Upscaling plot-scale soil respiration in winter wheat and summer maize rotation croplands in Julu County, North China

Abstract Soil respiration (R s ) data from 45 plots were used to estimate the spatial patterns of R s during the peak growing seasons of winter wheat and summer maize in Julu County, North China, by combining satellite remote sensing data, field-measured data, and a support vector regression (SVR) model. The observed R s values were well reproduced by the model at the plot scale, with a root-mean-square error (RMSE) of 0.31 μmol CO 2  m −2  s −1 and a coefficient of determination (R 2 ) of 0.73. No significant difference was detected between the prediction accuracy of the SVR model for winter wheat and summer maize. With forcing from satellite remote sensing data and gridded soil property data, we used the SVR model to predict the spatial distributions of R s during the peak growing seasons of winter wheat and summer maize rotation croplands in Julu County. The SVR model captured the spatial variations of R s at the county scale. The satellite-derived enhanced vegetation index was found to be the most important input used to predict R s . Removal of this variable caused an RMSE increase from 0.31 μmol CO 2  m −2  s −1 to 0.42 μmol CO 2  m −2  s −1 . Soil properties such as soil organic carbon (SOC) content and soil bulk density (SBD) were the second most important factors. Their removal led to an RMSE increase from 0.31 μmol CO 2  m −2  s −1 to 0.37 μmol CO 2  m −2  s −1 . The SVR model performed better than multiple regression in predicting spatial variations of R s in winter wheat and summer maize rotation croplands, as shown by the comparison of the R 2 and RMSE values of the two algorithms. The spatial patterns of R s are better captured using the SVR model than performing multiple regression, particularly for the relatively high and relatively low R s values at the center and northeast study areas. Therefore, SVR shows promise for predicting spatial variations of R s values on the basis of remotely sensed data and gridded soil property data at the county scale.

[1]  W. Oechel,et al.  On the use of MODIS EVI to assess gross primary productivity of North American ecosystems , 2006 .

[2]  B. Wesemael,et al.  Spatial analysis of soil organic carbon evolution in Belgian croplands and grasslands, 1960–2006 , 2011 .

[3]  K. Ichii,et al.  Comparison of the data‐driven top‐down and bottom‐up global terrestrial CO2 exchanges: GOSAT CO2 inversion and empirical eddy flux upscaling , 2015 .

[4]  Thomas Schmid,et al.  Assessment of soil respiration patterns in an irrigated corn field based on spectral information acquired by field spectroscopy , 2015 .

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[6]  Zhenghua Hu,et al.  Global annual soil respiration in relation to climate, soil properties and vegetation characteristics: Summary of available data , 2014 .

[7]  Nina Buchmann,et al.  Biotic and abiotic factors controlling soil respiration rates in Picea abies stands , 2000 .

[8]  A. Marchetti,et al.  Spatial Distribution of Soil Organic Matter Using Geostatistics: A Key Indicator to Assess Soil Degradation Status in Central Italy , 2012 .

[9]  Zheng Niu,et al.  Relationships between soil respiration and photosynthesis-related spectral vegetation indices in two cropland ecosystems , 2012 .

[10]  Corinne Le Quéré,et al.  Contributions to accelerating atmospheric CO2 growth from economic activity, carbon intensity, and efficiency of natural sinks , 2007, Proceedings of the National Academy of Sciences.

[11]  J. Raich,et al.  Soil Temperature, Not Aboveground Plant Productivity, Best Predicts Intra-Annual Variations of Soil Respiration in Central Iowa Grasslands , 2006, Ecosystems.

[12]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[13]  Dominique Arrouays,et al.  GlobalSoilMap France: High-resolution spatial modelling the soils of France up to two meter depth. , 2016, The Science of the total environment.

[14]  D. Bonal,et al.  Spatial variation of soil respiration across a topographic gradient in a tropical rain forest in French Guiana , 2006, Journal of Tropical Ecology.

[15]  C. Field,et al.  Relationships Between NDVI, Canopy Structure, and Photosynthesis in Three Californian Vegetation Types , 1995 .

[16]  J. Balogh,et al.  Dependence of soil respiration on soil moisture, clay content, soil organic matter, and CO2 uptake in dry grasslands , 2011 .

[17]  Benyang Tang,et al.  Spacebased Estimation of Moisture Transport in Marine Atmosphere Using Support Vector Regression , 2008 .

[18]  D. Bui,et al.  A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. , 2015 .

[19]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[20]  Kazuhito Ichii,et al.  Upscaling terrestrial carbon dioxide fluxes in Alaska with satellite remote sensing and support vector regression , 2013 .

[21]  B. Wardlow,et al.  Analysis of time-series MODIS 250 m vegetation index data for crop classification in the U.S. Central Great Plains , 2007 .

[22]  Jungho Im,et al.  Forest Biomass and Carbon Stock Quantification Using Airborne LiDAR Data: A Case Study Over Huntington Wildlife Forest in the Adirondack Park , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[23]  G. Pan,et al.  Modeling interannual variability of global soil respiration from climate and soil properties , 2010 .

[24]  Kurt Hornik,et al.  The support vector machine under test , 2003, Neurocomputing.

[25]  Zheng Niu,et al.  Estimating soil respiration using spatial data products: A case study in a deciduous broadleaf forest in the Midwest USA , 2014 .

