Digital soil mapping of soil subgroup class information in Coimbatore district using decision tree approach
DOI:
https://doi.org/10.14719/pst.5295Keywords:
decision tree, digital soil mapping, expert system, soil taxonomy, Tamil NaduAbstract
The study aimed to evaluate the effectiveness of Digital Soil Mapping (DSM) compared to traditional soil mapping methods, which can help implementing precise near-real-time smart agricultural applications. Conventional soil surveys, while informative, often lack detail and are labour-intensive. DSM addresses these limitations by integrating soil data with environmental covariates and classification algorithms. Four hundred forty soil profile data points were collected from various sources and grouped according to the USDA Soil Taxonomy at the soil subgroup level. Utilizing Landsat 8 satellite data and 33 environmental covariates, the decision tree algorithm generated 56 rules to predict soil classes. Key influencing factors identified include agro-climatic zones, physiography, mean annual minimum temperature, the green wavelength region of spectral data, rainfall, and geology. The model was trained on 348 data points and validated on 92 data points, achieving a classification accuracy of 79.35% and a Kappa coefficient of 0.78, indicating high reliability. The study concludes that DSM is a viable alternative to conventional soil mapping methods, primarily using decision tree algorithms. It demonstrates that the accuracy of DSM can be significantly enhanced by incorporating a larger number of soil profile observations and relevant environmental covariates. The expert system approach provides a more detailed and up-to-date understanding of soil distribution, crucial for agricultural planning and natural resource management in the Coimbatore district, Western Tamil Nadu.
Downloads
References
Jenny H. Factors of soil formation: A system of quantitative pedology. Dover Publications, New York. 1941;p. 281. https://doi.org/10.1097/00010694-194111000-00009
Lufega SM, Msanya BM. Pedological characterization and soil classification of selected soil units of Morogoro district, Tanzania. Int J Plant Soil Sci. 2017;16(1):1-12. https://doi.org/10.9734/IJPSS/2017/32681
Rossiter DG, Bouma J. A new look at soil phenoforms–Definition, identification, mapping. Geoderma. 2018;314:113-21. https://doi.org/10.1016/j.geoderma.2017.11.002
Eswaran H, Ahrens R, Rice TJ, Stewart BA. Soil classification: A global desk reference. CRC Press. 2002. https://doi.org/10.1201/9781420040364
Kempen B. Updating soil information with digital soil mapping. Wageningen University and Research; 2011.
Zhu AX, Hudson B, Burt J, Lubich K, Simonson D. Soil mapping using GIS, expert knowledge and fuzzy logic. Soil Sci Soc Am J. 2001;65(5):1463-72. https://doi.org/10.2136/sssaj2001.6551463x
Lagacherie P. Digital soil mapping: A state of the art. In: Hartemink AE, McBratney A, Mendonça-Santos Md, editors. Digital soil mapping with limited data. Springer, Dordrecht; 2008. 3-14. https://doi.org/10.1007/978-1-4020-8592-5_1
Carré F, McBratney AB, Mayr T, Montanarella L. Digital soil assessments: Beyond DSM. Geoderma. 2007;142(1-2):69-79. https://doi.org/10.1016/j.geoderma.2007.08.015
McBratney AB, Santos MLM, Minasny B. On digital soil mapping. Geoderma. 2003;117(1-2):3-52. https://doi.org/10.1016/S0016-7061(03)00223-4
Ma Y, Minasny B, Malone BP, McBratney AB. Pedology and digital soil mapping (DSM). Eur J Soil Sci. 2019;70(2):216-35. https://doi.org/10.1111/ejss.12790
Skidmore AK, Watford F, Luckananurug P, Ryan PJ. An operational GIS expert system for mapping forest soils. Photogramm Eng Remote Sensing. 1996;62(5):501-11.
Massawe BHJ, Subburayalu SK, Kaaya AK, Winowiecki L, Slater BK. Mapping numerically classified soil taxa in Kilombero Valley, Tanzania using machine learning. Geoderma. 2018;311:143-48. https://doi.org/10.1016/j.geoderma.2016.11.020
Taghizadeh-Mehrjardi R, Minasny B, McBratney AB, Triantafilis J, Sarmadian F, Toomanian N. Digital soil mapping of soil classes using decision trees in central Iran. CRC Press. 2012;28(2):147-68. https://doi.org/10.1080/15324982.2013.828801
Heung B, Ho HC, Zhang J, Knudby A, Bulmer CE, Schmidt MG. An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma. 2016;265:62-77. https://doi.org/10.1016/j.geoderma.2015.11.014
Goovaerts P. Geostatistics in soil science: State-of-the-art and perspectives. Geoderma. 1999;89(1-2):1-45. https://doi.org/10.1016/S0016-7061(98)00078-0
Lemercier B, Lacoste M, Loum M, Walter C. Extrapolation at regional scale of local soil knowledge using boosted classification trees: A two-step approach. Geoderma. 2012;171:75-84. https://doi.org/10.1016/j.geoderma.2011.03.010
Hengl T, Toomanian N, Reuter HI, Malakouti MJ. Methods to interpolate soil categorical variables from profile observations: Lessons from Iran. Geoderma. 2007;140(4):417-27. https://doi.org/10.1016/j.geoderma.2007.04.022
Ballabio C. Spatial prediction of soil properties in temperate mountain regions using support vector regression. Geoderma. 2009;151(3-4):338-50. https://doi.org/10.1016/j.geoderma.2009.04.022
Hastie T, Tibshirani R, Friedman JH, Friedman JH. The elements of statistical learning: Data mining, inference and prediction: Springer; 2009. https://doi.org/10.1007/978-0-387-84858-7
Hateffard F, Steinbuch L, Heuvelink GBM. Evaluating the extrapolation potential of random forest digital soil mapping. Geoderma. 2024;441:116740. https://doi.org/10.1016/j.geoderma.2023.116740
Dharumarajan S, Hegde R, Janani N, Singh SK. The need for digital soil mapping in India. Geoderma Regional. 2019;16:e00204. https://doi.org/10.1016/j.geodrs.2019.e00204
Lagacherie P, McBratney AB. Spatial soil information systems and spatial soil inference systems: Perspectives for digital soil mapping. Dev Soil Sci. 2006;31:3-22. https://doi.org/10.1016/S0166-2481(06)31001-X
Mosleh Z, Salehi MH, Jafari A, Borujeni EI, Mehnatkesh A. Identifying sources of soil classes variations with digital soil mapping approaches in the Shahrekord plain, Iran. Environ Earth Sci. 2017;76:1-10. https://doi.org/10.1007/s12665-017-7100-0
Bohn MP, Miller BA. Locally enhanced digital soil mapping in support of a bottom-up approach is more accurate than conventional soil mapping and top-down digital soil mapping. Geoderma. 2024;442:116781. https://doi.org/10.1016/j.geoderma.2024.116781
Land Cover database on 1: 50 000 scale. Natural Resources Census Project, LUCMD, LRUMG, RSAA, National Remote Sensing Centre, ISRO, Hyderabad; 2006.
