Combining Environmental Factors and Lab VNIR Spectral Data to Predict SOM by Geospatial Techniques
|
摘要
Soil organic matter(SOM) is an important parameter related to soil nutrient and miscellaneous ecosystem services. This paper attempts to improve the performance of traditional partial least square regression(PLSR) model by considering the spatial autocorrelation and soil forming factors. Surface soil samples(n = 180) were collected from Honghu City located in the middle of Jianghan Plain, China. The visible and near infrared(VNIR) spectra and six environmental factors(elevation, land use types, roughness, relief amplitude, enhanced vegetation index, and land surface water index) were used as the auxiliary variables to construct the multiple linear regression(MLR), PLSR and geographically weighted regression(GWR) models. Results showed that: 1) the VNIR spectra can increase about 39.62% prediction accuracy than the environmental factors in predicting SOM; 2) the comprehensive variables of VNIR spectra and the environmental factors can improve about 5.78% and 44.90% relative to soil spectral models and soil environmental models, respectively; 3) the spatial model(GWR) can improve about 3.28% accuracy than MLR and PLSR. Our results suggest that the combination of spectral reflectance and the environmental variables can be used as the suitable auxiliary variables in predicting SOM, and GWR is a promising model for predicting soil properties.
Soil organic matter(SOM) is an important parameter related to soil nutrient and miscellaneous ecosystem services. This paper attempts to improve the performance of traditional partial least square regression(PLSR) model by considering the spatial autocorrelation and soil forming factors. Surface soil samples(n = 180) were collected from Honghu City located in the middle of Jianghan Plain, China. The visible and near infrared(VNIR) spectra and six environmental factors(elevation, land use types, roughness, relief amplitude, enhanced vegetation index, and land surface water index) were used as the auxiliary variables to construct the multiple linear regression(MLR), PLSR and geographically weighted regression(GWR) models. Results showed that: 1) the VNIR spectra can increase about 39.62% prediction accuracy than the environmental factors in predicting SOM; 2) the comprehensive variables of VNIR spectra and the environmental factors can improve about 5.78% and 44.90% relative to soil spectral models and soil environmental models, respectively; 3) the spatial model(GWR) can improve about 3.28% accuracy than MLR and PLSR. Our results suggest that the combination of spectral reflectance and the environmental variables can be used as the suitable auxiliary variables in predicting SOM, and GWR is a promising model for predicting soil properties.
Soil organic matter(SOM) is an important parameter related to soil nutrient and miscellaneous ecosystem services. This paper attempts to improve the performance of traditional partial least square regression(PLSR) model by considering the spatial autocorrelation and soil forming factors. Surface soil samples(n = 180) were collected from Honghu City located in the middle of Jianghan Plain, China. The visible and near infrared(VNIR) spectra and six environmental factors(elevation, land use types, roughness, relief amplitude, enhanced vegetation index, and land surface water index) were used as the auxiliary variables to construct the multiple linear regression(MLR), PLSR and geographically weighted regression(GWR) models. Results showed that: 1) the VNIR spectra can increase about 39.62% prediction accuracy than the environmental factors in predicting SOM; 2) the comprehensive variables of VNIR spectra and the environmental factors can improve about 5.78% and 44.90% relative to soil spectral models and soil environmental models, respectively; 3) the spatial model(GWR) can improve about 3.28% accuracy than MLR and PLSR. Our results suggest that the combination of spectral reflectance and the environmental variables can be used as the suitable auxiliary variables in predicting SOM, and GWR is a promising model for predicting soil properties.
引文
Al-Asadi R A,Mouazen A M,2014.Combining frequency domain reflectometry and visible and near infrared spectroscopy for assessment of soil bulk density.Soil&Tillage Research,135:60-70.doi:10.1016/j.still.2013.09.002
Bendini A,Cerretani L,Di Virgilio F et al.,2007.In process monitoring in industrial olive mill by means of FT-NIR.European Journal of Lipid Science and Technology,109(5):498-504.doi:10.1002/ejlt.200700001
Brown D J,Shepherd K D,Walsh M G et al.,2006.Global soil characterization with VNIR diffuse reflectance spectroscopy.Geoderma,132(3):273-290.doi:10.1016/j.geoderma.2005.04.025
Cambou A,Cardinael R,Kouakoua E et al.,2016.Prediction of soil organic carbon stock using visible and near infrared reflectance spectroscopy(VNIRS)in the field.Geoderma,261:151-159.doi:10.1016/j.geoderma.2015.07.007
Conforti M,Castrignano A,Robustelli G et al.,2015.Laboratory-based Vis-NIR spectroscopy and partial least square regression with spatially correlated errors for predicting spatial variation of soil organic matter content.Catena,124:60-67.doi:10.1016/j.catena.2014.09.004
Evrendilek F,Celik I,Kilic S,2004.Changes in soil organic carbon and other physical soil properties along adjacent Mediterranean forest,grassland,and cropland ecosystems in Turkey.Journal of Arid Environments,59(4):743-752.doi:10.1016/j.jaridenv.2004.03.002
FAO,1998.World Reference Base for Soil Resources.Rome:Food and Agriculture Organization of the United Nations.
