Abstract
Soil classification is a method of encoding the most relevant information about a given soil, namely its composition and characteristics, in a single class, to be used in areas like agriculture and forestry. In this paper, we evaluate how confidently we can predict soil classes, following the World Reference Base classification system, based on the physical and chemical characteristics of its layers. The Random Forests classifier was used with data consisting of 6 760 soil profiles composed by 19 464 horizons, collected in Mexico. Four methods of modelling the data were tested (i.e., standard depths, n first layers, thickness, and area weighted thickness). We also fine-tuned the best parameters for the classifier and for a k-NN imputation algorithm, used for addressing problems of missing data. Under-represented classes showed significantly worse results, by being repeatedly predicted as one of the majority classes. The best method to model the data was found to be the n first layers approach, with missing values being imputed with k-NN (\(k=1\)). The results present a Kappa value from 0.36 to 0.48 and were in line with the state of the art methods, which mostly use remote sensing data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arrouays, D., McKenzie, N., de Forges, A.R., et al.: GlobalSoilMap: Basis of the Global Spatial Soil Information System. CRC Press, Leiden (2014)
Batjes, N.H., Ribeiro, E., Oostrum, A.v., et al.: Wosis: providing standardised soil profile data for the world. Earth Syst. Sci. Data 9(1), 1–14 (2017)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Brungard, C.W., Boettinger, J.L., Duniway, M.C., et al.: Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma 239, 68–83 (2015)
Congalton, R.G.: A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens. Environ. 37(1), 35–46 (1991)
Crookston, N.L., Finley, A.O.: yaimpute: an R package for KNN imputation. J. Stat. Softw. 23(10), 16 (2008)
Hengl, T., de Jesus, J.M., Heuvelink, G.B., et al.: Soilgrids250m: global gridded soil information based on machine learning. PLoS ONE 12(2), e0169748 (2017)
Hengl, T., Nussbaum, M., Wright, M.N., et al.: Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ 6, e5518 (2018)
Heung, B., Ho, H.C., Zhang, J., et al.: An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma 265, 62–77 (2016)
Hounkpatin, K.O., Schmidt, K., Stumpf, F., et al.: Predicting reference soil groups using legacy data: a data pruning and random forest approach for tropical environment (Dano catchment, Burkina Faso). Sci. Rep. 8(1), 9959 (2018)
IUSS Working Group WRB: World reference base for soil resources 2014, update 2015 international soil classification system for naming soils and creating legends for soil maps. World Soil Resources Reports No. 106, p. 192 (2015)
Jeune, W., Francelino, M.R., de Souza, E., et al.: Multinomial logistic regression and random forest classifiers in digital mapping of soil classes in Western Haiti. Rev. Bras. Cienc. Solo 42, e0170133 (2018)
Meier, M., Souza, E.d., Francelino, M.R., et al.: Digital soil mapping using machine learning algorithms in a tropical mountainous area. Revista Brasileira de Ciência do Solo 42, e0170421 (2018). http://dx.doi.org/10.1590/18069657rbcs20170421
Soil Survey Staff USA: Soil taxonomy: a basic system of soil classification for making and interpreting soil surveys. US Government Printing Office (1999)
Acknowledgments
This research was supported through Fundação para a Ciência e Tecnologia (FCT), through the project grant with reference PTDC/CCI-CIF/32607/2017 (MIMU), as well as through the INESC-ID (UID/CEC/50021/2019) and NOVA LINCS (UID/CEC/04516/2019) multi-annual funding.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Dias, D., Martins, B., Pires, J., de Sousa, L.M., Estima, J., Damásio, C.V. (2019). Soil Classification Based on Physical and Chemical Properties Using Random Forests. In: Moura Oliveira, P., Novais, P., Reis, L. (eds) Progress in Artificial Intelligence. EPIA 2019. Lecture Notes in Computer Science(), vol 11804. Springer, Cham. https://doi.org/10.1007/978-3-030-30241-2_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-30241-2_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30240-5
Online ISBN: 978-3-030-30241-2
eBook Packages: Computer ScienceComputer Science (R0)