Prediction of aboveground grassland biomass on the Loess Plateau, China, using a random forest algorithm

Grasslands are an important component of terrestrial ecosystems that play a crucial role in the carbon cycle and climate change. In this study, we collected aboveground biomass (AGB) data from 223 grassland quadrats distributed across the Loess Plateau from 2011 to 2013 and predicted the spatial distribution of the grassland AGB at a 100-m resolution from both meteorological station and remote sensing data (TM and MODIS) using a Random Forest (RF) algorithm. The results showed that the predicted grassland AGB on the Loess Plateau decreased from east to west. Vegetation indexes were positively correlated with grassland AGB, and the normalized difference vegetation index (NDVI) acquired from TM data was the most important predictive factor. Tussock and shrub tussock had the highest AGB, and desert steppe had the lowest. Rainfall higher than 400 m might have benefitted the grassland AGB. Compared with those obtained for the bagging, mboost and the support vector machine (SVM) models, higher values for the mean Pearson coefficient (R) and the symmetric index of agreement (λ) were obtained for the RF model, indicating that this RF model could reasonably estimate the grassland AGB (65.01%) on the Loess Plateau.

[1]  Q. Wang,et al.  A method for determining vegetation growth process using remote sensing data: A case study in the Three-River Headwaters Region, China , 2019, Journal of Mountain Science.

[2]  M. Boschetti,et al.  Assessment of pasture production in the Italian Alps using spectrometric and remote sensing information , 2007 .

[3]  Ping Wang,et al.  The assimilation of spectral sensing and the WOFOST model for the dynamic simulation of cadmium accumulation in rice tissues , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[4]  D. Flanagan,et al.  Spatial distribution and temporal trends of extreme temperature and precipitation events on the Loess Plateau of China during 1961–2007 , 2010 .

[5]  Ho Tong Minh Dinh,et al.  Aboveground biomass mapping in French Guiana by combining remote sensing, forest inventories and environmental data , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[6]  N. Keenlyside,et al.  Optimising assimilation of hydrographic profiles into isopycnal ocean models with ensemble data assimilation , 2017 .

[7]  Kelly K. Caylor,et al.  On soil moisture–vegetation feedbacks and their possible effects on the dynamics of dryland ecosystems , 2007 .

[8]  Kelly K. Caylor,et al.  An ecohydrological approach to predicting hillslope‐scale vegetation patterns in dryland ecosystems , 2012 .

[9]  Nancy F. Glenn,et al.  Landsat 8 and ICESat-2: Performance and potential synergies for quantifying dryland ecosystem vegetation cover and biomass , 2016 .

[10]  Min Liu,et al.  Estimation and uncertainty analyses of grassland biomass in Northern China: Comparison of multiple remote sensing data sources and modeling approaches , 2016 .

[11]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

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

[13]  W. Hong.  RESEARCH ADVANCES OF VEGETATION EFFECT ON SOIL AND WATER CONSERVATION IN CHINA , 2002 .

[14]  Michele Meroni,et al.  Revisiting the concept of a symmetric index of agreement for continuous datasets , 2016, Scientific Reports.

[15]  E. Vivoni,et al.  Forest ecohydrological response to bimodal precipitation during contrasting winter to summer transitions , 2014 .

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

[17]  Y. Lü,et al.  Revegetation in China’s Loess Plateau is approaching sustainable water resource limits , 2016 .

[18]  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 .

[19]  F. Zhang,et al.  Runoff and soil loss characteristics on loess slopes covered with aeolian sand layers of different thicknesses under simulated rainfall , 2017 .

[20]  Lei Deng,et al.  Species Composition, Richness and Aboveground Biomass of Natural Grassland in Hilly-Gully Regions of the Loess Plateau, China , 2014 .

[21]  Li Wang,et al.  Effects of vegetation and slope aspect on water budget in the hill and gully region of the Loess Pla , 2011 .