Gaetan C,Guyon X,Bleakley K,2010.Spatial Statistics and Modeling.Springer,90.
Ge Y,Thomasson J A,Morgan C L et al.,2007.VNIR diffuse reflectance spectroscopy for agricultural soil property determination based on regression-kriging.Transactions of the Asabe,50(3):1081-1092.doi:10.13031/2013.23122
Guo L,Chen Y,Shi T et al.,2017a.Exploring the role of the spatial characteristics of visible and near-infrared reflectance in predicting soil organic carbon density.ISPRS International Journal of Geo-Information,6(10):308.doi:10.3390/ijgi6100308
Guo L,Linderman M,Shi T et al.,2018.Exploring the sensitivity of sampling density in digital mapping of soil organic carbon and its application in soil sampling.Remote Sensing,10(6):888.doi:10.3390/rs10060888
Guo L,Zhao C,Zhang H et al.,2017b.Comparisons of spatial and non-spatial models for predicting soil carbon content based on visible and near-infrared spectral technology.Geoderma,285:280-292.doi:10.1016/j.geoderma.2016.10.010
Gupta D D,2015.Soils as launching pad for healthy society and humannity-reality and not myth.International Journal Environmental&Agricultural Science,1(2):37-45.
Hartemink A E,McBratney A,de Lourdes M M,2008.Digital Soil Mapping with Limited Data.Springer Science&Business Media,250-251.
Hubert M,Rousseeuw P J,Vanden Branden K,2005.ROBPCA:a new approach to robust principal component analysis.Technometrics,47(1):64-79.doi:10.1198/004017004000000563
Jaber S M,Al-Qinna M I,2015.Global and local modeling of soil organic carbon using Thematic Mapper data in a semi-arid environment.Arabian Journal of Geosciences,8(5):3159-3169.doi:10.1007/s12517-014-1370-6
Kumar S,2015.Estimating spatial distribution of soil organic carbon for the Midwestern United States using historical database.Chemosphere,127:49-57.doi:10.1016/j.chemosphere.2014.12.027
Kumar S,Lal R,Liu D S et al.,2013.Estimating the spatial distribution of organic carbon density for the soils of Ohio,USA.Journal of Geographical Sciences,23(2):280-296.doi:10.1007/s11442-013-1010-1
Lagacherie P,2008.Digital Soil Mapping:A State of the Art.Springer,3-14.
Liu Y,Guo L,Jiang Q et al.,2015.Comparing geospatial techniques to predict SOC stocks.Soil and Tillage Research,148:46-58.doi:10.1016/j.still.2014.12.002
Mouazen A,Kuang B,De Baerdemaeker J et al.,2010.Comparison among principal component,partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy.Geoderma,158(1):23-31.
Peon J,Fernandez S,Recondo C et al.,2017.Evaluation of the spectral characteristics of five hyperspectral and multispectral sensors for soil organic carbon estimation in burned areas.International Journal of Wildland Fire,26(3):230-239.doi:10.1071/wf16122
Rai P,Majumdar G,DasGupta S et al.,2005.Prediction of the viscosity of clarified fruit juice using artificial neural network:a combined effect of concentration and temperature.Journal of Food Engineering,68(4):527-533.doi:10.1016/j.jfoodeng.2004.07.003
Rossel R A V,Webster R,2012.Predicting soil properties from the Australian soil visible-near infrared spectroscopic database.European Journal of Soil Science,63(6):848-860.doi:10.1111/j.1365-2389.2012.01495.x
Roudier P,Hedley C B,Lobsey C R et al.,2017.Evaluation of two methods to eliminate the effect of water from soil vis-NIRspectra for predictions of organic carbon.Geoderma,296:98-107.doi:https://doi.org/10.1016/j.geoderma.2017.02.014
Schmidt M W,Torn M S,Abiven S et al.,2011.Persistence of soil organic matter as an ecosystem property.Nature,478(7367):49-56.doi:10.1038/nature10386
Shekhar S,Xiong H,2008.Encyclopedia of GIS.Springer Science&Business Media,60-61.
