مدل‌سازی پراکنش فسفر قابل جذب در خاک‌های سطحی شمال استان خوزستان با استفاده از مدل رگرسیون خطی چندگانه و الگوریتم جنگل تصادفی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه شهید چمران اهواز، خوزستان، ایران

2 گروه محیط زیست، دانشگاه گوئلف، آنتاریو، کانادا

چکیده

اطلاعات اندکی در رابطه با پراکنش مکانی عناصر دخیل در ارزیابی وضعیت حاصلخیزی خاک­های استان خوزستان و به­ویژه فسفر قابل جذب خاک­ها وجود دارد. از این رو، مطالعه حاضر با هدف تعیین مؤثرترین ویژگی­های خاکی کنترل کننده غلظت فسفر قابل جذب در خاک­های شمال استان خوزستان و معرفی مناسب­ترین روش مدل­سازی تغییرات مکانی فسفر قابل جذب با استفاده از روش­های رگرسیون خطی چندگانه و الگوریتم جنگل تصادفی انجام شد. بدین منظور تعداد 250 نمونه مرکب صورت تصادفی به روش ابرمکعب لاتین مشروط در دی­ماه تا بهمن ماه 1399 از خاک­های سطحی (10-0 سانتی­متری) اراضی شمال استان خوزستان تهیه شد. پس از آماده­سازی­های اولیه نمونه­ها، ویژگی­های فیزیکی و شیمیایی آن‌ها با استفاده از روش­های استاندارد آزمایشگاهی اندازه­گیری شد. سپس به­منظور مدل­سازی تغییرات مکانی فسفر قابل جذب خاک­ها، داده­های آزمایشی پس از آماده­سازی­های اولیه با استفاده از مدل­های رگرسیون خطی چندگانه و جنگل تصادفی در محیط نرم­افزار RStudio بررسی شدند. نتایج نشان داد که در 4/32 درصد از نمونه­های مورد بررسی غلظت فسفر قابل جذب کمتر از 5 میلی­گرم بر کیلوگرم است. نتایج ارزیابی مدل­های رگرسیون خطی چندگانه و جنگل تصادفی براساس آماره­های ارزیابی مدل شامل میانگین خطای مطلق (MAE)، جذر میانگین مربعات خطا (RMSE) و ضریب تبیین (R2) در هر سه مرحله­ی آموزش، آزمون و کل داده­ها نشان داد که مدل جنگل تصادفی با توجه به ضرایب تبیین بالاتر و همچنین مقادیر خطای کمتر، تخمین­های بهتر و دقیق­تری را ارائه می­دهد. بررسی اهمیت متغیرهای خاکی در مدل­سازی پراکنش فسفر قابل جذب در هر دو روش رگرسیون خطی چندگانه­ و جنگل تصادفی نشان داد که محتوای کربن آلی خاک­ها بیشترین نقش را در توزیع فسفر قابل جذب در منطقه مطالعاتی داراست. در کل به نظر می­رسد استفاده از مدل­هایی که روابط غیرخطی بین متغیرها را نیز لحاظ می­نمایند در پیش­بینی خصوصیات خاک­ها بهتر است.

کلیدواژه‌ها


عنوان مقاله [English]

Modelling distribution of available phosphorous contents in surface soils of northern Khuzestan Province using linear and random forest modelss

نویسندگان [English]

  • Saeid Hojati 1
  • Mojtaba Norouzi Masir 1
  • Asim Biswas 2
1 Department of Soil Science, ّّFaculty of Agriculture, Shahid Chamran University of Ahvaz, Khuzestan, Iran
2 School of Environmental Sciences, University of Guelph, Ontario, Canada
چکیده [English]