[26]  C. Potter,et al.  Interannual variability in global soil respiration, 1980–94 , 2002 .

[27]  J. Campbell,et al.  Supply‐side controls on soil respiration among Oregon forests , 2004 .

[28]  A-Xing Zhu,et al.  Developing a continental-scale measure of gross primary production by combining MODIS and AmeriFlux data through Support Vector Machine approach , 2007 .

[29]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[30]  Jinsheng Xie,et al.  The dynamic response of soil respiration to land‐use changes in subtropical China , 2010 .

[31]  J. C. Price.  The potential of remotely sensed thermal infrared data to infer surface soil moisture and evaporation , 1980 .

[32]  Yongqiang Yu,et al.  Estimating topsoil SOC sequestration in croplands of eastern China from 1980 to 2000 , 2009 .

[33]  Heba Elbasiouny,et al.  Spatial variation of soil carbon and nitrogen pools by using ordinary Kriging method in an area of north Nile Delta, Egypt , 2014 .

[34]  Zhongkui Luo,et al.  Predicting soil respiration using carbon stock in roots, litter and soil organic matter in forests of Loess Plateau in China , 2013 .

[35]  A. Thomson,et al.  Multi-Year Lags between Forest Browning and Soil Respiration at High Northern Latitudes , 2012, PloS one.

[36]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[37]  J. Drake,et al.  Modelling ecological niches with support vector machines , 2006 .

[38]  Wolfgang Lucht,et al.  A high‐resolution approach to estimating ecosystem respiration at continental scales using operational satellite data , 2014, Global change biology.

[39]  Guirui Yu,et al.  A remote sensing model to estimate ecosystem respiration in Northern China and the Tibetan Plateau , 2015 .

[40]  E. Davidson,et al.  Temperature sensitivity of soil carbon decomposition and feedbacks to climate change , 2006, Nature.

[41]  T. Andrew Black,et al.  Interpreting the dependence of soil respiration on soil temperature and water content in a boreal aspen stand , 2006 .

[42]  Nuno Carvalhais,et al.  Global spatiotemporal distribution of soil respiration modeled using a global database , 2015 .

[43]  Ryuichi Hirata,et al.  Multi-model analysis of terrestrial carbon cycles in Japan: limitations and implications of model calibration using eddy flux observations , 2010 .

[44]  Arnon Karnieli,et al.  Wheat and maize monitoring based on ground spectral measurements and multivariate data analysis , 2007 .

[45]  E. Davidson,et al.  Comparing simple respiration models for eddy flux and dynamic chamber data , 2006 .

[46]  Lei Zhang,et al.  Forest cover classification using Landsat ETM+ data and time series MODIS NDVI data , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[47]  T. Andrew Black,et al.  Soil respiration mapped by exclusively use of MODIS data for forest landscapes of Saskatchewan, Canada , 2014 .

[48]  Michael E. Schaepman,et al.  Representing major soil variability at regional scale by constrained Latin Hypercube Sampling of remote sensing data , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[49]  J. Raich,et al.  Vegetation and soil respiration: Correlations and controls , 2000 .

[50]  D. Baldocchi,et al.  Frontiers and challenges in soil respiration research: from measurements to model-data integration , 2011 .

[51]  T. A. Black,et al.  Remote sensing‐based estimation of annual soil respiration at two contrasting forest sites , 2015 .

[52]  Gerard B. M. Heuvelink,et al.  About regression-kriging: From equations to case studies , 2007, Comput. Geosci..

[53]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[54]  A-Xing Zhu,et al.  Prediction of Continental-Scale Evapotranspiration by Combining MODIS and AmeriFlux Data Through Support Vector Machine , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[55]  Michael G. Ryan,et al.  Interpreting, measuring, and modeling soil respiration , 2005 .

[56]  Markus Reichstein,et al.  Modeling temporal and large‐scale spatial variability of soil respiration from soil water availability, temperature and vegetation productivity indices , 2003 .

[57]  Shaohua Zhao,et al.  A Practical Split-Window Algorithm for Estimating Land Surface Temperature from Landsat 8 Data , 2015, Remote. Sens..

[58]  P. Ciais,et al.  Linking variability in soil solution dissolved organic carbon to climate, soil type, and vegetation type , 2014 .

[59]  C. Valentin,et al.  Soil organic carbon stocks in Laos: spatial variations and controlling factors , 2010 .

[60]  Chandra A. Madramootoo,et al.  Soil bulk density and crop yield under eleven consecutive years of corn with different tillage and residue practices in a sandy loam soil in central Canada , 2005 .

[61]  W. Han,et al.  Soil Respiration under Different Land Uses in Eastern China , 2015, PloS one.

[62]  Zheng Niu,et al.  Estimating the spatial pattern of soil respiration in Tibetan alpine grasslands using Landsat TM images and MODIS data , 2013 .

[63]  Zheng Niu,et al.  Modeling Spatial Patterns of Soil Respiration in Maize Fields from Vegetation and Soil Property Factors with the Use of Remote Sensing and Geographical Information System , 2014, PloS one.

[64]  Shaoqiang Wang,et al.  Impact of meteorological anomalies in the 2003 summer on Gross Primary Productivity in East Asia , 2009 .