[22]  Saurabh Das,et al.  A random forest algorithm for nowcasting of intense precipitation events , 2017 .

[23]  Gwangseob Kim,et al.  Space-time characterization of soil moisture from passive microwave remotely sensed imagery and ancillary data , 2002 .

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

[25]  Andrew K. Skidmore,et al.  Estimation of grassland biomass and nitrogen using MERIS data , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Ronghua Ma,et al.  Modeling grassland aboveground biomass using a pure vegetation index , 2016 .

[27]  L. 't Mannetje,et al.  Grasslands of the world , 2006 .

[28]  R. Crabtree,et al.  Hyperspectral One-Meter-Resolution Remote Sensing in Yellowstone National Park, Wyoming: I. Forage Nutritional Values , 2005 .

[29]  B. Hodson,et al.  The effect of passage in vitro and in vivo on the properties of murine fibrosarcomas. II. Sensitivity to cell-mediated cytotoxicity in vitro. , 1985, British Journal of Cancer.

[30]  Xinhua He,et al.  Balancing green and grain trade , 2015 .

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

[32]  O. Mutanga,et al.  Investigating the robustness of the new Landsat-8 Operational Land Imager derived texture metrics in estimating plantation forest aboveground biomass in resource constrained areas , 2015 .

[33]  Bin Xu,et al.  Remote Sensing-Based Biomass Estimation and Its Spatio-Temporal Variations in Temperate Grassland, Northern China , 2014, Remote. Sens..

[34]  Thomas Alexandridis,et al.  Data assimilation of satellite-based actual evapotranspiration in a distributed hydrological model of a controlled water system , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[35]  A. Porporato,et al.  Interplay of climate seasonality and soil moisture‐rainfall feedback , 2014 .

[36]  T. Jackson,et al.  Field observations of soil moisture variability across scales , 2008 .

[37]  Jing Wang,et al.  Estimating near future regional corn yields by integrating multi-source observations into a crop growth model , 2013 .

[38]  S. E. Haupt,et al.  Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation , 2017 .

[39]  Panteleimon Xofis,et al.  Factors affecting distribution of vegetation types on abandoned cropland in the hilly-gullied Loess Plateau region of China , 2008 .

[40]  Qi Jing,et al.  Estimating winter wheat biomass by assimilating leaf area index derived from fusion of Landsat-8 and MODIS data , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[41]  Jack E. Norland,et al.  Hyperspectral One-Meter-Resolution Remote Sensing in Yellowstone National Park, Wyoming: II. Biomass , 2005 .

[42]  O. Mutanga,et al.  Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa , 2015 .

[43]  Terje Gobakken,et al.  Mapping and estimating forest area and aboveground biomass in miombo woodlands in Tanzania using data from airborne laser scanning, TanDEM-X, RapidEye, and global forest maps: A comparison of estimated precision , 2016 .

[44]  O. Sala.  Grassland Ecosystems , 2012 .

[45]  Maosheng Zhao,et al.  Drought-Induced Reduction in Global Terrestrial Net Primary Production from 2000 Through 2009 , 2010, Science.

[46]  Long-qi Sun,et al.  Effects of incorporated plant litter on soil resistance to flowing water erosion in the Loess Plateau of China , 2016 .

[47]  J. Morrison,et al.  Distribution mapping of world grassland types , 2014 .

[48]  Mingyue Zhao,et al.  Spatial Heterogeneity of Soil Moisture and the Scale Variability of Its Influencing Factors: A Case Study in the Loess Plateau of China , 2013 .

[49]  Saguna Saguna,et al.  Applied machine learning: Forecasting heat load in district heating system , 2016 .

[50]  Rui Guo,et al.  Spatial and Temporal Variability of Annual Precipitation during 1958-2007 in Loess Plateau, China , 2010, CCTA.

[51]  Zhuo Feng,et al.  The effects of N and P additions on microbial N transformations and biomass on saline-alkaline grassland of Loess Plateau of Northern China , 2014 .