There is little information about the spatial distribution of elements involved in assessing the fertility of soils in Khuzestan province, especially the available phosphorus contents of the soils. Therefore, this study conducted to determine the most effective soil properties controlling the concentration of available phosphorus contents of soils in the north of Khuzestan province and to introduce the most appropriate method for modeling the spatial distribution of available phosphorus contents of the soils analyzed using linear regression and random forest algorithm. For this purpose, 250 composite soil samples (0-10 cm depth) were randomly collected using the Conditional Latin Hypercube sampling approach from December 2020 to February 2021. Then, the physical and chemical properties of the samples were determined using standard laboratory methods. The experimental data were then analyzed for descriptive statistics using SPSS software. To model the spatial variability of available phosphorus contents of the soils, the experimental data were modeled using linear regression and random forest models in RStudio software. The results showed that according to the measured amounts of absorbable phosphorus in the soil samples in 32.4% of the samples, the concentration of available phosphorus is less than 5 mg/kg. Evaluation of multiple linear regression and random forest models based on model evaluation metrics including mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2) using training, test and the whole dataset, showed that the random forest model provides better and more accurate estimates due to higher coefficients of determination as well as lower error values. The results also illustrated that the organic carbon content of the soils has the greatest contribution in the study area to predict available contents of soil phosphorus. In conclusion, models that include non-linear relationships between variables seem to be more suitable in predicting soil properties.

کلیدواژه‌ها [English]

