基于最优模型选择的牧草地上生物量遥感估算研究

doi:10.11733/j.issn.1007-0435.2021.05.011

草地学报 ›› 2021, Vol. 29 ›› Issue (5): 946-955.DOI: 10.11733/j.issn.1007-0435.2021.05.011

基于最优模型选择的牧草地上生物量遥感估算研究

郭超凡, 陈泽威, 张志高

安阳师范学院资源环境与旅游学院, 河南安阳 455000

收稿日期:2020-10-29 修回日期:2021-01-20 出版日期:2021-05-15 发布日期:2021-06-02
通讯作者: 郭超凡,E-mail:guochao881016@163.com
作者简介:郭超凡(1988-)，男，汉族，山西吕梁人，博士，讲师，主要从事植被定量遥感研究，E-mail：guochao881016@163.com
基金资助:
国家自然科学基金项目（41602366）；河南省高等学校重点科研项目（21A170004）；安阳市科技计划项目（2021C01SF021）；大学生创新创业训练计划项目（X2020104790155）共同资助

Research on Remote Sensing Estimation of Forage Above-ground Biomass Based on Optimal Model Selection

GUO Chao-fan, CHEN Ze-wei, ZHANG Zhi-gao

College of Resources Environment and Tourism, Anyang Normal University, Anyang, Henan Province 455000, China

Received:2020-10-29 Revised:2021-01-20 Online:2021-05-15 Published:2021-06-02

摘要/Abstract

摘要： 生物量快速精准监测对于草地资源的可持续开发和利用具有重要意义。以青海省海晏县草场为研究区，采用Sentinel-2影像结合地面实测数据进行牧草生物量估算研究并探究最优模型。构建21种典型植被指数与生物量的关系模型，包括单变量指数模型、多元线性模型和随机森林模型，并采用留一交叉验证决定系数和均方根误差进行模型精度检验和最优模型选择。结果表明：绿色叶绿素指数（Green chlorophyll index，CI_green）和归一化差异水体指数（Normalized difference water index，NDWI）与生物量具有最优拟合关系，同样反映牧草水分和叶绿素含量的其他指数在模型中也具有重要的贡献占比，说明牧草的长势和水分含量对牧草生物量的估算具有较大影响。3种模型中，多元模型精度高于单变量模型，非线性模型精度高于线性模型。其中随机森林模型效果最优，R_cv²达到0.74，RMSE_cv达到187.71 g·m^-2，并且该模型在缓解“过饱和”方面也具有明显优势。

关键词: 牧草, 生物量估算, Sentinel-2影像, 随机森林, 青海省草地

Abstract: Above-ground biomass of grassland is one of the key indicators for evaluating the grassland ecosystem productivity,and accurate estimation of forage biomass has important guiding significance for the real-time monitoring of growth status,the sustainable use,and management of grassland resources. The sentinel-2 image and ground measured data of the study area,which was located in Haiyan country,Qinghai Province,were used for the estimation of forage biomass to explore the optimal model. To select the optimal regression model,21 typical relationship models related to vegetation index and forage biomass data were constructed,which included a univariate index model,multiple linear regression model,and random forest model. Moreover,the model accuracy was tested through the Leave-one-out cross-validated coefficient of determination (R_cv²) and the cross-validated root mean square error (RMSE_cv). Finally,the optimal inversion model was used to map the spatial distribution of biomass of the study area. The results showed that CI_greenand NDWI had better performance in fitting relationship with forage biomass. The CI_re,MTVI2,GVMI2,and WDRVI,which indicate the water content and chlorophyll content of forage,also had important contributions in the multivariate model,which indicated that the growth and water content of forage had a great influence on the estimation of forage wet biomass. Besides,the accuracy of estimated results could be effectively improved by eliminating image noise (atmospheric noise and background noise). In the three inversion models,the random forest model had the best estimation accuracy,R_cv²reached 0.74,and RMSE_cv reached 187.71 g·m^-2. In conclusion,the study used Sentinel-2 data combining with random forest algorithm to form an accurate estimation of forage biomass. The results could provide a theoretical basis for remote sensing monitoring of forage biomass in the future and a reference for sustainable development and utilization of grassland.

