Please wait a minute...
Journal of Integrative Agriculture  2019, Vol. 18 Issue (2): 301-315    DOI: 10.1016/S2095-3119(18)61936-7
Special focus: Digital mapping in agriculture and environment Advanced Online Publication | Current Issue | Archive | Adv Search |
An integrated method of selecting environmental covariates for predictive soil depth mapping
LU Yuan-yuan1, 2, LIU Feng1, ZHAO Yu-guo1, 2, SONG Xiao-dong1, ZHANG Gan-lin1, 2 
1 State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, P.R.China
2 University of Chinese Academy of Sciences, Beijing 100049, P.R.China
Download:  PDF (20438KB) ( )  
Export:  BibTeX | EndNote (RIS)      
Abstract  
Environmental covariates are the basis of predictive soil mapping.  Their selection determines the performance of soil mapping to a great extent, especially in cases where the number of soil samples is limited but soil spatial heterogeneity is high.  In this study, we proposed an integrated method to select environmental covariates for predictive soil depth mapping.  First, candidate variables that may influence the development of soil depth were selected based on pedogenetic knowledge.  Second, three conventional methods (Pearson correlation analysis (PsCA), generalized additive models (GAMs), and Random Forest (RF)) were used to generate optimal combinations of environmental covariates.  Finally, three optimal combinations were integrated to produce a final combination based on the importance and occurrence frequency of each environmental covariate.  We tested this method for soil depth mapping in the upper reaches of the Heihe River Basin in Northwest China.  A total of 129 soil sampling sites were collected using a representative sampling strategy, and RF and support vector machine (SVM) models were used to map soil depth.  The results showed that compared to the set of environmental covariates selected by the three conventional selection methods, the set of environmental covariates selected by the proposed method achieved higher mapping accuracy.  The combination from the proposed method obtained a root mean square error (RMSE) of 11.88 cm, which was 2.25–7.64 cm lower than the other methods, and an R2 value of 0.76, which was 0.08–0.26 higher than the other methods.  The results suggest that our method can be used as an alternative to the conventional methods for soil depth mapping and may also be effective for mapping other soil properties.
Keywords:  environmental covariate selection        integrated method        predictive soil mapping        soil depth  
Received: 21 December 2017   Accepted:
Fund: The study was supported financially by the National Natural Science Foundation of China (91325301, 41571212 and 41137224), the Project of “One-Three-Five” Strategic Planning & Frontier Sciences of the Institute of Soil Science, Chinese Academy of Sciences (ISSASIP1622), and the National Key Basic Research Special Foundation of China (2012FY112100).
Corresponding Authors:  Correspondence ZHANG Gan-lin, Tel: +86-25-86881279, E-mail: glzhang@issas.ac.cn    
About author:  LU Yuan-yuan, E-mail: exlimit00@qq.com;

Cite this article: 

LU Yuan-yuan, LIU Feng, ZHAO Yu-guo, SONG Xiao-dong, ZHANG Gan-lin. 2019. An integrated method of selecting environmental covariates for predictive soil depth mapping. Journal of Integrative Agriculture, 18(2): 301-315.

Abe S. 2010. Support Vector Machines for Pattern Classification. 2nd ed. Springer-Verlag, London, UK.
Behrens T, Zhu A X, Schmidt K, Scholten T. 2010. Multi-scale digital terrain analysis and feature selection for digital soil mapping. Geoderma, 155, 175–185.
Boer M, Del Barrio G, Puigdefábres J. 1996. Mapping soil depth classes in dry Mediterranean areas using terrain attributes derived from a digital elevation model. Geoderma, 72, 99–118.
Böhner J, Selige T. 2006. Spatial prediction of soil attributes using terrain analysis and climate regionalisation. Gottinger Geographische Abhandlungen, 115, 13–28.
Breiman L. 2001. Random forests. Machine Learning, 45, 5–32.
