spatio-temporal Variation of Natural Grassland Coverage on the Tibetan Plateau based on Machine Learning Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	文铜, 柳小妮, 纪童, 杨冬阳, 乔欢欢, 姜佳昌, 潘冬荣. 基于植被指数的三江源高寒草地植物分类与识别方法研究[J]. 草地学报, 2022, 30(7): 1811-1818.
[2]	高宏元, 侯蒙京, 葛静, 包旭莹, 李元春, 刘洁, 冯琦胜, 梁天刚, 贺金生, 钱大文. 基于随机森林的高寒草地地上生物量高光谱估算[J]. 草地学报, 2021, 29(8): 1757-1768.
[3]	郭超凡, 陈泽威, 张志高. 基于最优模型选择的牧草地上生物量遥感估算研究[J]. 草地学报, 2021, 29(5): 946-955.
[4]	王秀梅, 董建军. 基于广义线性模型估算内蒙古荒漠草原及典型草原地上生物量变化[J]. 草地学报, 2020, 28(6): 1711-1718.
[5]	闫俊杰, 张静, 雷雨, 沙吾丽·达吾提拜, 吕光辉. 2000-2016年新疆伊犁河谷草地NDVI变化趋势分析[J]. 草地学报, 2018, 26(4): 859-868.
[6]	冯文兰, 钟昊哲, 王永前, 龚雪梅. 2001—2013年若尔盖地区植被退化的时空格局分析[J]. 草地学报, 2015, 23(2): 239-245.
[7]	周鑫, 盛建东, 张文太, 武红旗, 王新军. 基于MODIS数据的伊犁地区草地地上生物量反演[J]. 草地学报, 2015, 23(1): 27-33.
[8]	付刚, 沈振西, 张宪洲, 石培礼, 何永涛, 武建双, 周宇庭. 利用MODIS影像和气候数据模拟藏北高寒草甸的土壤呼吸[J]. 草地学报, 2011, 19(3): 400-405.
[9]	高娃. 草原返青期遥感监测分析[J]. , 2009, 17(2): 227-233.