Modeling Spatial Distribution of Soil Classes Using Machine Learning Algorithms in Some Parts of Zanjan Provice

Document Type : Research Paper

Authors

1 department of soil science, zanjan univercity,

2 Professor of agrology group, Faculty of agriculture. Zanjan university.

3 Soil and Water Research Institute, Agricultural Research, Education and Extension Organization, Karaj, Iran

4 Researcher, Department of Soil Science, Faculty of Agriculture, University of Tehran

10.22092/ijsr.2023.361649.698

Abstract

Digital soil mapping (DSM), which uses machine learning (ML) algorithms and environmental covariates, is used worldwide for predicting soil properties and classes, due to being time-effective and cost-saving. This research was conducted to compare ML models and their efficiency in predicting the spatial distribution of soil subgroups in part of Zanjan Province. For this purpose, sampling was carried out through a regular pattern with 500 meters intervals, and 148 soil profile samples were randomly collected and classified. The soils of the region at the subgroup level were categorized in five classes, including Typic Calcixerepts, Typic Haploxerepts, Gypsic Haploxerepts, Typic Xerorthents, and Lithic Xerorthents. Environmental covariates included geomorphological and geological maps, digital elevation model (DEM), and remote sensing (RS), selected by principal component analysis (PCA) and expert knowledge approaches. Fifty-seven environmental variables were extracted as representatives of soil forming factors. Modeling of the soil-landscape relationship was performed using three algorithms, namely, multinomial logistic regression (MNLR), random forest (RF), and boosted regression tree (BRT) in Rstudio software. The results of evaluation metrics such as overall accuracy and Kappa index were 65% and 0.32 for the RF algorithm, 60% and 0.35 for the BRT, and 65% and 0.41 for the MNLR. Referring to the importance of environmental variables, results showed that the four factors of valley depth, LS-Factor, channel network distance, and multiple resolution ridge top flatness index (MRRTF) were the most important variables in MNLR algorithm. Also, the results of two statistics of user’s accuracy (UA) and producer’s accuracy (PA) showed that the MNLR model performed better in the spatial prediction of soil at subgroup level. Soil classes with higher frequency had higher accuracy. The results of the prediction accuracy of soil classes showed that the model prediction is more accurate for the more frequent types in the observations.