Key words: Forage, Biomass estimation, Sentinel-2 image, Random forest, Grassland in Qinghai Province

中图分类号:

S812

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.

GUO Chao-fan, CHEN Ze-wei, ZHANG Zhi-gao. Research on Remote Sensing Estimation of Forage Above-ground Biomass Based on Optimal Model Selection[J]. Acta Agrestia Sinica, 2021, 29(5): 946-955.

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.1007-0435.2021.05.011

https://manu40.magtech.com.cn/Jweb_cdxb/CN/Y2021/V29/I5/946

参考文献

[1] 姜恕. 草地生态研究方法[M]. 北京:农业出版社,1988:10
[2] 徐斌,杨秀春,侯向阳,等. 草原植被遥感监测方法研究进展[J]. 科技导报,2007(9):5-8
[3] 朴世龙,方精云,贺金生,等. 中国草地植被生物量及其空间分布格局[J]. 植物生态学报,2004(4):491-498
[4] 蔡宗磊,苗正红,常雪,等. 基于无人机大样方数据及国产卫星反演草地植被覆盖度方法研究[J]. 草地学报,2019,27(5):1431-1440
[5] 于璐,王迅,柴沙驼,等. 基于高分卫星遥感的天然草地牧草营养含量季节动态反演的研究[J]. 草地学报,2020,28(2):547-557
[6] 渠翠平,关德新,王安志,等.基于MODIS数据的草地生物量估算模型比较[J]. 生态学杂志,2008(11):2028-2032
[7] 牛志春,倪绍祥. 青海湖环湖地区草地植被生物量遥感监测模型[J]. 地理学报,2003(5):695-702
[8] 潘影,张燕杰,武俊喜,等. 基于遥感和无人机数据的草地NDVI影响因子多尺度分析[J]. 草地学报,2019,27(6):1766-1773
[9] 陈鹏飞,Nicolas Tremblay,王纪华,等. 估测作物冠层生物量的新植被指数的研究[J]. 光谱学与光谱分析,2010,30(2):512-517
[10] 高明亮,赵文吉,宫兆宁,等. 基于环境卫星数据的黄河湿地植被生物量反演研究[J]. 生态学报,2013,33(2):542-553
[11] 张正健,刘志红,郭艳芬,等. 基于NDVI的西藏不同草地类型生物量回归建模分析[J]. 高原山地气象研究,2010,30(3):43-47
[12] 辛晓平,徐大伟,何小雷,等. 草地碳循环遥感研究进展[J]. 中国农业信息,2018,30(4):1-16
[13] Näsi,Roope,Viljanen N，Kaivosoja J，et al. Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features[J]. Remote Sensing,2018,10(7):1082-2014
[14] Andrew D,Pierce,Calvin A,et al. Use of random forests for modeling and mapping forest canopy fuels for fire behavior analysis in Lassen Volcanic National Park,California,USA - ScienceDirect[J]. Forest Ecology and Management,2012,279(1):77-89
[15] Onisimo Mutanga. High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm[J]. International Journal of Applied Earth Observation and Geoinformation 2012.18:399-406
[16] 张爱武,张帅,郭超凡,等. Landsat8光谱衍生数据分类体系下的牧草生物量反演[J]. 光谱学与光谱分析,2020,40(1):239-246
[17] 苏伟,赵晓凤,孙中平,等. 基于Sentinel-2A影像的玉米冠层叶绿素含量估算[J]. 光谱学与光谱分析,2019,39(5):1535-1542
[18] 郑阳,吴炳方,张淼. Sentinel-2数据的冬小麦地上干生物量估算及评价[J]. 遥感学报,2017,21(2):318-328
[19] Jurgens,C. The modified normalized difference vegetation index (mNDVI) a new index to determine frost damages in agriculture based on Landsat TM data[J]. International Journal of Remote Sensing,1997,18(17):3583-3594
[20] Dong T，Meng J，Shang J，et al. Evaluation of Chlorophyll-Related Vegetation Indices Using Simulated Sentinel-2 Data for Estimation of Crop Fraction of Absorbed Photosynthetically Active Radiation[J]. Selected Topics in Applied Earth Observations and Remote Sensing,IEEE Journal of,2015,8(8):4049-4059
[21] Wu C Y,N Z,G S,et al. The potential of the satellite derived green chlorophyll index for estimating midday light use efficiency in maize,coniferous forest and grassland[J]. Ecological Indicators,2012,14(1):66-73
