Application of Machine Learning Models in Spatial Estimation of Soil Phosphorus and Potassium in Some Parts of Abyek Plain

Document Type : Research Paper

Authors

1 Ph.D. Student, Soil Science and Engineering Department, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

2 Professor, Soil Science and Engineering Department, Faculty of Agricultural Engineering and Technology, University College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

3 Professor, Agricultural Machinery Engineering Department, Faculty of Agricultural Engineering and Technology, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, Iran

4 Professor, Earth and Life Institute (ELI), Universite catholique de Louvain (UCL), Louvain-la-Neuve, Belgium

Abstract

Modeling and mapping of plants nutrient elements in soil has importance in increasing the productivity of agriculture and achieving sustainable development. The aim of this research was to prepare digital maps of two nutrients, namely, available phosphorus (Pav) and exchangeable potassium (Kex) using machine learning models (MLM) i.e., random forest (RF), cubist (CB), support vector regression (SVR) and k-nearest neighborhood (k-NN) at two depths of 15-30 and 0-15 cm in a part of Abyek Plain. In this regard, 278 soil profiles were dug, sampled from the desired horizons, and samples were analyzed. MLM performance was implemented by 10-fold cross-valuation. The modeling results demonstrated that the RF model had the highest accuracy and minimum error compared to the other three models in spatial estimation of available Pav and Kex at the two studied depths. According to the results, for Pav at a depth of 0-15 cm, CCC statistics values of 0.84, 0.74, 0.48 and 0.35 and NRMSE values of 0.38, 0.54, 0.70, and 0.80 belonged to RF, CB, k-NN, and SVR, respectively. For Kex at the same depth, CCC values were 0.82, 0.72, 0. 70, 0.47 and NRMSE 0.25, 0.34, 0.36 and 0.45, by RF, CB, SVR, and k-NN models, respectively. Similar results were obtained for 15-30 cm layer. The relative importance of environmental variables showed that soil covariates had a more effective role in the spatial estimation of Pav and Kex than other environmental variables. According to the estimated maps of the two elements and the predominance of agricultural land uses, major parts of the area are Pav deficient based on standard amounts. Therefore, to increase productivity and improve management of soil fertility, use of phosphate fertilizers is recommended under the supervision of soil experts.
 