Keywords

Main Subjects


  1. سالنامه آماری استان زنجان 1398، «1- سرزمین و آب‌وهوا»، سازمان آمار کشور.
  2. عباس زاده افشار، ف.، و ایوبی، ش.، و جعفری، ا. 1397. پیش‌بینی مکانی گروه بزرگ‌های خاک با استفاده از مدل‌های رگرسیونی و درخت تصمیم در منطقه جنوب شرق ایران. مهندسی زراعی (مجله علمی کشاورزی), 41(2): 133-146.
  3. فاتحی، ش.، محمدی، ج.، صالحی، م.، مؤمنی، ع.، تومانیان، ت.، جعفری، ا. 1394. انبوهش­زدائی مکانی نقشه­ی سنتی خاک با استفاده از رگرسیون لاجیستیک چند کلاسه و درختان طبقه­بندی) مطالعه موردی: زیر حوضه آبخیز مرک در استان کرمانشاه. چهاردهمین کنگره علوم خاک ایران، 28-30 شهریور، رفسنجان، ایران، 208-213.
  4. فرزام نیا، پ.، منافی، ش.، ممتاز، ح.ر. 1394. تشکیل و تحول خاک‌های متشکله بر روی رسوبات کواترنر در بخشی از دشت ارومیه. مجله مدیریت خاک و تولید پایدار، 5(2): 93-111.
  5. مصلح، ز.، صالحی، م. ح.، و جعفری، ع. 1396. نقشه‌برداری رقومی کلاس‌های خاک در سطوح مختلف رده‌بندی آمریکایی با استفاده از مدل رگرسیون درختی توسعه‌یافته در دشت شهرکرد. چهاردهمین کنگره علوم خاک ایران، 28-30 شهریور، رفسنجان، ایران، 347-343.
  6. مقصودی ز، رستمی‌نیا م، فرامرزی م، کشاورزی ع، رحمانی ا، موسوی س.ا. نقشه‌برداری رقومی کلاس فامیل خاک با استفاده از رویکرد یادگیری ماشین (مطالعه موردی: اراضی نیمه‌خشک غرب ایران). 1399. مجله علوم آب‌وخاک. ۲۴ (۲): ۱۶۳-۱۵۳.
  7. موسوی، س.، و سرمدیان، ف.، و رحمانی، ا. 1398. مدل‌سازی و پیش‌بینی مکانی کلاس خاک با استفاده از الگوریتم یادگیری رگرسیون درختی توسعه‌یافته و جنگل­های تصادفی در بخشی از اراضی دشت قزوین. تحقیقات آب‌وخاک ایران (علوم کشاورزی ایران), 50(10): 2525-2538.
  8. موسسه تحقیقات خاک و آب. ١٣89. مطالعات پژوهشی مکان­یابی، خاک­شناسی و ارزیابی اراضی برای احداث باغات در استان زنجان. نشریه شماره 1547، 364 صفحه. کرج. ایران.
  9. Abeare, S. 2009. Comparisons of boosted regression tree, GLM and GAM performance in the standardization of yellowfin tuna catch-rate data from the Gulf of Mexico lonline [sic] fishery.
  10. Adhikari, K., Hartemink, A.E., Minasny, B., Bou Kheir, R., Greve, M.B., and Greve M.H. 2014. Digital mapping of soil organic carbon contents and stocks in Denmark. PLoS ONE, 9:1-13.
  11. Artieda, O., Herrero, J., and Drohan, P. J. 2006. Refinement of the differential water loss method for gypsum determination in soils. Soil Science Society of America Journal, 70(6): 1932-1935.
  12. Behrens, T., Schmidt, K., MacMillan, R. A., and Viscarra Rossel, R. A. 2018. Multi-scale digital soil mapping with deep learning. Scientific reports, 8(1): 1-9.
  13. Bouyoucos, G. J. 1962. Hydrometer method improved for making particle size analyses of soils 1. Agronomy journal, 54(5): 464-465.
  14. Breiman, L. 2001. Random forests. Machine learning, 45(1): 5-32.
  15. Breiman, L., and Cutler, A. 2004. Random Forests. Department of Statistics, University of Berkeley.
  16. Brungard, C. W., Boettinger, J. L., Duniway, M. C., Wills, S. A., and Edwards Jr, T. C. 2015. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma, 239: 68-83.
  17. Congalton, R. G. 1991. A review of assessing the accuracy of classifications of remotely sensed data. Remote sensing of environment, 37(1): 35-46.
  18. Debella-Gilo, M., and Etzelmüller, B. 2009. Spatial prediction of soil classes using digital terrain analysis and multinomial logistic regression modeling integrated in GIS: Examples from Vestfold County, Norway. Catena, 77(1): 8-18.
  19. Elith, J., Leathwick, J. R., and Hastie, T. 2008. A working guide to boosted regression trees. Journal of animal ecology, 77(4): 802-813.
  20. Elnaggar, A. A. 2007. Development of predictive mapping techniques for soil survey and salinity mapping. Oregon State University.
  21. Evans, D.L., Janes‐Bassett, V., Borrelli, P., Chenu, C., Ferreira, C.S., Griffiths, R.I., Kalantari, Z., Keesstra, S., Lal, R., Panagos, P. and Robinson, D.A. 2022. Sustainable futures over the next decade are rooted in soil science. European Journal of Soil Science, 73(1):
  22. Fan, N.Q., Zhao, F.H., Zhu, L.J., Qin, C.Z. and Zhu, A.X. 2022. Digital soil mapping with adaptive consideration of the applicability of environmental covariates over large areas. International Journal of Applied Earth Observation and Geoinformation, 113:102986.