[22] Zarco-Tejada P J，Hornero A，Hernandez-Clemente R，et al. Understanding the temporal dimension of the red-edge spectral region for forest decline detection using high-resolution hyperspectral and Sentinel-2a imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2018,137(3):134-148
[23] Boyd D S，Almond S，Dash J，et al. Phenology of vegetation in Southern England from Envisat MERIS terrestrial chlorophyll index (MTCI) data[J]. International Journal of Remote Sensing,2011,32(23):8421-8447
[24] Gitelson A A. Wide Dynamic Range Vegetation Index for Remote Quantification of Biophysical Characteristics of Vegetation[J]. Journal of Plant Physiology,2004,161(2):0-173
[25] Hardisky M A，Daiber F C，Roman C T，et al. Remote sensing of biomass and annual net aerial primary productivity of a salt marsh[J]. Remote Sensing of Environment,1984,16(2):91-106
[26] E.Raymond Hunt, M.Tugrul Yilmaz. Remote sensing of vegetation water content using shortwave infrared reflectances[C]. San Diego,California,United States,2007:237-239
[27] Liu J，Pattey E，Guillaume Jégo. Assessment of vegetation indices for regional crop green LAI estimation from Landsat images over multiple growing seasons[J]. Remote Sensing of Environment,2012,123:347-358
[28] Jiang Z，Huete A R，Didan K，et al. Development of a two-band enhanced vegetation index without a blue band[J]. Remote Sensing of Environment,2008,112(10):3833-3845
[29] Steven M D. The Sensitivity of the OSAVI Vegetation Index to Observational Parameters[J]. Remote Sensing of Environment,1998,63(1):49-60
[30] Li W，Du Z，Feng L，et al. A Comparison of Land Surface Water Mapping Using the Normalized Difference Water Index from TM,ETM+and ALI[J]. Remote Sensing,2013,5(11):5530-5549
[31] Ceccato P,Stéphane Flasse,Jean-Marie Grégoire. Designing a spectral index to estimate vegetation water content from remote sensing data:Part 2. Validation and applications[J]. Remote Sensing of Environment,2002,82(2-3):198-207
[32] N.Delbart,T.L.Toan,L.Kergoat,et al. Remote sensing of spring phenology in boreal regions:A free of snow-effect method using NOAA-AVHRR and SPOT-VGT data (1982-2004)[J]. Remote Sensing of Environment,2006,101(1):52-62
[33] 孙诗睿,赵艳玲,王亚娟,等. 基于无人机多光谱遥感的冬小麦叶面积指数反演[J]. 中国农业大学学报,2019,24(11):51-58
[34] 尚珂. 基于支持向量机回归的草地地上生物量遥感估测研究[D]. 昆明:西南林业大学,2015:124
[35] 刘振波,邹娴,葛云健,等. 基于高分一号WFV影像的随机森林算法反演水稻LAI[J]. 遥感技术与应用,2018,33(3):458-464
[36] 江佳乐,刘湘南,刘美玲,等. 基于随机森林的香港海域海表盐度遥感反演模型[J]. 海洋通报,2014,33(3):333-341
[37] 陈妍,宋豫秦,王伟. 基于随机森林回归的草场植被盖度反演模型研究——以新疆阿勒泰地区布尔津县为例[J]. 生态学报,2018,38(7):2384-2394
[38] Meng B，Yi S，Liang T，et al. Modeling alpine grassland above ground biomass based on remote sensing data and machine learning algorithm:A case study in the east of Tibetan Plateau,China[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,PP(99):2986-2995
[39] Meng B，Ge J，Liang T，et al. Evaluation of Remote Sensing Inversion Error for the Above-Ground Biomass of Alpine Meadow Grassland Based on Multi-Source Satellite Data[J]. REMOTE SENSING,2017,9(4):372-391

