Evaluating Digital Soil Mapping Approaches for 3D Mapping of Soil Organic Carbon

Document Type : Research Paper

Authors

1 PhD. Student, Soil Science Department, University of Zanjan and Agricultural Research, Education and Extension Organization, Soil and Water Research Institute (SWRI)

2 Associate Professor, Dept. of Soil Science, Faculty of Agriculture, University of Zanjan

3 Assistant Professor, Dept. of Soil Science, Faculty of Agriculture and Natural Resources, University of Ardakan

4 Associate Professor, Dept. of Plant and Environmental Sciences, New Mexico State University

Abstract

Whileland resource management needs detailed and accurate information about soil properties and distribution, this kind of data is limited in Iran. In this research, we tested performance of three digital soil mapping (DSM) approaches including Multiple Linear Regression (MLR), Cubist (CU) and Random Forest (RF) to map the spatial 3D distribution of soil organic carbon (SOC) in Saadat Shahr plain in Fars Province. Latin hypercube sampling (LHS) was used to determine locations of soil profiles in the field. The soil profiles were sampled and SOC was measured. Different environmental covariates including terrain attributes, remote sensing auxiliary variables, and maps of soil, geoform and distance from rivers were used in this research as auxiliary data. According to the link of the environmental covariates and soil organic carbon contents in the framework of each model in combination with equal-area spline algorithm, soil organic carbon maps were produced at five standard depths of soils in the whole study area. Model performance was evaluated by root-mean-square error (RMSE), mean error (ME) and normalized root-mean-square error (NRMSE). Among the used models, RF model showed the highest performance to predict organic carbon in depths of 0-5 and 60-100 cm. Meanwhile, MLR and CU had the lowest error for prediction in depths of 5-15 and 15-30 cm, respectively. In spite of these results, RF model was considered as the best model for its power to explain the spatial distribution of soil organic carbon in all soil depths in the study area. 

