Aboveground Biomass Simulation and Its Temporal-Spatial Variation of Yongqu River Basin in the Alpine Meadow in the Yellow River Source Zone

doi:10.11733/j.issn.1007-0435.2023.07.006

Acta Agrestia Sinica ›› 2023, Vol. 31 ›› Issue (7): 1964-1976.DOI: 10.11733/j.issn.1007-0435.2023.07.006

Previous Articles Next Articles

Aboveground Biomass Simulation and Its Temporal-Spatial Variation of Yongqu River Basin in the Alpine Meadow in the Yellow River Source Zone

LI Xi-lai¹, GAO Jay², SHI Yan²

1. College of Agriculture and Animal Husbandry, Qinghai University, Xining, Qinghai Province 810016, China;
2. School of Environment, the University of Auckland, Auckland 1010, New Zealand

Received:2022-12-28 Revised:2023-03-16 Online:2023-07-15 Published:2023-08-01

黄河源永曲河流域高寒草甸地上生物量模拟与时空分布特征研究

李希来¹, Jay Gao², 师研²

1. 青海大学农牧学院, 青海西宁 810016;
2. 奥克兰大学环境学院, 新西兰奥克兰 1010

通讯作者: 师研,E-mail:yshi917@aucklanduni.ac.Nz
作者简介:李希来(1964-),男,河南孟津县人,教授,主要从事高寒草地生态环境模拟、生态修复和管理的教学和科学研究,E-mail:xilai-li@163.com
基金资助:
青海省自然科学基金创新团队项目(2020-ZJ-904)；国家自然科学联合基金项目(U21A20191)；高等学校学科创新引智计划项目(D18013) ；青海省科技创新创业团队项目“三江源生态演变与管理创新团队”资助

Abstract

Abstract: It is critical to model and map alpine meadow aboveground biomass (AGB) accurately for pastoral sustainable management on the Qinghai-Tibet Plateau. This study evaluated the performance of the four models and various input features combinations for grassland AGB modelling and mapping based on Google Earth Engine in the Yellow River source zone. The former includes the traditional multiple linear regression (MLR),support vector machine (SVM),artificial neural network (ANN),and deep neural network (DNN),the latter the ground measurements (GM),geospatial variables (GV),meteorological variables (MV),plant functional types (VT). The results showed that the solely use of GV had poor performance in AGB simulation (0.122<R²<0.486). The involvement of MV and VT into GV improved the accuracy (R²) by 0.104~0.203. The combination of GM-GV improved the accuracy to the highest level (0.678<R²<0.705),but models with GM has limitation to map AGB. However,without GM,DNN achieved the highest accuracy of 0.686 (R²) using the feature combination of GV-VT-MV. It was found out that the use of multiple vegetation dataset improved the AGB estimation accuracy. Further analysis between the temporal-spatial AGB distribution and topographic factors showed that elevation is the most important determinant of AGB distribution,and it also has the strongest influence on the variation of annual AGB. The method proposed in this study was able to model and map alpine meadow AGB and its variation,it could be used in the management of the alpine meadow grassland for sustainable development.

Key words: Qinghai Tibet Plateau alpine meadow, Machine learning, Google Earth Engine, Aboveground biomass simulation, Spatial distribution of aboveground biomass

摘要： 本研究基于谷歌引擎通过四种常用模型及多种输入组合(地理空间变量(Geospatial variables,GV)，植物功能类型(Plant functional types,VT)，地面测量(Ground measurements,GM)，气象变量(Meteorological variables,MV))对黄河源区高寒草甸地上生物量(Aboveground biomass,AGB)进行了模拟，并分析了AGB的时空分布与地形因子的关系。结果表明，仅使用GV构建的模型表现较差(0.122<R²<0.486)，MV和VT分别与GV结合使用时能提高模拟精度0.104～0.203(R²)，GM与GV结合使用时，模型精度达到了最高(0.678<R²<0.705)。在没有GM参与的情况下，深度神经网络(Deep neural network,DNN)模型结合GV-VT-MV变量组合获得了最好模拟精度为0.686(R²)。混合使用多种植被类型的数据可以提高模拟精度。本研究发现海拔是影响黄河源流域单位内高寒草甸AGB时空分布的重要决定因素，并且对AGB年变化量影响最强。

关键词: 青藏高原高寒草甸, 机器学习, 谷歌引擎, 地上生物量模拟, 地上生物量空间分布

CLC Number:

Q141

LI Xi-lai, GAO Jay, SHI Yan. Aboveground Biomass Simulation and Its Temporal-Spatial Variation of Yongqu River Basin in the Alpine Meadow in the Yellow River Source Zone[J]. Acta Agrestia Sinica, 2023, 31(7): 1964-1976.