Brevik E C, Calzolari C, Miller B A, Pereira P, Kabala C, Baumgarten A, Jordán A. 2016. Soil mapping, classification, and pedologic modeling: History and future directions. Geoderma, 264, 256–274.
Bui D T, Tuan T A, Klempe H, Pradhan B, Revhaug I. 2016. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides, 13, 361–378.
Bui E, Henderson B, Viergever K. 2009. Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia. Global Biogeochemical Cycles, 23, GB4033.
Buol S W, Southard R J, Graham R C, McDaniel P A. 2011. Soil Genesis and Classification. 6th ed. John Wiley & Sons, New York, USA.
DCHP (Data Center of the Heihe Project). 2011. Landsat TM mosaic image of the heihe riverBasin in 2010. [2013-07-03]. http://westdc.westgis.ac.cn
Deng J M, Qin B Q, Wang B W. 2015. Quick implementing of generalized additive models using R and its application in bluegreen algal bloom forecasting. Chinese Journal of Ecology, 34, 835–842. (in Chinese)
Dietrich W E, Reiss R, Hsu M L, Montgomery D R. 1995. A process-based model for colluvial soil depth and shallow landsliding using digital elevation data. Hydrological Processes, 9, 383–400.
Gessler P E, Moore I D, McKenzie N J, Ryan P J. 1995. Soil-landscape modelling and spatial prediction of soil attributes. International Journal of Geographical Information Systems, 9, 421–432.
Grimm R, Behrens T, Märker M, Elsenbeer H. 2008. Soil organic carbon concentrations and stocks on Barro Colorado Island - Digital soil mapping using Random Forests analysis. Geoderma, 146, 102–113.
Hastie T J, Tibshirani R J. 1990. Generalized Additive Models. Chapman and Hall, New York, USA.
Heimsath A M, Dietrich W E, Nishiizumi K, Finkel R C. 2001. Stochastic processes of soil production and transport: Erosion rates, topographic variation and cosmogenic nuclides in the Oregon Coast Range. Earth Surface Processes and Landforms, 26, 531–552.
Heung B, Bulmer C E, Schmidt M G. 2014. Predictive soil parent material mapping at a regional-scale: A Random Forest approach. Geoderma, 214, 141–154.
Hudson B D. 1992. The soil survey as paradigm-based science. Soil Science Society of America Journal, 56, 836–841.
Jenny H. 1994. Factors of Soil Formation: A System of Quantitative Pedology. McGraw-Hill, New York, USA.
Körner C. 2003. Alpine Plant Life: Functional Plant Ecology of High Mountain Ecosystems. 2nd ed. Springer Science and Business Media, New York, USA.
Körner C. 2007. The use of “altitude” in ecological research. Trends in Ecology & Evolution, 22, 569–574
Kuriakose S L, Devkota S, Rossiter D G, Jetten V G. 2009. Prediction of soil depth using environmental variables in an anthropogenic landscape, a case study in the Western Ghats of Kerala, India. Catena, 79, 27–38.
Lacoste M, Mulder V L, Richer-de-Forges A C, Martin M P, Arrouays D. 2016. Evaluating large-extent spatial modeling approaches: A case study for soil depth for France. Geoderma Regional, 7, 137–152.
Li A D, Tan X, Wu W, Liu H B, Zhu J. 2017. Predicting active-layer soil thickness using topographic variables at a small watershed scale. PLoS ONE, 12, e0183742.
Li X, Yang F, Li D C, Zhang G L. 2017. Mode of profile distribution of soil sand content and its affecting factors in the Qilian Mountains. Acta Pedologica Sinica, 54, 854–863.  (in Chinese)
Liang X, Wood E F, Lettenmaier D P. 1996. Surface soil moisture parameterization of the VIC-2L model: Evaluation and modification. Global and Planetary Change, 13, 195–206.
Lin L I K. 1989. A concordance correlation coefficient to evaluate reproducibility. Biometrics, 45, 255–268.