Keywords

References

  1. اسکندری، ش.، ک. نبی­اللهی. و ر. تقی­زاده مهرجردی. 1397. نقشه­برداری رقومی کربن آلی خاک (مطالعه موردی: مریوان، استان کردستان). نشریه آب و خاک، جلد32، شماره4، 750-737.
  2. تقی زاده مهرجردی، ر.، ع. امیریان چکان. و ف. سرمدیان. 1397. نقشه­برداری رقومی سه بعدی ظرفیت تبادل کاتیونی خاک در منطقه دورود استان لرستان. نشریه آب وخاک. جلد 28، شماره 5، 1010-998.
  3. حسن­شاهی، ح. 1370. مطالعات خاک‌شناسی نیمه تفضیلی دشتهای سعادت‌شهر، سیوند، سیدان و ارسنجان (استان فارس). موسسه تحقیقات خاک و آب، نشریه شماره 838، 145 صفحه. تهران. ایران.
  4. Adhikari, K., Hartemink, A.E., Minasny, B., Bou Kheir, R., Greve, M.B., and M.H. Greve. 2014. Digital mapping of soil organic carbon contents and stocks in Denmark. PLoS One 9(8).
  5. Amirian-Chekan, A., Taghizadeh-Mehrjardi, R., Kerry, R., Kumar, S., Khordehbin, S., and S. Yusefi-Khanghah. 2017. Spatial 3D distribution of soil organic carbon under different land use types. Environ. Monit. Assess. 189:131.
  6. Ballabio, C. 2009. Spatial prediction of soil properties in temperate mountain regions using support vector regression. Geoderma. 151 (3–4):338–350.
  7. Bishop, T.F.A., McBratney, A.B., and G.M. Laslett. 1999. Modelling soil attribute depth functions with equal-area quadratic smoothing splines. Geoderma. 91 (1–2): 27–45.
  8. Breiman, L. 2001. Random forests. Machine Learning. 45:5-32.
  9. Brungard, C. W., Boettinger, J. L., Duniway, M. C., Wills, S. A., and T. C. Edwards. 2015. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma. 239- 240:68–83.
  10. Cambule, A.H., Rossiter, D.G., Stoorvogel, J.J., and E.M.A. Smaling. 2014. Soil organic carbon stocks inthe Limpopo National Park, Mozambique: amount, spatial distribution and uncertainty. Geoderma. 213:46–56.
  11. Camera, C., Zomeni, Z., Noller, J.S., Zissimos, A.M., Christoforou, I.C., and A. Bruggeman. 2017. A high resolution map of soil types and physical properties for Cyprus: A digital soil mapping optimization. Geoderma. 285:35-49.
  12. Chabala, L. M., Mulolwa, A., and O. Lungu. 2017. Application of ordinary kriging in mapping soil organic carbon in Zambia. Pedosphere. 27 (2):338-343.
  13. Gallant, J.C., and J.M. Austin. 2015. Derivation of terrain covariates for digital soil mapping in Australia. Soil Research. 53:895–90.
  14. Global Soil Map. 2011. Specifications, Version 1 Global Soil Map.net products. Release 2.1.
  15. Guo, P.T., Li, M.F., Luo, W., Tang, Q.F., Liu, Z.W., and Z.M. Lin. 2015. Digital mapping of soil organic matter for rubber plantation at regional scale: an application of Random Forest plus residual kriging approach. Geoderma. 237-238:49-59.
  16. Hastie, T., Tibshirani, R., and J. Friedman. 2001. The elements of statistical learning: data mining, inference, and prediction. Springer, New York.
  17. Hengl, T., Huvelink, G.B.M., and A. Stein. 2004. A genericframework for spatial prediction of soil variables based on regression-kriging. Geoderma. 120 (1–2):75–93.
  18. Hengl, T., Heuvelink, G.B., Kempen, B., Leenaars, J.G., Walsh, M.G., Shepherd, K.D., Sila, A., MacMillan, R.A., de Jesus, J.M., Tamene, L., and J.E. Tondoh. 2015. Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions. PLoS One. 10:1–26.
  19. Ho, H.C., Knudby, A., Sirovyak, P., Xu, Y., Hodul, M., and S.B. Henderson. 2014. Mapping maximum urban air temperature on hot summer days. Remote Sens Environ. 154:38-5.
  20. Holmes, G., Hall, M., and E. Frank. 1999. Generating rule sets from model trees. In: Foo, N. (Ed.), AdvancedTopics in Artificial Intelligence. Lecture Notes in Artificial Intelligence. 1–12.
  21. Jenny, H. 1941. Factors of Soil Formation, A System of Quantitative Pedology. McGraw-Hill, New York.
  22. Karunaratne, S.B., Bishop, T.F.A., Baldock, J.A., and I.O.A. Odeh. 2014. Catchment scale mapping of measureable soil organic carbon fractions. Geoderma. 219:14–23.
  23. Kempen, B., Brus, D. J., and J.J. Stoorvogel. 2011. Three dimensional mapping of soil organic matter content using soil type–specific depth functions. Geoderma, 162 (1–2), 107–123.
  24. Liu, F., Zhang, G. L., Sun, Y. J., Zhao, Y. G., and D.C. Li. 2013. Mapping the three-dimensional distribution of soil organicmatter across a subtropical hilly landscape. Soil Sci. Soc. Am. J. 77(4):1241–1253.