Shi Z,Wang Q,Peng J et al.,2014.Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations.Science China Earth Sciences,57(7):1671-1680.doi:10.1007/s11430-013-4808-x
Terra F S,DemattêJ A M,Viscarra Rossel R A,2015.Spectral libraries for quantitative analyses of tropical Brazilian soils:Comparing vis-NIR and mid-IR reflectance data.Geoderma,255-256:81-93.doi:10.1016/j.geoderma.2015.04.017
Trangmar B B,Yost R S,Uehara G,1985.Application of geostatistics to spatial studies of soil properties.Advances in agronomy,38(1):45-94.doi:10.1016/S0065-2113(08)60673-2
Viscarra Rossel R A,Hicks W S,2015.Soil organic carbon and its fractions estimated by visible-near infrared transfer functions.European Journal of Soil Science,66(3):438-450.doi:10.1111/ejss.12237
Wang K,Zhang C,Li W,2013.Predictive mapping of soil total nitrogen at a regional scale:a comparison between geographically weighted regression and cokriging.Applied Geography,42:73-85.doi:10.1016/j.apgeog.2013.04.002
Wilding L,1985.Spatial variability:its documentation,accommodation and implication to soil surveys.Soil spatial variability.Workshop.
Zhang C,Tang Y,Xu X et al.,2011.Towards spatial geochemical modelling:use of geographically weighted regression for mapping soil organic carbon contents in Ireland.Applied Geochemistry,26(7):1239-1248.doi:10.1016/j.apgeochem.2011.04.014
Zhang Haitao,Guo Long,Chen Jiaying et al.,2013.Modeling of spatial distributions of farmland density and its temporal change using geographically weighted regression model.Chinese Geographical Science,24(2):191-204.doi:10.1007/s11769-013-0631-8
Zornoza R,Mataix-Solera J,Guerrero C et al.,2007.Evaluation of soil quality using multiple lineal regression based on physical,chemical and biochemical properties.Science of the Total Environment,378(1):233-237.doi:10.1016/j.scitotenv.2007.01.052
Bendini A,Cerretani L,Di Virgilio F et al.,2007.In process monitoring in industrial olive mill by means of FT-NIR.European Journal of Lipid Science and Technology,109(5):498-504.doi:10.1002/ejlt.200700001
Brown D J,Shepherd K D,Walsh M G et al.,2006.Global soil characterization with VNIR diffuse reflectance spectroscopy.Geoderma,132(3):273-290.doi:10.1016/j.geoderma.2005.04.025
Cambou A,Cardinael R,Kouakoua E et al.,2016.Prediction of soil organic carbon stock using visible and near infrared reflectance spectroscopy(VNIRS)in the field.Geoderma,261:151-159.doi:10.1016/j.geoderma.2015.07.007
Conforti M,Castrignano A,Robustelli G et al.,2015.Laboratory-based Vis-NIR spectroscopy and partial least square regression with spatially correlated errors for predicting spatial variation of soil organic matter content.Catena,124:60-67.doi:10.1016/j.catena.2014.09.004
Evrendilek F,Celik I,Kilic S,2004.Changes in soil organic carbon and other physical soil properties along adjacent Mediterranean forest,grassland,and cropland ecosystems in Turkey.Journal of Arid Environments,59(4):743-752.doi:10.1016/j.jaridenv.2004.03.002
FAO,1998.World Reference Base for Soil Resources.Rome:Food and Agriculture Organization of the United Nations.
Gaetan C,Guyon X,Bleakley K,2010.Spatial Statistics and Modeling.Springer,90.
Ge Y,Thomasson J A,Morgan C L et al.,2007.VNIR diffuse reflectance spectroscopy for agricultural soil property determination based on regression-kriging.Transactions of the Asabe,50(3):1081-1092.doi:10.13031/2013.23122
Guo L,Chen Y,Shi T et al.,2017a.Exploring the role of the spatial characteristics of visible and near-infrared reflectance in predicting soil organic carbon density.ISPRS International Journal of Geo-Information,6(10):308.doi:10.3390/ijgi6100308
Guo L,Linderman M,Shi T et al.,2018.Exploring the sensitivity of sampling density in digital mapping of soil organic carbon and its application in soil sampling.Remote Sensing,10(6):888.doi:10.3390/rs10060888
Guo L,Zhao C,Zhang H et al.,2017b.Comparisons of spatial and non-spatial models for predicting soil carbon content based on visible and near-infrared spectral technology.Geoderma,285:280-292.doi:10.1016/j.geoderma.2016.10.010
Gupta D D,2015.Soils as launching pad for healthy society and humannity-reality and not myth.International Journal Environmental&Agricultural Science,1(2):37-45.
Hartemink A E,McBratney A,de Lourdes M M,2008.Digital Soil Mapping with Limited Data.Springer Science&Business Media,250-251.