Liaw A, Wiener M. 2002. Classification and regression by randomForest. R News, 2, 18–22.
Liu F, Geng X, Zhu A X, Fraser W. 2012. Soil texture mapping over low relief areas using land surface feedback dynamic patterns extracted from MODIS. Geoderma, 171–172, 44–52.
Liu F, Geng X, Zhu A X, Walter F, Song X D, Zhang G L. 2016. Soil polygon disaggregation through similarity-based prediction with legacy pedons. Journal of Arid Land, 8, 760–772.
Liu F, Zhu A X, Li B L, Pei T, Qin C Z, Liu G H, Wang Y J, Zhou C H. 2009. Identification of spatial difference of soil types using land surface feedback dynamic patterns. Chinese Journal of Soil Science, 40, 501–508. (in Chinese)
Lu Y Y, Zhang G L, Zhao Y G, Li D C, Yang J L, Liu F. 2014. Extracting and mapping of soil depth distribution rules in complex landscape environment. Transactions of the Chinese Society of Agricultural Engineering, 30, 132–141. (in Chinese)
McBratney A B, Santos M M, Minasny B. 2003. On digital soil mapping. Geoderma, 117, 3–52.
Minasny B, McBratney A. 2016. Digital soil mapping: A brief history and some lessons. Geoderma, 264, 301–311.
Nottebaum V, Lehmkuhl F, Stauch G, Hartmann K, Wünnemann B, Schimpf S, Lu H. 2014. Regional grain size variations in aeolian sediments along the transition between Tibetan highlands and north-western Chinese deserts - the influence of geomorphological settings on aeolian transport pathways. Earth Surface Processes and Landforms, 39, 1960–1978.
Nottebaum V, Stauch G, Hartmann K, Zhang J R, Lehmkuhl F. 2015. Unmixed loess grain size populations along the northern Qilian Shan (China): Relationships between geomorphologic, sedimentologic and climatic controls. Quaternary International, 372, 151–166.
Pásztor L, Laborczi A, Takács K, Szatmári G, Bakacsi Z, Szabó J. 2016. Variations for the implementation of SCORPAN’s “S”. In: Digital Soil Mapping Across Paradigms. Scales and Boundaries. Springer, Singapore. pp. 331–342.
Power J F, Sandoval F M, Ries R E, Merrill S D. 1981. Effects of topsoil and subsoil thickness on soil water content and crop production on a disturbed soil. Soil Science Society of America Journal, 45, 124–129.
Pye K. 1995. The nature, origin and accumulation of loess. Quaternary Science Reviews, 14, 653–667.
R Development Core Team. 2014. R: A Language and Environment for Statistical Computing. [2015-01-25]. http://www.R-project.org/
Rad M R P, Toomanian N, Khormali F, Brungard C W, Komaki C B, Bogaert P. 2014. Updating soil survey maps using random forest and conditioned Latin hypercube sampling in the loess derived soils of northern Iran. Geoderma, 232, 97–106.
Rodriguez-Galiano V, Mendes M P, Garcia-Soldado M J, Chica-Olmo M, Ribeiro L. 2014. Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: A case study in an agricultural setting (Southern Spain). Science of the Total Environment, 476, 189–206.
Sarkar S, Roy A K, Martha T R. 2013. Soil depth estimation through soil-landscape modelling using regression kriging in a Himalayan terrain. International Journal of Geographical Information Science, 27, 2436–2454.
Scarpone C, Schmidt M G, Bulmer C E, Knudby A. 2016. Modelling soil thickness in the critical zone for Southern British Columbia. Geoderma, 282, 59–69.
Schenk H J, Jackson R B. 2005. Mapping the global distribution of deep roots in relation to climate and soil characteristics. Geoderma, 126, 129–140.
Scull P, Franklin J, Chadwick O A, McArthur D. 2003. Predictive soil mapping: A review. Progress in Physical Geography, 27, 171–197.
SSS (Soil Survey Staff). 2010. Keys to Soil Taxonomy. 11th ed. United States Department of Agriculture Natural Resources Conservation Service, Washington.
