Analysis of different sources of uncertainty in digital mapping of some soil properties (case study of Ravansar plain, Kermanshah province)

Document Type : Original Article

Authors

1 Research Assistant Prof., Soil and Water Research Department, Kermanshah Agricultural and Natural Resources Research and Education Center, AREEO, Kermanshah, Iran

2 soil conservation departement

3 Research Associate Professors, Soil and Water Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran;

10.30466/asr.2025.55489.1853

Abstract

The digital mapping of sand, silt and clay is used in the design of irrigation systems, land evluation and soil erosion models. In contrast, the quantification of the spatial uncertainty of the mentioned soil properties provides users with a criterion for the reliability of these maps. For this purpose, in this research, two sources of uncertainty, including the uncertainty of variation of available data and the uncertainty of the model, were investigated using the standard deviation criterion. This research performed in an area of 57000 hectares in Ravansar plain of Kermanshah province. 120 observation points and derivatives of DEM and vegetation and parent materials indices obtained from Landsat 8 images were used as model inputs. To estimate the uncertainty caused by the variations in the available data, the random forest model was run 50 times based on the random separation of the data into two categories: training (25%) and validation (75%). Quantile regression forest model was used to predict soil properties and estimate model uncertainty. The results of the validation of the predictions of the random forest model showed that the value of R2 is 0.47, 0.38, and 0.27 for sand, silt, and clay, respectively and the RMSE value was determined for sand (8.61), silt (8.25), and clay (8.1). These results state that the predictor variables explain the sand changes well, but the ability of the random forest model to predict sand is less than the silt and clay variables. Also, the results showed that the uncertainty in variations of available data is about 1/4 the total uncertainty and uncertainty in the model is about 3/4 of the total uncertainty. Since the uncertainty of the model takes a larger share of the total uncertainty, in order to reduce the total uncertainty must be carefully chosen machine learning models.