李希来, Jay Gao, 师研. 黄河源永曲河流域高寒草甸地上生物量模拟与时空分布特征研究[J]. 草地学报, 2023, 31(7): 1964-1976.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://manu40.magtech.com.cn/Jweb_cdxb/EN/10.11733/j.issn.1007-0435.2023.07.006

https://manu40.magtech.com.cn/Jweb_cdxb/EN/Y2023/V31/I7/1964

References

[1] ZHANG Y,ZHANG C,WANG Z,et al. Vegetation dynamics and its driving forces from climate change and human activities in the Three-River Source Region,China from 1982 to 2012[J]. Science of the Total Environment,2016,563-564:210-220
[2] 李凯辉,胡玉昆,王鑫,等. 不同海拔梯度高寒草地地上生物量与环境因子关系[J]. 应用生态学报,2007,18(9):2019-2024
[3] 赵慧芳,李晓东,张东,等. 基于MODIS数据的青海省草地地上生物量估算及影响因素研究[J]. 草业学报,2020,29(12):5-16
[4] XU B,YANG X C,TAO W G,et al. MODIS-based remote sensing monitoring of grass production in China[J]. International Journal of Remote Sensing,2008,29(17-18):5313-5327
[5] WACHENDORF M,FRICKE T,MÖCKEL T. Remote sensing as a tool to assess botanical composition,structure,quantity and quality of temperate grasslands[J]. Grass and Forage Science,2018,73(1):1-14
[6] 陈哲,汪浩,王金洲,等. 基于物候相机归一化植被指数估算高寒草地植物地上生物量的季节动态[J]. 植物生态学报,2021,45(5):487-495
[7] WEBER D,SCHAEPMAN-STRUB G,ECKER K. Predicting habitat quality of protected dry grasslands using Landsat NDVI phenology[J]. Ecological Indicators,2018,91:447-460
[8] GONG Z,KAWAMURA K,ISHIKAWA N,et al. MODIS normalized difference vegetation index (NDVI) and vegetation phenology dynamics in the Inner Mongolia grassland[J]. Solid Earth,2015,6(4):1185-1194
[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] 王正兴,刘闯,赵冰茹,等. 利用MODIS增强型植被指数反演草地地上生物量[J]. 兰州大学学报:自然科学版,2005,41(2):10-16
[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] BRETAS I L,VALENTE D S M,SILVA F F,et al. Prediction of aboveground biomass and dry-matter content in Brachiaria pastures by combining meteorological data and satellite imagery[J]. Grass and Forage Science,2021,76(3):340-352
[13] 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
[14] 张宪洲,李猛,武建双,等. 青藏高原草地地上生物量和理论载畜量[J]. 资源与生态学报,2022,13(1):129-141
[15] SHI Y,GAO J,LI X L,et al. Improved estimation of aboveground biomass of disturbed grassland through including bare ground and grazing intensity[J]. Remote Sensing,2021,13(11):2105
[16] 李士美,谢高地,张彩霞. 典型草地地上现存生物量资产动态[J]. 草业学报,2009,18(4):1-8
[17] LIANG T G,YANG S X,FENG Q S,et al. Multi-factor modeling of above-ground biomass in alpine grassland:A case study in the Three-River Headwaters Region,China[J]. Remote Sensing of Environment,2016,186:164-172
[18] REDDERSEN B,FRICKE T,WACHENDORF M. A multi-sensor approach for predicting biomass of extensively managed grassland[J]. Computers and Electronics in Agriculture,2014,109:247-260
[19] TIRYAKI S,AYDIN A. An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model[J]. Construction and Building Materials,2014,62:102-108
[20] PANDA S S,AMES D P,PANIGRAHI S. Application of vegetation indices for agricultural crop yield prediction using neural network techniques[J]. Remote Sensing,2010,2(3):673-696
[21] 乐荣武,张娜,王晶杰,等. 2000-2019 年内蒙古草地地上生物量的时空变化特征[J]. 中国科学院大学学报,2022,39(1):21-33
[22] 金哲人,冯琦胜,王瑞泾,等. 基于MODIS数据与机器学习的青藏高原草地地上生物量研究[J]. 草业学报,2022,31(10):1-17
[23] ZHANG B H,ZHANG L,XIE D,et al. Application of synthetic NDVI time series blended from Landsat and MODIS data for grassland biomass estimation[J]. Remote Sensing,2015,8(1):10
[24] YANG S X,FENG Q S,LIANG T G,et al. Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region[J]. Remote Sensing of Environment,2018,204:448-455
[25] XIE Y,SHA Z,YU M,et al. A comparison of two models with Landsat data for estimating above ground grassland biomass in Inner Mongolia,China[J]. Ecological Modelling,2009,220(15):1810-1818