NRSC. Lithology, physiography and soils of Tamil Nadu at 1:50000 scale, Natural resources census project. Hyderabad: National Remote Sensing Centre, ISRO in collaboration with Institute of Remote Sensing and Tamil Nadu Agricultural University; 2012.
Quinlan J. See5 Manual. http://www.rulequest.com/see5-info.html. 1997.
Niblett T. Constructing decision trees in noisy domains. In: The Second European Working Session on Learning. Sigma Press; 1987. p. 67-78.
Congalton RG. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing Environ. 1991;37(1):35-46. https://doi.org/10.1016/0034-4257(91)90048-B
Richards JA. Remote sensing digital image analysis. Springer; 2022. https://doi.org/10.1007/978-3-030-82327-6
Bui EN, Searle RD, Wilson PR, Philip SR, Thomas M, Brough D, et al. Soil surveyor knowledge in digital soil mapping and assessment in Australia. Geoderma Regional. 2020;22:e00299. https://doi.org/10.1016/j.geodrs.2020.e00299
Kumaraperumal R, Pazhanivelan S, Geethalakshmi V, Raj NM, Muthumanickam D, Kaliaperumal R, et al. Comparison of machine learning-based prediction of qualitative and quantitative digital soil-mapping approaches for Eastern districts of Tamil Nadu, India. Land. 2022;11(12):2279. https://doi.org/10.3390/land11122279
Purushothaman NK, Reddy NN, Das BS. National-scale maps for soil aggregate size distribution parameters using pedotransfer functions and digital soil mapping data products. Geoderma. 2022;424:116006. https://doi.org/10.1016/j.geoderma.2022.116006
Taghizadeh-Mehrjardi R, Nabiollahi K, Minasny B, Triantafilis J. Comparing data mining classifiers to predict spatial distribution of USDA-family soil groups in Baneh region, Iran. Geoderma. 2015;253-254:67-77. https://doi.org/10.1016/j.geoderma.2015.04.008
Brungard CW, Boettinger JL, Duniway MC, Wills SA, Edwards Jr TC. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma. 2015;239:68-83. https://doi.org/10.1016/j.geoderma.2014.09.019
Zeraatpisheh M, Ayoubi S, Jafari A, Finke P. Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran. Geomorphology. 2017;285:186-204. https://doi.org/10.1016/j.geomorph.2017.02.015
Landis JR, Koch GG. An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers. Biometrics. 1977;1:363-74. https://doi.org/10.2307/2529786
Marsman BA, de Gruijter JJ. Quality of soil maps: A comparison of soil survey methods in a sandy area. ISRIC. 1986;103.
Giasson E, Sarmento EC, Weber E, Flores CA, Hasenack H. Decision trees for digital soil mapping on subtropical basaltic steep lands. Scientia Agricola. 2011;68:167-74. https://doi.org/10.1590/S0103-90162011000200006
Manteghi S, Moravej K, Mousavi SR, Delavar MA, Mastinu A. Digital soil mapping for soil types using machine learning approaches at the landscape scale in the arid regions of Iran. Adv Space Res. 2024;74(1):1-16. https://doi.org/10.1016/j.asr.2024.04.042
Kshatriya TV, Kumaraperumal R, Pazhanivelan S, Moorthi NR, Muthumanickam D, Ragunath K, et al. Spatial prediction of soil continuous and categorical properties using deep learning approaches for Tamil Nadu, India. Agronomy. 2024;14(11):2707. https://doi.org/10.3390/agronomy14112707
Downloads
Published
Versions
- 28-04-2025 (2)
- 20-04-2025 (1)
How to Cite
Issue
Section
License
Copyright (c) 2025 K Ramalingam, P P Chidambaram, J Mylsamy, N R Moorthi, J Ramasamy, M Dhanaraju, B Kannan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright and Licence details of published articles
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Open Access Policy
Plant Science Today is an open access journal. There is no registration required to read any article. All published articles are distributed under the terms of the Creative Commons Attribution License (CC Attribution 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited (https://creativecommons.org/licenses/by/4.0/). Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