Keywords

Main Subjects

References

References
Akpa, S. I. C., Odeh, I. O. A., Bishop, T. F. A. and Hartemink, A. E. 2014. Digital mapping of soil particle-size fractions for Nigeria. Soil Science Society of America Journal, 78: 1953–1966.
Behrens, T., Schmidt, K., and Scholten, T .2008. An approach to removing uncertainties in nominal environmental covariates and soil class maps. In: Hartemink A., McBratney A. and Mendoca-Santos, M.L. (Eds.), Digital Soil Mapping with Limited Data. Springer, pp. 213–224.
Bishop T.F.A., Minasny B. and McBratney A.B. 2006. Uncertainty analysis for soil-terrain models. International Journal of Geographical Information Science, 20(2): 117–134.
Bouyoucos G.J. (1962). Hydrometer method improved for making particle size analyses of soils. Agronomy Journal, 54(5): 464-465
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32
Cressie N. and Kornak J. 2003. Spatial statistics in the presence of location error with an application to remote sensing of the environment. Statistical Science, 18(4): 436–456.
Conrad O., Bechtel B., Bock M., Dietrich H., Fischer E., Gerlitz L., Wehberg J., Wichmann V. and Böhner, J. 2015. System for Automated Geoscientific Analyses (SAGA) v. 2.1.4. Geoscientific Model Development Discussions, (8): 2271-2312.
Gomez C., Drost, A.P.A. and Roger, J.M. 2015. Analysis of the uncertainties affecting predictions of clay contents from VNIR/SWIR hyperspectral data. Remote Sensing of Environment, 156: 58-70.
Heuvelink G.B.M. 2014. Uncertainty quantification of Global Soil Map products. In: Global Soil Map Basis of the global spatial soil information system. Arrouays D., McKenzie N.J., Hempel J., Richer de-Forges A.C. and McBratney A.B., (eds). 335-340.
Heuvelink G.B.M. 1998. Error propagation in environmental modelling with GIS. Taylor and Francis, London. 144 pp.
Jensen, J.R. 2005. Introductory digital image processing: A remote sensing perspective, 3rd edition. Pearson Prentice Hall. 296-300, 301-321, 315-316.
Khosravani P., Baghernejad M., Moosavi A.A. and FallahShams S.R. 2024. Digital Mapping of Soil Texture Particles with Machine Learning Models and Environmental Covariates. Journal of Water and Soil, 37(6): 923-942. (In Persian)
Lagacherie P., McBratney A.B. and Volz, M. 2007. Digital soil mapping: An introductory perspective. Elsevier, Amsterdam.
Macmillan R.A. Jones, R.K., & McNabb, D.2004. Defining a hierarchy of spatial entities for environmental analysis and modeling using digital elevation models (DEMs). Computers, Environment and Urban Systems, 28:175-200.
Meinshausen N. 2006. Quantile regression forests. Journal of Machine Learning Research, 7: 983-999.
Nikou M. and Tziachris, P. 2022. Prediction and Uncertainty Capabilities of Quantile Regression Forests in Estimating Spatial Distribution of Soil Organic Matter. ISPRS International Journal of Geo-Information, 11: 130.
Poggio L., Gimona A. and Mark B. 2016. Bayesian spatial modelling of soil properties and their uncertainty: The example of soil organic matter in Scotland using R-INLA. Geoderma, 277: 69 - 82.
Ramcharan A., Hengl T., Nauman T., Brungard C., Waltman S., Wills S. and Thompson J. 2017. Soil Property and Class Maps of the Conterminous US at 100-meter Spatial Resolution based on a Compilation of National Soil Point Observations and Machine Learning. Soil Science Society of America Journal, 82(1):186-201
Rouse J.W., Hass R.H.J., Schell A. and Deering D.W. 1973. Monitoring vegetation systems in the Great Plains with ERTS. 3th ERTS Symposium. 10-14 Dec.Washington, DC., USA
Szatmári G. and Pásztor L. 2019. Comparison of various uncertainty modelling approaches based on geostatistics and machine learning algorithms. Geoderma, 337: 1329-1340.
Saurette D., Zhang Y., Ji W., Huq Easher T., Li H., Shi Z., Adamchuk V. and Biswas A. 2020. Three-dimensional digital soil mapping of multiple soil properties at a field-scale using regression kriging. Geoderma, 366: 42-53.
Soil Science Division Staff. 2017. Soil survey manual. C. Ditzler, K. Scheffe, and H.C. Monger (Eds.). USDA Handbook 18. Government Printing Office, Washington, D.C.
Stumpf F., Schmidt K., Goebes P., Behrens T., Schönbrodt-Stitt S., Wadoux A., Xiang W. and Scholten T. 2017.Uncertainty-guided sampling to improve digital soil maps. Catena, 153: 30–38.
Teixeira D., Marques J., Silva S.D., Vasconcelos V., de Carvalho J.O., Martins E. and Pereira G. 2018. Mapping units based on spatial uncertainty of magnetic susceptibility and clay content. Catena, 164.
Theres L. and Rs S. 2022. Prediction of Soil Properties Using Quantile Regression Forest Machine Learning Algorithm – A Case Study of Salem and Rasipuram Block, Tamil Nadu, India. International Journal of Environment and Climate Change, 2530-2553.
Wadoux A.M.J.C., Minasny B. and McBratney A.B. 2020. Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science, 210: 33-59.
Wang D. Wang P., Cong W., & Wang P.2022. Calibrating probabilistic predictions of quantile regression forests with conformal predictive systems. Pattern Recognition Letters,156:2-3
Xiao J., Shen Y., Tateishi R. and Bayaer W. 2006. Development of topsoil grain size index for monitoring desertification in arid land using remote sensing. International Journal of Remote Sensing, 27: 2411–2422.
Applied Soil Research
Volume 13, Issue 2 - Serial Number 2
September 2025
Pages 1-16

Files

History

  • Receive Date: 30 July 2024
  • Revise Date: 08 December 2024
  • Accept Date: 11 December 2024

Share

How to cite

Statistics