基于最优模型选择的牧草地上生物量遥感估算研究

Research on Remote Sensing Estimation of Forage Above-ground Biomass Based on Optimal Model Selection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	姚喜喜, 王立亚, 严振英, 张文娟, 孙海群, 周睿. 放牧对温性荒漠草原植物群落特征与牧草营养品质的影响[J]. 草地学报, 2021, 29(S1): 165-172.
[2]	张金花, 何静, 张小彦, 张树衡, 张恒, 李彦湘. 除草剂胁迫下3种牧草浸提液对受体植物种子萌发和幼苗生长的影响[J]. 草地学报, 2021, 29(8): 1719-1728.
[3]	姚喜喜, 才华, 刘皓栋, 李长慧. 不同季节高寒草甸牧草瘤胃发酵特性和体外消化率分析[J]. 草地学报, 2021, 29(8): 1729-1737.
[4]	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.
[5]	谢开云, 孟翔, 徐珍珍, 张力文, 万江春, 颜安, 李陈建. 新疆半干旱地区不同种类混播草地的牧草产量和营养价值研究[J]. 草地学报, 2021, 29(8): 1835-1842.
[6]	张峰, 赵天启, 乔荠瑢, 赵萌莉, 张心玥, 吴建新. 刈割留茬高度对大针茅草原生产力及可持续利用的影响[J]. 草地学报, 2021, 29(7): 1491-1498.
[7]	王晶, 伏兵哲. 基于文献计量分析的禾本科牧草染色体加倍研究进展[J]. 草地学报, 2021, 29(3): 413-424.
[8]	王斌, 杨彦军, 董秀, 李满有, 沈笑天, 曹立娟, 兰剑. 补播禾草对退化苜蓿草地生产性能及牧草品质的影响[J]. 草地学报, 2021, 29(3): 618-624.
[9]	苏贝贝, 张英, 道日娜. 4种豆科栽培牧草根际土壤细菌群落分布特征研究[J]. 草地学报, 2021, 29(2): 250-258.
[10]	苏贝贝, 张英, 道日娜. 4种豆科植物根际土壤真菌群落特征与土壤理化因子间相关性分析[J]. 草地学报, 2021, 29(12): 2670-2677.
[11]	王玉琴, 宋梅玲, 王宏生, 尹亚丽, 马玉寿. 添加氮素对退化高寒草地植被及营养品质的影响[J]. 草地学报, 2021, 29(12): 2742-2751.
[12]	姚喜喜, 周睿, 李长慧, 多杰索南. 坡向对青藏高原高寒草地植被分布格局和牧草品质特征的影响[J]. 草地学报, 2021, 29(12): 2792-2799.
[13]	贺福全, 陈懂懂, 李奇, 霍莉莉, 赵亮, 李春丽, 陈昕. 三江源区高寒草地营养承载力时空格局[J]. 草地学报, 2021, 29(12): 2808-2816.
[14]	张海娟, 芦光新, 范月君, 周华坤, 周学丽, 窦声云, 颜珲璘, 马坤, 赵阳安. 不同染色方法对两种禾本科牧草菌根侵染率的影响[J]. 草地学报, 2021, 29(12): 2838-2844.
[15]	王雪萌, 张涵, 宋瑞, 刘备, 张铁军, 毛培胜, 贾善刚. 中美牧草种子生产比较[J]. 草地学报, 2021, 29(10): 2115-2125.