Svetnik V, Liaw A, Tong C, Culberson J C, Sheridan R P, Feuston B P. 2003. Random forest: A classification and regression tool for compound classification and QSAR modeling. Journal of Chemical Information and Computer Sciences, 43, 1947–1958.
Tang Y C. 2008. Statistical Analysis with R. Higher Education Press, Beijing. (in Chinese)
Tesfa T K, Tarboton D G, Chandler D G, McNamara J P. 2008. A generalized additive soil depth model for a mountainous semi-arid watershed based upon topographic and land cover attributes. In: Boettinger J L, Howell D W, Moore A C, Hartemink A E, Kienast-Broen S, eds., 3rd Global Workshop on Digital Soil Mapping-Bridging Research. Environmental Applications. and Operation. Springer, Logan, USA. pp. 29–41.
Tesfa T K, Tarboton D G, Chandler D G, McNamara J P. 2009. Modeling soil depth from topographic and land cover attributes. Water Resources Research, 45, 1–16.
Vapnik V N. 1998. Statistical Learning Theory. John Wiley& Sons, New York, USA.
Wang Q F, Jin H J, Zhang T J, Wu Q B, Cao B, Peng X Q, Wang K, Li L L. 2016. Active layer seasonal freeze-thaw processes and influencing factors in the alpine permafrost regions in the upper reaches of the Heihe River in Qilian Mountains. Chinese Science Bulletin, 61, 2742–2756. (in Chinese)
Wood S N. 2001. Mgcv: GAMs and generalized ridge regression for R. R News, 1, 20–25.
Yang F, Huang L M, Rossiter D G, Yang F, Yang R M, Zhang G L. 2017. Evolution of loess-derived soil along a climatic toposequence in the Qilian Mountains, NE Tibetan Plateau. European Journal of Soil Science, 68, 270–280.
Yang R M, Rossiter D G, Liu F, Lu Y Y, Yang F, Yang F, Zhao Y G, Li D C, Zhang G L. 2015. Predictive mapping of topsoil organic carbon in an Alpine environment aided by Landsat TM. PLoS ONE, 10, e0139042.
Yi C, Li D C, Zhang G L, Zhao Y G, Yang J L, Liu F, Song X D. 2015. Criteria for partition of soil thickness and case studies. Acta Pedologica Sinica, 52, 220–227. (in Chinese)
Zeng C Y, Yang L, Zhu A X. 2017. Construction of membership functions for soil mapping using the partial dependence of soil on environmental covariates calculated by random forest. Soil Science Society of America Journal, 81, 341–353.
Zhang G L, Liu F, Song X D. 2017. Recent progress and future prospect of digital soil mapping: A review. Journal of Integrative Agriculture, 16, 2871–2885.
Zhi J J, Zhang G L, Yang F, Yang R M, Liu F, Song X D, Zhao Y G, Li D C. 2017. Predicting mattic epipedons in the northeastern Qinghai-Tibetan Plateau using Random Forest. Geoderma Regional, 10, 1–10.
Zhu A X, Yang L, Li B L, Qin C Z, English E, Burt J E, Zhou C H. 2008. Purposive sampling for digital soil mapping for areas with limited data. In: Hartemink A E, McBratney A B, MendonÇa-Santos M L, eds., Digital Soil Mapping with Limited Data. Springer, Dordrecht. pp. 233–245.
Zou X B, Zhao J W, Malcolm J W P, Mel H, Mao H P. 2010. Variables selection methods in near-infrared spectroscopy. Analytica Chimica Acta, 667, 14–32.
 
[1] LIU Feng, YANG Fei, ZHAO Yu-guo, ZHANG Gan-lin, LI De-cheng. Predicting soil depth in a large and complex area using machine learning and environmental correlations[J]. >Journal of Integrative Agriculture, 2022, 21(8): 2422-2434.
No Suggested Reading articles found!