  23. Garg, K.K., Anantha, K.H., Nune, R., Akuraju, V.R., Singh, P., Gumma, M.K., Dixit, S. and Ragab, R. 2020. Impact of land use changes and management practices on groundwater resources in Kolar district, Southern India. Journal of Hydrology: Regional Studies, 31: 100732.
  24. Hartemink, A. E., A. McBratney and M. d. L. Mendonca-Santos. 2008. Digital soil mapping with limited data.
  25. Helfenstein, A., Mulder, V.L., Heuvelink, G.B. and Okx, J.P. 2022. Tier 4 maps of soil pH at 25 m resolution for the Netherlands. Geoderma, 410:115659.
  26. Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B., and Gräler, B. 2018. Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ, 6, e5518.
  27. Hengl, T., Toomanian, N., Reuter, H., and Malakouti, M.J. 2007. Methods to interpolate soil categorical variables from profile observations: Lessons from Iran. Geoderma, 140: 417–427.
  28. A., Finke P.A, Van deWauw, J., Ayoubi, S., and Khademi, H. 2012. Spatial prediction of USDA-great soil groups in the arid Zarand region, Iran: comparing logistic regression approaches to predict diagnostic horizons and soil types. EuropianJournal Soil Science, 63(2): 284–298.
  29. Jafari, A., Ayoubi, S., Khademi, H., Finke, P. A., and Toomanian, N. 2013. Selection of a taxonomic level for soil mapping using diversity and map purity indices: a case study from an Iranian arid region. Geomorphology, 201:86-97.
  30. Jenny, H. 1994. Factors of soil formation: a system of quantitative pedology. Courier Corporation.
  31. Jensen, J. R. 1996. Introductory digital image processing: a remote sensing perspective (No. Ed. 2). Prentice-Hall Inc.
  32. Jeune, W., Francelino, M. R., Souza, E. D., Fernandes Filho, E. I., & Rocha, G. C. 2018. Multinomial logistic regression and random forest classifiers in digital mapping of soil classes in western Haiti. Revista Brasileira de Ciência do Solo, 42.
  33. Kempen, B., Brus, D. J., Heuvelink, G. B., and Stoorvogel, J. J. 2009. Updating the 1: 50,000 Dutch soil map using legacy soil data: A multinomial logistic regression approach. Geoderma, 151(3-4): 311-326.
  34. Kirkham, M. B. 2014. Principles of soil and plant water relations. Academic Press.
  35. Kleinbaum, A. M. 2018. Reorganization and tie decay choices. Management Science, 64(5): 2219-2237.
  36. Kuhn, M., and Johnson, K. 2013. Applied predictive modeling (Vol. 26, p. 13). New York: Springer.
  37. Lagacherie, P., McBratny, A.B. and Volts, M. 2007. Digital soil mapping: An introductory perspective. Developments in soil science 31(Elsevier, Amsterdam).
  38. Lanyon, L. E., and Heald, W. R. 1983. Magnesium, calcium, strontium, and barium. Methods of Soil Analysis: Part 2 Chemical and Microbiological Properties, 9: 247-262.
  39. Liang, P., Qin, C.-Z., Zhu, A.-X., Hou, Z.-W., Fan, N.-Q., Wang, Y.-J. 2020. A case-based method of selecting covariates for digital soil mapping. Journal of Integrative Agriculture 19: 2–11
  40. Ma, Y., Minasny, B., Malone, B. P., and Mcbratney, A. B. 2019. Pedology and digital soil mapping (DSM). European Journal of Soil Science, 70(2): 216-235.
  41. Mallah, S., Delsouz Khaki, B., Davatgar, N., Scholten, T., Amirian-Chakan, A., Emadi, M., Kerry, R., Mosavi, A.H. and Taghizadeh-Mehrjardi, R., 2022. Predicting Soil Textural Classes Using Random Forest Models: Learning from Imbalanced Dataset. Agronomy, 12(11): 2613.
  42. Marchetti, A., Piccini, C., Santucci, S., Chiuchiarelli, I., and Francaviglia, R. 2011. Simulation of soil types in Teramo province (Central Italy) with terrain parameters and remote sensing data. Catena, 85(3): 267-273.
  43. Markus, E., and Merkli, C. 2007. Weathering, mineralogical evolution and soil organic matter along aHolocene soil toposequence developed on carbonate-rich materials. Geomorphology 97: 675-696.
  44. McBratney, A. B., Santos, M. M., and Minasny, B. 2003. On digital soil mapping. Geoderma, 117(1-2): 3-52.
