Above-ground biomass estimation of provincial scattered grassland based on Google Earth Engine and machine learning

doi:10.13474/j.cnki.11-2246.2019.0076

Abstract

Abstract: Estimating above-ground biomass of grassland in large areas is of great significance for grassland resource utilization,management and global carbon cycle research.In order to pursue efficient and rapid estimation of above-ground biomass of provincial scattered grassland,this study selected Anhui province as the research area,built the relationship between Landsat8 OLI,auxiliary data and measured above-ground biomass data through machine learning and Google Earth Engine (GEE) platform.The main results showed that the model which constructed by spectral information,terrain factors and machine learning had obvious advantages,the estimated accuracy was more than 65%.The classification and regression tree (CART) model R² was 0.57,the estimated accuracy was 68.60%.Support vector machine (SVM) model R² was 0.59,the estimated accuracy was 75.74%.The GEE platform has rich and available data,it can complete pre-processing and calculation analysis efficiently.The combination of GEE and ground survey data has the potential to estimate above-ground biomass of scattered grassland on a national scale.

Key words: grassland biomass, Google Earth Engine, machine learning, regression analysis

CLC Number:

P237

XIU Xiaomin, ZHOU Shufang, CHEN Qian, MENG Jihua, DONG Wenquan, YANG Guangbin, LI Xiaosong. Above-ground biomass estimation of provincial scattered grassland based on Google Earth Engine and machine learning[J]. 测绘通报, 2019, 0(3): 46-52,75.

