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

Effective and accurate assessment of grassland above-ground biomass (AGB) especially via remote sensing (RS), is crucial for forage-livestock balance and ecological environment protection of alpine grasslands. Because of complexity and extensive spatial distribution of natural grassland resources, the RS estimation models based on moderate resolution imaging spectroradiometer (MODIS) data exhibited low accuracy and poor stability. In this study, various methods for estimating the AGB of alpine grassland vegetation using MODIS vegetation indices were evaluated by combining with meteorology, soil, topography geography and in situ measured AGB data (during grassland growing season from 2011 to 2016) in Gannan region. Results show that 1) five out of ten factors (elevation, slope, aspect, topographic position, temperature, precipitation and the concentration of clay and sand in the soil) exert significant effects on grassland AGB, with R2 0.04–0.39, and RMSE 859.68–1075.09 kg/ha, respectively; 2) the accuracy and stability of AGB estimation model can be improved by constructing multivariate models, especially using multivariate nonparameter models; 3) the optimum estimation model is constructed on the basis of random forest algorithm (RF). Compared with univariate/multivariate parameter models, RMSE of RF model decreased 26.45%–44.27%. Meanwhile, RF models can explain 89.41% variation in AGB during grass growing season. This study presented a more suitable RS inversion model integrated MODIS vegetation indices and other effect factors. Besides, the accuracy based on MODIS data was greatly improved. Thus, our study provides a scientific basis for effective and accurate estimating alpine grassland AGB.

[1]  B. Fu,et al.  Effects of plant diversity on soil erosion for different vegetation patterns , 2016 .

[2]  Dandan Xu,et al.  Some Insights on Grassland Health Assessment Based on Remote Sensing , 2015, Sensors.

[3]  D. O. Hall,et al.  The global carbon sink: a grassland perspective , 1998 .

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Jingyun Fang,et al.  Aboveground biomass in Tibetan grasslands , 2009 .

[6]  Jay Gao,et al.  Determination of land degradation causes in Tongyu County, Northeast China via land cover change detection , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Yang Fei.  Comparison of HJ-1A CCD and TM data and for estimating grass LAI and fresh biomass , 2012 .

[8]  Bin Xu,et al.  Remote sensing monitoring upon the grass production in China , 2007 .

[9]  Xing Li,et al.  A radiative transfer model-based method for the estimation of grassland aboveground biomass , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[10]  Qin He,et al.  Neural Network and Its Application in IR , 1999 .

[11]  Fiona Cawkwell,et al.  Modeling Managed Grassland Biomass Estimation by Using Multitemporal Remote Sensing Data—A Machine Learning Approach , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[12]  Jian Sun,et al.  Relationships of Biomass with Environmental Factors in the Grassland Area of Hulunbuir, China , 2014, PloS one.

[13]  H. Xie,et al.  Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region , 2018 .

[14]  Jan G. P. W. Clevers,et al.  Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties - A review , 2015 .

[15]  Li Zhang,et al.  Estimates of grassland biomass and turnover time on the Tibetan Plateau , 2018 .

[16]  Qianjun Zhao,et al.  Remote sensing based monitoring of interannual variations in vegetation activity in China from 1982 to 2009 , 2014, Science China Earth Sciences.

[17]  Lijian Han,et al.  A method of modifying error for non-synchronicity of grass yield remote sensing estimation and measurement , 2001 .

[18]  Huanhuan Yuan,et al.  Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models , 2017, Remote. Sens..

[19]  E. Dwyer,et al.  Satellite remote sensing of grasslands: from observation to management—a review , 2016 .

[20]  Jordi Cristóbal,et al.  Estimating above-ground biomass on mountain meadows and pastures through remote sensing , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[21]  Dominique Arrouays,et al.  Carbon cycling and sequestration opportunities in temperate grasslands , 2004 .

[22]  Jay Shankar Singh,et al.  Estimating aboveground net primary production in grasslands: a simulation approach , 1986 .

[23]  F. Baret,et al.  Assessing the biomass dynamics of Andean bofedal and totora high-protein wetland grasses from NOAA/AVHRR , 2003 .