  45. McBratney, A., de Gruijter, J., and Bryce, A. 2019. Pedometrics timeline. Geoderma, 338: 568-575.
  46. Olaya, V. 2004. A gentle introduction to SAGA GIS. The SAGA user group.
  47. Padarian, J., Minasny, B., and McBratney, A. B. 2020. Machine learning and soil sciences: A review aided by machine learning tools. Soil, 6(1): 35-52.
  48. Pelegrino, M. H. P., Silva, S. H. G., Menezes, M. D. D., Silva, E. D., Owens, P. R., and Curi, N. 2016. Mapping soils in two watersheds using legacy data and extrapolation for similar surrounding areas. Ciência e Agrotecnologia, 40:534-546.
  49. Perry Jr, C. R., & Lautenschlager, L. F. 1984. Functional equivalence of spectral vegetation indices. Remote sensing of environment, 14(1-3): 169-182.
  50. Richards, L.A. 1954. Diagnosis and improvement of saline and alkali soils (Vol. 78, No. 2, p. 154). LWW.
  51. Schaetzl, R. J., and Thompson, M. L. 2015. Soils. Cambridge university press.
  52. Scull, P., Franklin, J., and Chadwick, O.A. 2005. The application of classification tree analysis to soil type prediction in a desert landscape. Ecological Modelling, 181: 1–15.
  53. Soil science division staff. 2017. "Soil survey manual". USDA Handbook 18.120-131
  54. Staff, S. S. 2014. Keys to soil taxonomy. United States Department of Agriculture: Washington, DC, USA.
  55. Sumner, M. E., and Miller, W. P. 1996. Cation exchange capacity and exchange coefficients. Methods of soil analysis: Part 3 Chemical methods, 5:1201-1229.
  56. Santra, P., Meena, H.M. and Yadav, O.P. 2021. Spatial and temporal variation of photosynthetic photon flux density within agrivoltaic system in hot arid region of India. Biosystems Engineering, 209:74-93.
  57. Taghizadeh-Mehrjardi, R., Minasny, B., Sarmadian, F., and Malone, B. P. 2014. Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213:15-28.
  58. Taghizadeh-Mehrjardi, R., Nabiollahi, K., Minasny, B., and Triantafilis, J. 2015. Comparing data mining classifiers to predict spatial distribution of USDA-family soil groups in Baneh region, Iran. Geoderma, 253: 67-77.
  59. Taghizadeh-Mehrjardi, R., Mahdianpari, M., Mohammadimanesh, F., Behrens, T., Toomanian, N., Scholten, T. and Schmidt, K., 2020. Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran. Geoderma, 376, p.114552.
  60. Tan, W. F., Zhang, R., Cao, H., Huang, C. Q., Yang, Q. K., Wang, M. K., and Koopal, L. K. 2014. Soil inorganic carbon stock under different soil types and land uses on the Loess Plateau region of China. Catena, 121: 22-30.
  61. Vaysse, K., and Lagacherie, P. 2015. Evaluating digital soil mapping approaches for mapping Global Soil Map soil properties from legacy data in Languedoc-Roussillon (France). Geoderma Regional, 4: 20-30.
  62. Walkley, A., and Black, I. A. 1934. An examination of the Degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil science, 37(1): 29-38.
  63. Wiesmeier, M., Urbanski, L., Hobley, E., Lang, B., von Lützow, M., Marin-Spiotta, E., van Wesemael, B., Rabot, E., Ließ, M., Garcia-Franco, N. and Wollschläger, U. 2019. Soil organic carbon storage as a key function of soils-A review of drivers and indicators at various scales. Geoderma, 333: 149-162.
  64. Xiao-Lin, S. U. N., Yu-Guo, Z. H. A. O., ZHANG, G. L., Sheng-Chun, W. U., Yu-Bon, M. A. N., and Ming-Hung, W. O. N. G. 2011. Application of a digital soil mapping method in producing soil orders on mountain areas of Hong Kong based on legacy soil data. Pedosphere, 21(3): 339-350.
  65. Yang, l., Jiao, Y., Fahmy, S., Zhu, A-X., Hann, S., Burt, J. E., and Qi, F. 2011. Updating conventional
    soil maps through digital soil mapping. Soil Science Society of America Journal AbstractPedology,75(3): 1044-1053
  66. 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 (12): 2871–2885.
  67. Zinck, J.A., Metternicht, G., Bocco, G. and Del Valle, H.F. eds. 2015. Geopedology: An integration of geomorphology and pedology for soil and landscape studies. Springer.