Keywords

Main Subjects

References

  1. خزائی، ا.، ع. بستانی و ن. دواتگر. 1396. تغییرات مکانی نیتروژن، فسفر و پتاسیم و ظرفیت تبادل کاتیونی خاک در اراضی شرکت کشت و صنعت شریف‌آباد قزوین. پژوهش‌های خاک (علوم خاک و آب), 31 (2), 195-213.
  2. زارعیان، غ ر.، م. ه. فرپور، م. حجازی و ا. جعفری. 1396. ارتباط شکل‌های مختلف پتاسیم با خصوصیات فیزیکو شیمیایی و کانی‌شناسی رسی خاک‌های دشت قره‌باغ در استان فارس. پژوهش‌های خاک، 31, (2), 315-327.
  3. طاعتی، ع.، ف. سرمدیان، ح ر. متقیان و س. ر. موسوی. 1399. پهنه‌بندی برخی ویژگی‌های سطحی و عمقی پروفیل خاک با استفاده از تکنیک زمین‌آمار در بخشی از اراضی دشت قزوین. انسان و محیط‌زیست، 18(1), 67-81.‎
  4. شعبانی، ح. و م. دلاور. 1395. ارزیابی تغییرات مکانی عناصر غذایی پرمصرف در اراضی دانشگاه زنجان. پژوهش‌های کاربردی زراعی (پژوهش و سازندگی)، 29(110), 75-82.
  5. موسوی، س.ر.، ف. سرمدیان و ا. رحمانی. 1398. مدل‌سازی و پیش‌بینی مکانی کلاس خاک با استفاده از الگوریتم یادگیری رگرسیون درختی توسعه‌یافته و جنگل-های تصادفی در بخشی از اراضی دشت قزوین. تحقیقات آب‌ و خاک ایران (علوم کشاورزی ایران)، 50 (10)، 2525-2538.
  6. علمداری، پ.، و. کامرانی و م. ح. محمدی. 1394. ارتباط بین اشکال مختلف پتاسیم و کانی‌های رسی در واحدهای فیزیوگرافی متفاوت. آب ‌و خاک، 29 (6)، 1578- 1589.
  7. Adhikari, K., P.R., Owens, A.J., Ashworth, T.J., Sauer, Z., Libohova, J.L. Richter., & M., Miller. 2018. Topographic controls on soil nutrient variations in a silvopasture system. Agrosystems, Geosciences & Environment, 1(1:(1-15.
  8. Bogunovic, I., P., Pereira, & C., Brevik. 2017. Spatial distribution of soil chemical properties in an organic farm in Croatia. Science of the Total Environment, 584:535-545.
  9. Carter, M.R. &G., Gregorich. 2007. Soil sampling and methods of analysis. CRC press.
  10. Gao, L., M., Huang, W., Zhang, L., Qiao, G., Wang, & , Zhang. 2021. Comparative Study on Spatial Digital Mapping Methods of Soil Nutrients Based on Different Geospatial Technologies. Sustainability, 13(6): p.3270.
  11. Gao, X.S., X.I.A.O., Yi, L.J., Deng, Q.Q., LI, C.Q., Wang, L.I., Bing, O.P., Deng, & E.N.G., Min. 2019. Spatial variability of soil total nitrogen, phosphorus and potassium in Renshou County of Sichuan Basin, China. Journal of Integrative Agriculture, 18(2):279-289.
  12. Hashemi, S.S, & , Abbaslou. 2016. Potassium reserves in soils with arid and semi-arid climate in southern Iran: a perspective based on potassium fixation. Iran Agricultural Research, 35(2): 88-95.
  13. Hengl, T., M., Nussbaum, M.N., Wright, G.B., Heuvelink, & , Gräler. 2018. Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. Peer Journal, 6:5518.
  14. Hengl, T., M.A., Miller, J., Križan, K.D., Shepherd, A., Sila, M., Kilibarda, O., Antonijević, L., Glušica, A., Dobermann, S.M., Haefele, & S.P., McGrath. 2021. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Scientific Reports, 11(1):1-18.
  15. Khaledian, Y. & A., Miller. 2020. Selecting appropriate machine learning methods for digital soil mapping. Applied Mathematical Modelling, 81, 401-418.
  16. Kingsley, J., S.O., Lawani, A.O., Esther, K.M., Ndiye, O.J., Sunday, & , Penizek. 2019. Predictive Mapping of Soil Properties for Precision Agriculture Using Geographic Information System (GIS) Based Geostatistics Models. Modern Applied Science, 13(10): 60-77.
  17. Kuhn, M. & , Johnson. 2013. Applied predictive modeling. New York: Springer, Vol. 26:13.
  18. Ludwick, A.E., L.C., Bonezkowski, C.A., Bruice, K.B., Campbell, R.M., Millaway, S.E., Petrie, I.L., Phillips, & J.J., Smith. 1998. Western fertilizer handbook.
  19. Ma, Y., B., Minasny, & , Wu. 2017. Mapping key soil properties to support agricultural production in Eastern China. Geoderma Regional, 10:144-153.
  20. Matinfar, H.R., Z., Maghsodi, S.R., Mousavi, & , Rahmani. 2021. Evaluation and Prediction of Topsoil organic carbon using Machine learning and hybrid models at a Field-scale. Catena, 202 ,105258.
  21. Mendes, W.D.S., J.A.M., Dematte, D.F.U., Salazar, & T.A., Amorim. 2020. Geostatistics or machine learning for mapping soil attributes and agricultural practices. Revista Ceres, 67(4):330-336.
  22. Minasny, B. & B., McBratney. 2016. Digital soil mapping: A brief history and some lessons. Geoderma, 264:301-311.
  23. Oliver, M. A, & , Webster. 2014. A tutorial guide to geostatistics: Computing and modelling variograms and kriging. Catena, 113: 56-69.
  24. Padarian, J., B., Minasny, & B., McBratney. 2020. Machine learning and soil sciences: A review aided by machine learning tools. Soil, 6(1):35-52.
  25. Parsaie, F., A.F., Firouzi, S.R., Mousavi, A., Rahmani, M.H. Sedri, & , Homaee. 2021. Large-scale digital mapping of topsoil total nitrogen using machine learning models and associated uncertainty map. Environmental Monitoring and Assessment, 193(4): 1-15.
  26. Staff, S.S., 2014. Keys to Soil Taxonomy, 12th Edn Washington. DC: Natural Resources Conservation Service, United States Department of Agriculture.
  27. Suleymanov, A., E., Abakumov, R., Suleymanov, I., Gabbasova, & , Komissarov. 2021. The Soil Nutrient Digital Mapping for Precision Agriculture Cases in the Trans-Ural Steppe Zone of Russia Using Topographic Attributes. ISPRS International Journal of Geo-Information, 10(4): 243.
  28. Srisomkiew, S., M., Kawahigashi, & , Limtong. 2021. Digital mapping of soil chemical properties with limited data in the Thung Kula Ronghai region, Thailand. Geoderma, 389, 114942.
  29. Taghizadeh-Mehrjardi, R, K., Schmidt, N., Toomanian, B., Heung, T., Behrens, A.H., Mosavi, S. S., Band, A., Amirian-Chakan, A., Fathabadi, & T., Scholten. 2021. Improving the spatial prediction of soil salinity in arid regions using wavelet transformation and support vector regression models. Geoderma, 383:114793.
  30. Tu, C., T., He, X., Lu, Y., Luo, & , Smith. 2018. Extent to which pH and topographic factors control soil organic carbon level in dry farming cropland soils of the mountainous region of Southwest China. Catena, 163: 204-209.
  31. Wang, J., B., Fu, Y., Qiu, & , Chen. 2001. Soil nutrients in relation to land use and landscape position in the semi-arid small catchment on the loess plateau in China. Journal of Arid Environments, 48(4):537-550.
  32. Wang, S., X., Jin, K., Adhikari, W., Li, M., Yu, Z., Bian, & , Wang. 2018. Mapping total soil nitrogen from a site in northeastern China. Catena, 166:134-146.
  33. Wilding, L.P. 1985. Spatial variability: its documentation, accomodation and implication to soil surveys. In Soil spatial variability, Las Vegas NV, 166-194.
  34. Zhang, B., D.A., MacLean, R.C., Johns. & S., Eveleigh. 2018. Effects of hardwood content on balsam fir defoliation during the building phase of a spruce budworm outbreak. Forests, 9(9) :530.
  35. Zhou, T., Y., Geng, J., Chen, C., Sun, D., Haase, & , Lausch. 2019. Mapping of Soil Total Nitrogen Content in the Middle Reaches of the Heihe River Basin in China Using Multi-Source Remote Sensing-Derived Variables. Remote Sensing. 11(24): 2934.
Iranian Journal of Soil Research
Volume 35, Issue 4
February 2022
Pages 397-411

Files

Share

How to cite

Statistics