Hubert M,Rousseeuw P J,Vanden Branden K,2005.ROBPCA:a new approach to robust principal component analysis.Technometrics,47(1):64-79.doi:10.1198/004017004000000563
Jaber S M,Al-Qinna M I,2015.Global and local modeling of soil organic carbon using Thematic Mapper data in a semi-arid environment.Arabian Journal of Geosciences,8(5):3159-3169.doi:10.1007/s12517-014-1370-6
Kumar S,2015.Estimating spatial distribution of soil organic carbon for the Midwestern United States using historical database.Chemosphere,127:49-57.doi:10.1016/j.chemosphere.2014.12.027
Kumar S,Lal R,Liu D S et al.,2013.Estimating the spatial distribution of organic carbon density for the soils of Ohio,USA.Journal of Geographical Sciences,23(2):280-296.doi:10.1007/s11442-013-1010-1
Lagacherie P,2008.Digital Soil Mapping:A State of the Art.Springer,3-14.
Liu Y,Guo L,Jiang Q et al.,2015.Comparing geospatial techniques to predict SOC stocks.Soil and Tillage Research,148:46-58.doi:10.1016/j.still.2014.12.002
Mouazen A,Kuang B,De Baerdemaeker J et al.,2010.Comparison among principal component,partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy.Geoderma,158(1):23-31.
Peon J,Fernandez S,Recondo C et al.,2017.Evaluation of the spectral characteristics of five hyperspectral and multispectral sensors for soil organic carbon estimation in burned areas.International Journal of Wildland Fire,26(3):230-239.doi:10.1071/wf16122
Rai P,Majumdar G,DasGupta S et al.,2005.Prediction of the viscosity of clarified fruit juice using artificial neural network:a combined effect of concentration and temperature.Journal of Food Engineering,68(4):527-533.doi:10.1016/j.jfoodeng.2004.07.003
Rossel R A V,Webster R,2012.Predicting soil properties from the Australian soil visible-near infrared spectroscopic database.European Journal of Soil Science,63(6):848-860.doi:10.1111/j.1365-2389.2012.01495.x
Roudier P,Hedley C B,Lobsey C R et al.,2017.Evaluation of two methods to eliminate the effect of water from soil vis-NIRspectra for predictions of organic carbon.Geoderma,296:98-107.doi:https://doi.org/10.1016/j.geoderma.2017.02.014
Schmidt M W,Torn M S,Abiven S et al.,2011.Persistence of soil organic matter as an ecosystem property.Nature,478(7367):49-56.doi:10.1038/nature10386
Shekhar S,Xiong H,2008.Encyclopedia of GIS.Springer Science&Business Media,60-61.
Shi Z,Wang Q,Peng J et al.,2014.Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations.Science China Earth Sciences,57(7):1671-1680.doi:10.1007/s11430-013-4808-x
Terra F S,DemattêJ A M,Viscarra Rossel R A,2015.Spectral libraries for quantitative analyses of tropical Brazilian soils:Comparing vis-NIR and mid-IR reflectance data.Geoderma,255-256:81-93.doi:10.1016/j.geoderma.2015.04.017
Trangmar B B,Yost R S,Uehara G,1985.Application of geostatistics to spatial studies of soil properties.Advances in agronomy,38(1):45-94.doi:10.1016/S0065-2113(08)60673-2
Viscarra Rossel R A,Hicks W S,2015.Soil organic carbon and its fractions estimated by visible-near infrared transfer functions.European Journal of Soil Science,66(3):438-450.doi:10.1111/ejss.12237
Wang K,Zhang C,Li W,2013.Predictive mapping of soil total nitrogen at a regional scale:a comparison between geographically weighted regression and cokriging.Applied Geography,42:73-85.doi:10.1016/j.apgeog.2013.04.002
Wilding L,1985.Spatial variability:its documentation,accommodation and implication to soil surveys.Soil spatial variability.Workshop.
Zhang C,Tang Y,Xu X et al.,2011.Towards spatial geochemical modelling:use of geographically weighted regression for mapping soil organic carbon contents in Ireland.Applied Geochemistry,26(7):1239-1248.doi:10.1016/j.apgeochem.2011.04.014
Zhang Haitao,Guo Long,Chen Jiaying et al.,2013.Modeling of spatial distributions of farmland density and its temporal change using geographically weighted regression model.Chinese Geographical Science,24(2):191-204.doi:10.1007/s11769-013-0631-8
Zornoza R,Mataix-Solera J,Guerrero C et al.,2007.Evaluation of soil quality using multiple lineal regression based on physical,chemical and biochemical properties.Science of the Total Environment,378(1):233-237.doi:10.1016/j.scitotenv.2007.01.052