[26] REICHSTEIN M,CAMPS-VALLS G,STEVENS B,et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature,2019,566(7743):195-204
[27] 秦格霞,吴静,李纯斌,等. 基于机器学习算法的天祝藏族自治县草地地上生物量反演[J]. 草业学报,2022,31(4):177-188
[28] BEYSOLOW II T. Introduction to deep learning using R:A step-by-step guide to learning and implementing deep learning models using R[M]. Berkeley:Apress,2017:6
[29] TAMIMINIA H,SALEHI B,MANDIANPARI M,et al. Comparison of machine and deep learning methods to estimate shrub willow biomass from UAS imagery[J]. Canadian Journal of Remote Sensing,2021,47(2):209-227
[30] MAIMAITIJIANG M,SAGAN V,SIDIKE P,et al. Soybean yield prediction from UAV using multimodal data fusion and deep learning[J]. Remote Sensing of Environment,2020,237:111599
[31] MOGHIMI A,YANG C,ANDERSON J A. Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat[J]. Computers and Electronics in Agriculture,2020,172:105299
[32] ZHANG H F,SUN Y,CHANG L,et al. Estimation of grassland canopy height and aboveground biomass at the quadrat scale using unmanned aerial vehicle[J]. Remote Sensing,2018,10(6):851
[33] 张典业,牛得草,陈鸿洋,等. 青藏高原东缘高寒草甸地上生物量的估测模型[J]. 山地学报,2014(4):453-459
[34] 苏淑兰,肖建设,裴青生,等. 放牧对高寒草地植被生长的影响及其生物量预测模型构建[J]. 草业科学,2019,36(1):20-26
[35] 赖炽敏,赖日文,薛娴,等. 基于植被盖度和高度的不同退化程度高寒草地地上生物量估算[J]. 中国沙漠,2019,39(5):127
[36] ZHOU W,LI H R,XIE L J,et al. Remote sensing inversion of grassland aboveground biomass based on high accuracy surface modeling[J]. Ecological Indicators,2021.121:107215
[37] WANG G Q,LIU S M,LIU T X,et al. Modelling above-ground biomass based on vegetation indexes:a modified approach for biomass estimation in semi-arid grasslands[J]. International Journal of Remote Sensing,2019,40(10):3835-3854
[38] 焦翠翠,于贵瑞,陈智,等. 基于遥感反演的 1982-2015 年中国北方温带和青藏高原高寒草地地上生物量空间数据集[J]. 中国科学数据(中英文网络版),2019,4(1):35-49
[39] HU H F,WANG Z H,LIU G H,et al. Vegetation carbon storage of major shrublands in China[J]. Journal of Plant Ecology,2006,30(4):539-544
[40] 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
[41] HANCHER M. New Techniques for Deep Learning with Geospatial Data using TensorFlow,Earth Engine,and Google Cloud Platform[C]. AGU Fall Meeting Abstracts,2017:IN11E-08
[42] DAI L,KE X,GUO X,et al. Responses of biomass allocation across two vegetation types to climate fluctuations in the northern Qinghai-Tibet Plateau[J]. Ecology and Evolution,2019,9(10):6105-6115
[43] 吴蓉蓉,史惠兰,王维,等. 青海河南高寒草地生态系统健康评价[J]. 安徽大学学报:自然科学版,2018,42(3):98-108
[44] 章文波,刘宝元,吴敬东. 小区植被覆盖度动态快速测量方法研究[J]. 水土保持通报,2001,21(6):60-63
[45] XING C R,FENG Y G,YANG G J,et al. Method of estimating vegetation coverage based on remote sensing[J]. Remote Sensing Technology and Application,2012,24(6):849-854
[46] SHI Y,GAO J,BRIERLEY G,et al. Improving the accuracy of models to map alpine grassland above-ground biomass using Google earth engine[J]. Grass and Forage Science,2023,78(2),237-253
[47] FAN J,YUE W,WU L,et al. Evaluation of SVM,ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China[J]. Agricultural and Forest Meteorology,2018,263:225-241
[48] WONG T T. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation[J]. Pattern Recognition,2015,48(9):2839-2846
[49] ZHANG W,DU T,WANG J. Deep learning over multi-field categorical data[C]. European Conference on Information Retrieval,2016:45-57
[50] DORMANN C F,ELITH J,BACHER S,et al. Collinearity:A review of methods to deal with it and a simulation study evaluating their performance[J]. Ecography,2013,36(1):27-46
[51] SMOLA A J,SCHOLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing,2004,14(3):199-222
[52] KURBIEL T,KHALEGHIAN S. Training of deep neural networks based on distance measures using RMSProp[EB/OL]. https://arxiv.org/abs/1708.01911,2017-08-06/2023-03-16