References

[1] Food and Agriculture Organization of the United Nations. FAOSTAT[EB/OL].[2018-10-21].http://www.fao.org/faostat/en/#country/351.
[2] 方精云,杨元合,马文红,等.中国草地生态系统碳库及其变化[J].中国科学(生命科学),2010,40(7):566-576.
[3] ALI I, CAWKWELL F, DWYER E, et al. Satellite remote sensing of grasslands:from observation to management-a review[J]. Journal of Plant Ecology, 2016, 9(6):649-671.
[4] POKLUDA P, HAUCK D,CIZEK L. Importance of marginal habitats for grassland diversity:fallows and overgrown tall-grass steppe as key habitats of endangered ground-beetle carabus hungaricus[J]. Insect Conservation and Diversity, 2012, 5(1):27-36.
[5] PUNJABI G A, CHELLAM R, VANAK A T. Importance of native grassland habitat for den-site selection of Indian foxes in a fragmented landscape[J]. PloS One, 2013, 8(10):e76410.
[6] SWAAY C A. The importance of calcareous grasslands for butterflies in Europe[J]. Biological Conservation, 2002, 104(3):315-318.
[7] 方精云,白永飞,李凌浩,等. 我国草原牧区可持续发展的科学基础与实践[J].科学通报,2016,61(2):155-164,133.
[8] 沈海花,朱言坤,赵霞,等. 中国草地资源的现状分析[J]. 科学通报, 2016, 61(2):139-154.
[9] 王新云,郭艺歌,何杰. 基于多源遥感数据的草地生物量估算方法[J]. 农业工程学报,2014,30(11):159-166.
[10] 方金. 基于多源遥感数据的甘南牧区草地生物量遥感监测研究[D]. 兰州:兰州大学,2013.
[11] 刘占宇,黄敬峰,吴新宏,等. 草地生物量的高光谱遥感估算模型[J]. 农业工程学报,2006,22(2):111-115.
[12] 除多,姬秋梅,德吉央宗,等. 利用EOS/MODIS数据估算西藏藏北高原地表草地生物量[J]. 气象学报,2007,65(4):612-621.
[13] 金云翔,徐斌,杨秀春,等. 内蒙古锡林郭勒盟草原产草量动态遥感估算[J]. 中国科学(生命科学),2011,41(12):1185-1195.
[14] 李庆,王洪涛,刘文,等. 以HJ-1卫星遥感数据估算高寒草地植被净第一性生产力的潜力评估——以若尔盖草地为例[J]. 中国沙漠,2013,33(4):1250-1255.
[15] 王红岩,李晓松,张瑾,等. 北京一号,环境星,Landsat TM传感器估算草地覆盖度、叶面积指数、地上生物量比较研究[J]. 光谱学与光谱分析,2013,33(10):2803-2808.
[16] 王磊,耿君,杨冉冉,等. 高分一号卫星影像特征及其在草地监测中的应用[J]. 草地学报,2015,23(5):1093-1100.
[17] 张旭琛,朱华忠,钟华平,等. 新疆伊犁地区草地植被地上生物量遥感反演[J]. 草业学报,2015,24(6):25-34.
[18] 行敏锋,何彬彬. 干旱区草原地上植被生物量估算——以乌图美仁大草原芦苇植被为例[J]. 地球信息科学学报,2014,16(2):335-340.
[19] 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.
[20] SIMONETTI D, SIMONETTI E, SZANTOI Z, et al. First results from the phenology-based synthesis classifier using Landsat 8 imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7):1496-1500.
[21] 徐晗泽宇,刘冲,王军邦,等. Google Earth Engine平台支持下的赣南柑橘果园遥感提取研究[J]. 地球信息科学学报,2018,20(3):396-404.
[22] DONG J W, XIAO X M, MENARGUEZ M A, et al. Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine[J]. Remote Sensing of Environment, 2016, 185:142-154.
[23] LOBELL D B, THAU D, SEIFERT C, et al. A scalable satellite-based crop yield mapper[J]. Remote Sensing of Environment, 2015, 164:324-333.
[24] HANSEN M C, POTAPOV P V, MOORE R, et al. High-resolution global maps of 21st-century forest cover change[J]. Science, 2014, 344(6187):850-853.
[25] PEKEL J F, COTTAM A, GORELICK N, et al. High-resolution mapping of global surface water and its long-term changes[J]. Nature, 2016, 540(7633):418-422.
[26] TRIANNI G, LISINI G, ANGIULI E, et al. Scaling up to national/regional urban extent mapping using Landsat data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7):3710-3719.
[27] PATEL N N, ANGIULI E, GAMBA P, et al. Multitemporal settlement and population mapping from Landsat using Google Earth Engine[J]. International Journal of Applied Earth Observation and Geoinformation, 2015, 35(Part B):199-208.
[28] KAUFMAN Y J, TANRE D. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS[J]. IEEE Transactions on Geoscience and Remote Sensing, 1992, 30(2):261-270.
[29] 梁栋,管青松,黄文江,等. 基于支持向量机回归的冬小麦叶面积指数遥感反演[J]. 农业工程学报,2013,29(7):117-123.
[30] 臧淑英,张策,张丽娟,等. 遗传算法优化的支持向量机湿地遥感分类——以洪河国家级自然保护区为例[J]. 地理科学,2012,32(4):434-441.
[31] CHANG C C, LIN C J. LIBSVM:A library for support vector machines[EB/OL].[2018-10-21].http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[32] FARUTO. LIBSVM-faruto ultimate version a toolbox with implements for support vector machines based on libsvm[EB/OL].[2018-10-21].http://www.matlabsky.com.
[33] 中华人民共和国农业部.天然草原等级评定技术规范.NY/T 1579-2007[S].北京:中国农业出版社,2008.
[34] 吴朝阳,牛铮. 基于辐射传输模型的高光谱植被指数与叶绿素浓度及叶面积指数的线性关系改进[J].植物学通报,2008,25(6):714-721.
[35] 何亚娟,潘学标,裴志远,等. 基于SPOT遥感数据的甘蔗叶面积指数反演和产量估算[J].农业机械学报,2013,44(5):226-231.
[36] JU J C, ROY D P. The availability of cloud-free Landsat ETM+ data over the conterminous United States and globally[J]. Remote Sensing of Environment, 2008, 112(3):1196-1211.
[37] ROY D P, JU J C, LEWIS P, et al. Multi-temporal MODIS-Landsat data fusion for relative radiometric normalization, gap filling, and prediction of Landsat data[J]. Remote Sensing of Environment, 2008, 112(6):3112-3130.
[38] VRIELING A, JONG S M D, STERK G, et al. Timing of erosion and satellite data:a multi-resolution approach to soil erosion risk mapping[J]. International Journal of Applied Earth Observation and Geoinformation, 2008, 10(3):267-281.
[39] GORELICK N, HANCHER M, DIXON M, et al. Google Earth Engine:planetary-scale geospatial analysis for everyone[J]. Remote Sensing of Environment, 2017, 202:18-27.
[40] 赵萍,傅云飞,郑刘根,等. 基于分类回归树分析的遥感影像土地利用/覆被分类研究[J].遥感学报,2005,9(6):708-716.
[41] 王健峰,张磊,陈国兴,等. 基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,39(3):28-31.
[42] 杜京义,侯媛彬. 基于遗传算法的支持向量回归机参数选取[J].系统工程与电子技术,2006,28(9):1430-1433.
[43] 王道明,鲁昌华,蒋薇薇,等. 基于粒子群算法的决策树SVM多分类方法研究[J].电子测量与仪器学报,2015,29(4):611-615.
[44] WASKE B, BENEDIKTSSON J A, ÁRNASON K, et al. Mapping of hyperspectral AVIRIS data using machine-learning algorithms[J]. Canadian Journal of Remote Sensing, 2009, 35(S1):106-116.
[45] 贾坤,姚云军,魏香琴,等. 植被覆盖度遥感估算研究进展[J].地球科学进展,2013,28(7):774-782.