[24]  Maj-Liz Nordberg,et al.  Vegetation index differencing and linear regression for change detection in a Swedish mountain range using Landsat TM® and ETM+® imagery , 2005 .

[25]  M. B. Dodd,et al.  Associations between vegetation patterns and soil texture in the shortgrass steppe , 2002, Plant Ecology.

[26]  M. Wachendorf,et al.  A multi-sensor approach for predicting biomass of extensively managed grassland , 2014 .

[27]  Stuart Green,et al.  Application of statistical and machine learning models for grassland yield estimation based on a hypertemporal satellite remote sensing time series , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[28]  Xiangzheng Deng,et al.  Diffused impact of grassland degradation over space: A case study in Qinghai province , 2017 .

[29]  F. Woodward,et al.  Increases in terrestrial carbon storage from the Last Glacial Maximum to the present , 1990, Nature.

[30]  Martin Brandt,et al.  Do Agrometeorological Data Improve Optical Satellite-Based Estimations of the Herbaceous Yield in Sahelian Semi-Arid Ecosystems? , 2016, Remote. Sens..

[31]  J. Li,et al.  MODIS-based remote-sensing monitoring of the spatiotemporal patterns of China's grassland vegetation growth , 2013 .

[32]  Xia Cui,et al.  Modeling of Alpine Grassland Cover Based on Unmanned Aerial Vehicle Technology and Multi-Factor Methods: A Case Study in the East of Tibetan Plateau, China , 2018, Remote. Sens..

[33]  Lukas W. Lehnert,et al.  Retrieval of grassland plant coverage on the Tibetan Plateau based on a multi-scale, multi-sensor and multi-method approach. , 2015 .

[34]  R. J. Olson,et al.  Estimating net primary productivity from grassland biomass dynamics measurements , 2002 .

[35]  Shi Qiu,et al.  Estimating the Aboveground Dry Biomass of Grass by Assimilation of Retrieved LAI Into a Crop Growth Model , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Shuxia Yang,et al.  Evaluation of Remote Sensing Inversion Error for the Above-Ground Biomass of Alpine Meadow Grassland Based on Multi-Source Satellite Data , 2017, Remote. Sens..

[37]  Hongjie Xie,et al.  Multi-factor modeling of above-ground biomass in alpine grassland: A case study in the Three-River Headwaters Region, China , 2016 .

[38]  Liang Tian-gang,et al.  Spatial and temporal dynamic changes of net primary product based on MODIS vegetation index in Gannan grassland. , 2010 .

[39]  Lei Zhang,et al.  A comparison of two models with Landsat data for estimating above ground grassland biomass in Inner Mongolia, China , 2009 .

[40]  Xiusheng Yang,et al.  Effects of rye grass coverage on soil loss from loess slopes , 2015, International Soil and Water Conservation Research.

[41]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[42]  Li Zhang,et al.  Application of Synthetic NDVI Time Series Blended from Landsat and MODIS Data for Grassland Biomass Estimation , 2015, Remote. Sens..

[43]  Bin Xu,et al.  Using MODIS time series data to estimate aboveground biomass and its spatio-temporal variation in Inner Mongolia’s grassland between 2001 and 2011 , 2013 .

[44]  Tiangang Liang,et al.  Classification management for grassland using MODIS data: a case study in the Gannan region, China , 2012 .

[45]  Robin P. White,et al.  Pilot analysis of global ecosystems: grassland ecosystems. , 2000 .

[46]  C. Schmullius,et al.  Carbon stock and density of northern boreal and temperate forests , 2014 .

[47]  Zhanjie Li,et al.  Roles of soil erodibility, rainfall erosivity and land use in affecting soil erosion at the basin scale , 2016 .

[48]  Qianjun Zhao,et al.  Estimating grassland aboveground biomass using multitemporal MODIS data in the West Songnen Plain, China , 2013 .

[49]  Estimating wetland vegetation biomass in the Poyang Lake of central China from Landsat ETM data , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[50]  Estimating wetland vegetation biomass in the Poyang Lake of central China from Landsat ETM data , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.