[53] RUDER S. An overview of gradient descent optimization algorithms[EB/OL]. https://arxiv.org/abs/1609.04747,2017-09-15/2023-03-16
[54] QOLOMANY B,MAABREH M,AL-FUQAHA A,et al. Parameters optimization of deep learning models using particle swarm optimization[C]. 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC),IEEE,2017:1285-1290
[55] SHRESTHA A,MAHMOOD A. Review of deep learning algorithms and architectures[J]. IEEE access,2019,7:53040-53065
[56] ROGERS J,GUNN S. Identifying feature relevance using a random forest[C]. Berlin:Springer,International Statistical and Optimization Perspectives Workshop "Subspace,Latent Structure and Feature Selection",2006:173-184
[57] YU H,WU Y,NIU L,et al. A method to avoid spatial overfitting in estimation of grassland above-ground biomass on the Tibetan Plateau[J]. Ecological Indicators,2021,125:107450
[58] GAO Q,ZHU W,SCHWARTZ M W,et al. Climatic change controls productivity variation in global grasslands[J]. Scientific Reports,2016,6:26958
[59] HU Z Y,LI Q X,CHEN X,et al. Climate changes in temperature and precipitation extremes in an alpine grassland of Central Asia[J]. Theoretical and Applied Climatology,2016,126(3-4):519-531
[60] SUN J,DU W P. Effects of precipitation and temperature on net primary productivity and precipitation use efficiency across China's grasslands[J]. GIScience and Remote Sensing,2017,54(6):881-897
[61] 董洲,赵霞,梁栋,等. 内蒙古灌丛化草原分布特征的遥感辨识[J]. 农业工程学报,2014,30(11):152-158
[62] 刘涛宇,赵霞,沈海花,等. 灌丛化草原灌木和草本植物光谱特征差异及灌木盖度反演——以内蒙古镶黄旗为例[J]. 植物生态学报,2016,40(10):969-979
[63] ZHOU L H,SHEN H H,CHEN L Y,et al. Ecological consequences of shrub encroachment in the grasslands of northern China[J]. Landscape Ecology,2019,34(1):119-130
[64] RACINE J S,HART J,LI Q. Testing the significance of categorical predictor variables in nonparametric regression models[J]. Econometric Reviews,2006,25(4):523-544
[65] SILVA J P M,DA SILVA M L M,DA SILVA E F,et al. Computational techniques applied to volume and biomass estimation of trees in Brazilian savanna[J]. Journal of Environmental Management,2019,249:109368
[66] DONG Z,ZHAO X,LIANG D,et al. Remote sensing identification of shrub encroachment in grassland in Inner Mongolia[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(11):152-158
[67] LIU T Y,ZHAO X,SHEN H H,et al. Spectral feature differences between shrub and grass communities and shrub coverage retrieval in shrub-encroached grassland in Xianghuang Banner,Nei Mongol,China[J]. Chinese Journal of Plant Ecology,2016,40(10):969-979
[68] ZHOU D,XIA Z,DONG L,et al. Remote sensing identification of shrub encroachment in grassland in Inner Mongolia[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(11):152-158
[69] MADSEN B,TREIER U A,ZLINSZKY A,et al. Detecting shrub encroachment in seminatural grasslands using UAS LiDAR[J]. Ecology and Evolution,2020,10(11):4876-4902
[70] KUEMMERLE T,RODER A,HILL J. Separating grassland and shrub vegetation by multidate pixel-adaptive spectral mixture analysis[J]. International Journal of Remote Sensing,2006,27(15):3251-3271
[71] WANG J,XIAO X M,BAJGAIN R,et al. Estimating leaf area index and aboveground biomass of grazing pastures using Sentinel-1,Sentinel-2 and Landsat images[J]. Isprs Journal of Photogrammetry and Remote Sensing,2019,154:189-201
[72] GUERINI FILHO M,KUPLICH T M,QUADROS F L F D. Estimating natural grassland biomass by vegetation indices using Sentinel 2 remote sensing data[J]. International Journal of Remote Sensing,2019,41(8):2861-2876
[73] ZENG W Z,ZHANG D Y,FANG Y H,et al. Comparison of partial least square regression,support vector machine,and deep-learning techniques for estimating soil salinity from hyperspectral data[J]. Journal of Applied Remote Sensing,2018,12(2):022204