  25. Mahler, P. J (ED). 1970. Manual of Multipurpose Land Classification. Report no. 212. Soil and Water Research Institute (SWIR), Tehran. Iran.
  26. Malone, B.P., McBratney, A.B., Minasny, B., and G.M. Laslett. 2009. Mapping continuous depth functions of soil carbon storage and available water capacity. Geoderma. 154:138–152.
  27. Malone, B.P., Minasny, B., and A.B. McBratney. 2017. Using R for digital soil mapping. Netherlands, Springer.
  28. Martin, M.P., Orton, T.G., Lacarce, E., Meersmans, J., Sably, N.P.A., Paroissien, J.B., Jolivet, C., Boulonne, L., and D. Arrouays. 2014. Evaluation of modeling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale. Geoderma 223–225:97–107.
  29. McBratney, A.B., Mendonça Santos, M.L., and B. Minasny. 2003. on digital soil mapping. Geoderma. 117:3–52.
  30. McBratney, A.B., Stockmann, U., Angers, D., Minasny, B., and D. Field. 2014. Challenges for Soil Organic Carbon Research. In Alfred E. Hartemink, Kevin McSweeney (Eds.), Soil Carbon, (pp. 3-16). Cham: Springer.
  31. Minasny, B., and A.B. McBratney. 2006. A conditioned Latin hypercube method for samplingin the presence of ancillary information. Comput. Geosci. 32:1378–1388.
  32. Minasny, B., McBratney, A. B., Malone, B. P., and I. Wheeler. 2010. Digital mapping of soil carbon. 19th World Congress of Soil Science. Brisbane, Australia.
  33. Minasny, B., McBratney, A. B., Malone, B. P., and I. Wheeler. 2013. Digital mapping of soil carbon. Adv. Agron. 118:1–47.
  34. Minasny, B., and A.B. McBratney. 2016. Digital soil mapping: a brief history and some lessons. Geoderma. 264:301-311.
  35. Mosleh, Z., Salehi, M.H., Jafari, A., Borujeni, I.E., and A. Mehnatkesh. 2016. The effectiveness of digital soil mapping to predict soil properties over low-relief areas. Environ. Monit. Assess. 188: 1–13.
  36. Poggio, L., and A. Gimona. 2014. National scale 3D modelling of soil organic carbon stockswith uncertainty propagation — an example from Scotland. Geoderma. 232–234:284–299.
  37. Rossel, R.A.V., Webster, R., Bui, E.N., and J.A. Baldock. 2014. Baseline map of organic carbon in Australian soil to support national carbon accounting and monitoring under climate change. Glob Chang Biol. 20 (9):2953–2970.
  38. R Development Core Team. 2015. R: a language and environment for statistical computing. R. Foundation for Statistical Computing, Vienna, Austria. http://www.
  39. Saga Development Team. 2011. System for Automated Geoscientific Analyses (SAGA). Available at http://saga-gis.org/en/index.html.
  40. Schoeneberger, P.J., Wysocki, D.A., Benham, E.C., and W.D. Broderson. 2012. Field book for describing and sampling soils, version 3.0. USDA Natural Resources Conservation Service, National Soil Survey Center, Lincoln, NE.
  41. Sindayihebura, A., Ottoy, S., Dondeyne, S., and M.V. Meirvenne. 2017. Comparing digital soil mapping techniques for organic carbon and clay content: Case study in Burundi's central plateaus. Catena. 156:161-175.
  42. Soil Survey Staff. 2014. Keys to soil taxonomy, 12th edition. USDA Natural Resources Conservation Service.
  43. Taghizadeh-Mehrjardi, R., Nabiollahi, K., and R. Kerry. 2016. Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma. 266:98–110.
  44. Venables, W.N., and B.D. Ripley. 2013. Modern applied statistics with S-PLUS. Springer.
  45. Walkly, A., and I. A. Black. 1934. An examination of digestion method for determining soil organic matter and a proposed modification of the chromic acid titration. Soil Sci. 37:29-38.
  46. Were, K., Bui, D.T., Dick, Ø.B., and B.R. Singh. 2015. 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. Ecol. Ind. 5:394–403.
  47. Wilding, L.P. 1985. Spatial variability: its documentation, accommodation and implicationto soil surveys. In: Nielsen, D.R., Bouma, J. (Eds.), Soil Spatial Variability. Pudoc, Wageningen, the Netherlands. 166–194.
  48. Zhao, Z., Yang, Q., Benoy, G., Chow, T.L., Xing, Z., Rees, H.W., and F.R. Meng. 2010. Using artificialneural network models to produce soil organic carbon content distribution maps acrosslandscapes. Soil Sci. 90 (1):75–87.
  49. Zinck, J.A. 1989. Physiography and soils. Lecture-notes for soil students. Soil Science Division. Soil survey courses subject matter: K6 ITC, Enschede, The Netherlands.
Iranian Journal of Soil Research
Volume 33, Issue 2
September 2019
Pages 227-239

Files

Share

How to cite

Statistics