[74] ZHENG H,CHENG T,LI D,et al. Combining Unmanned Aerial Vehicle (UAV)-Based Multispectral Imagery and Ground-Based Hyperspectral Data for Plant Nitrogen Concentration Estimation in Rice[J]. Front Plant Science,2018,9:936
[75] 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
[76] OSCO L P,MARCATO JUNIOR J,MARQUES RAMOS A P,et al. A review on deep learning in UAV remote sensing[J]. International Journal of Applied Earth Observation and Geoinformation,2021,102:102456
[77] ALI I,CAWKWELL F,GREEN S,DWYER N. Application of statistical and machine learning models for grassland yield estimation based on a hypertemporal satellite remote sensing time series[C]. 2014 IEEE Geoscience and Remote Sensing Symposium,IEEE,2014:5060-5063
[78] FAN J L,ZHENG J,WU L F,et al. Estimation of daily maize transpiration using support vector machines,extreme gradient boosting,artificial and deep neural networks models[J]. Agricultural Water Management,2021,245:106547
[79] YE Q,YU S,LIU J,et al. Aboveground biomass estimation of black locust planted forests with aspect variable using machine learning regression algorithms[J]. Ecological Indicators,2021,129:107948
[80] GE J,MENG B P,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
[81] 张雨欣,黄健熙,金云翔,等. 草地地上生物量估算模型研究进展[J]. 草地学报,2022,30(4):850-858
[82] MENG B,LIANG T,YI S,et al. Modeling alpine grassland above ground biomass based on remote sensing data and machine learning algorithm:A case study in east of the Tibetan Plateau,China[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:2986-2995
[83] YUAN Q Q,SHEN H F,LI T W,et al. Deep learning in environmental remote sensing:Achievements and challenges[J]. Remote Sensing of Environment,2020,241:111716
[84] CHEN Y,GUERSCHMAN J,SHENDRYK Y,et al. Estimating Pasture Biomass Using Sentinel-2 Imagery and Machine Learning[J]. Remote Sensing,2021,13(4):603
[85] BRIERLEY G J,LI X L,CULLUM C, et al. Landscape and Ecosystem Diversity,Dynamics and Management in the Yellow River Source Zone. Springer Geography[M]. Cham:Springer,Cham,2016:253-274
[86] 张宇鹏,吴笑天,李希来,等. 黄河源流域单元退化高寒草甸空间分布及其对土壤理化性质的响应[J]. 草地学报,30(3):503-512
[87] GAO Q,WAN Y,LI Y,et al. Effects of topography and human activity on the net primary productivity (NPP) of alpine grassland in northern Tibet from 1981 to 2004[J]. International Journal of Remote Sensing,2013,34(6):2057-2069
[88] 马婧婧,刘耘华,盛建东,等. 新疆草地优势种植物相对生物量沿海拔梯度变化特征[J]. 草业学报,2021,30(8):25-35
[89] 赵文,尹亚丽,李世雄,等. 祁连山不同类型草地植被群落及牧草营养特征研究[J]. 草地学报,2022,30(6):1328-1335
[90] ZHANG R Y,WANG Z W,HAN G D,et al. Grazing induced changes in plant diversity is a critical factor controlling grassland productivity in the Desert Steppe,Northern China[J]. Agriculture Ecosystems and Environment,2018,265:73-83

Aboveground Biomass Simulation and Its Temporal-Spatial Variation of Yongqu River Basin in the Alpine Meadow in the Yellow River Source Zone

黄河源永曲河流域高寒草甸地上生物量模拟与时空分布特征研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	WEN Tong, LIU Xiao-ni, JI Tong, YANG Dong-yang, QIAO Huan-huan, JIANG Jia-chang, PAN Dong-rong. Studying on Plant Classification and Recognition Method for Three-River Source Alpine Grassland Plant Based on Vegetation Index [J]. Acta Agrestia Sinica, 2022, 30(7): 1811-1818.
[2]	YUE Yi-fan, CHEN Guo-peng, WANG Li, LI Xiao-xia, LI Tian. Analyses of Vegetation Coverage Changes in Zhouqu County from 1998 to 2019 Based on GEE Platform [J]. Acta Agrestia Sinica, 2022, 30(6): 1534-1542.
[3]	BU Ling-xin, LAI Quan, LIU Xin-yi. Adaptation of Different Machine Learning Algorithms for Grassland Biomass Estimation [J]. Acta Agrestia Sinica, 2022, 30(11): 3156-3164.