  • Conditioned Latin Hypercube
  • Prediction
  • Validation
  • Organic Carbon Content
Bertrand, I., Holloway, R.E., Armstrong, R.D., Mclaughlin, M.J. 2003. Chemical characteristics of phosphorus in alkaline soils from southern Australia. Australian Journal of Soil Research, 41: 61-76.
Breiman, L. 2001. Random forests. Machine Learning, 45: 5-32.
Breiman, L., Cutler, A. 2004. Random Forests. Department of Statistics, University of Berkeley. http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm.
Camera, C., Zomeni, Z., Noller, J.S., Zissimos, A.M., Christiforou, I.C., Bruggeman, A. 2017. A high resolution map of soil types and physical properties for Cyprus: A digital soil mapping optimization. Geoderma, 285: 35-49.
Gee, G.W., Bauder, J.W., 1986. Particle size analysis. In: Klute, A. (Ed.), Methods of Soil Analysis, Part 1. Physical and Mineralogical Methods, second ed. ASA and SSSA, Madison,WI, pp. 383–411.
Grimm, R., Behrens, T., Marker, M., Elsenbeer, H., 2008. Soil organic carbon concentrations and stocks on Barro Colorado Island-Digital soil mapping using random forests analysis. Geoderma, 146 (1-2): 102-113.
Havlin, J.L., S.L. Tisdale, J.D. Beaton, Nelson, W.L. 2005. Soil fertility and fertilizers: An introduction to nutrient management. Seventh edition, Pearson Education, Upper Saddle River, NJ.
Hengl, T., Heuvelink, G.B.M., Kempen, B., Leenaars, J.G.B., Walsh, M.G., Shepherd, K.D.,Sila, A., MacMillan, R.A., De Jesus, J.M., Tamene, L., Tondoh, J.E. 2015. Mapping soil properties of Africa at 250 m resolution: Random Forests significantly improve current predictions. PLoS ONE 10 (6): e0125814.
Hojati, S. 2018. Spatial variability of selected heavy metals in surface soils of northern Khuzestan Province. Project No. 93021034, Iran National Science Foundation, Tehran, Iran, 133 pages.
Jamshidi, M., Delavar, M.A., Taghizadeh-Mehrjerdi, R., Brungard, C. 2019. Evaluating digital soil mapping approaches for 3D mapping of soil organic carbon. Iranian Journal of Soil Research, 33(2): 227-239.
Khordehbin, S., Hojati, S., Landi, A., Ahmadianfar, I. 2020. Comparison of different data mining methods in predicting soil organic carbon storage in some lands of Behbahan city. Iranian Journal of Soil and Water Research, 51(4): 1041-1054.
Loeppert, R.H., Suarez, D.L. 1996. Carbonate and Gypsum. In: Sparks, D.L., Page, A.L., Helmke, P.A., Loeppert, R.H., Soltanpour, P.N., Tabatabai, M.A., Johnston, C.T., Sumner, M.E. (Eds.), pp. 437-474. Methods of Soil Analysis. Part 3. Chemical Methods, ASA and SSSA, Madison, USA.
Minasny, B., McBratney, A.B., 2006. A conditioned latin hypercube method for sampling in the presence of ancillary information. Computers and Geosciences, 32(9): 1378-1388.
Mirzashahi, K., Salimpour, S., Paknejad, A.R. 2014. Fertilizer recommendation for crops and orchards in the north of Khuzestan province. Journal No. 536, Soil and Water Research Institute, Tehran, Iran, 56 pages.
Moazed, H., Y, Hoseini, A.A. Naseri, Abbasi, F. 2010. Determining phosphorus adsorption isotherm in soil and its relation to soil characteristic. Journal of Food, Agriculture & Environment. 8(2): 1153-1157.
Mohebbi, S.M.J. 2014. Investigation of relationships between available phosphorus, potassium and some soilproperties in agricultural lands of Varamin- Iran. International Journal of Agriculture and Biosciences, 3(1): 7-12.
Mousavi, A., Shahbazi, F., Oustan, Sh., Jafarzadeh, A.A., Minasny, B. 2020. Application of two data mining techniques for mapping the spatial distribution of soil organic carbon (case study: East shore of Urmia Lake). Journal of Water and Soil, 34(3): 689-705.  
Nelson, D.W., Sommers, L., 1982. Total carbon, organic carbon, and organic matter. In: Page, A.L., (Ed.), Methods of soil analysis. Part 2: Chemical and microbiological properties, pp. 539-579. American Society of Agronomy and Soil Science Society of America, Madison, WI, USA.
Olsen, S.R., Cole, C.V., Watanabe, F.S., Dean, L.A., 1954. Estimation of available phosphorus in soils by extraction with sodium bicarbonate. U.S. Dep. Of Agric. Circ, 939 pp.
Pahlavan-Rad, M.R., Khormali, F., Toomanian, N., Brungard, C.W., Kiani, F., Komaki, C.B., Bogaert, P. 2016. Legacy soil maps as a covariate in digital soil mapping: A case study from Northern Iran. Geoderma, 279: 141-148.
Pahlavan-Rad, M.R., Khormali, F., Toomanian, N., Kiani, F., Komaki, C.B. 2015. Digital soil mapping using Random Forest model in Golestan province. Journal of Soil and Water Conservation, 21(6): 73-93.
Pilevar Shahri, A.J., Ayoubi, Sh., Khademi, H. 2011. Comparison of artificial neural network (ANN) and multivariate linear regression(MLR) models to predict soil organic carbon using digital terrain analysis (case study: Zargham Abad Semirom, Isfahan proviance). Journal of Water and Soil, 24(6): 1151-1163.
R Core Team. 2021. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.
Rhoades, J.D., 1986. Soluble salts. In: Page, A.L., Miller, R.H., Keeny, D.R. (Eds.), Methods of Soil Analysis, Part 2. Chemical and Microbiological Properties, second ed. ASA and SSSA, Madison, WI, pp. 167–180.
Rhoades, J. D., Chanduvi, F., Lesch, S., 1999. Food and agricultural organization of the UN. Soil salinity assessment: Methods and interpretation of electrical conductivity measurements. FAO Irrigation and Drainage, Paper No. 57.
Riemersma, S., Little, J., Ontkean, G., Moskal-Hébert, T., 2006. Phosphorus sources and sinks in watersheds: A review. Alberta soil phosphorus limits project, 82 p. 
Souri, M.K. 1397. Phosphorus in agriculture and environment with emphasis on management and measurement methods. Agricultural Education and Extension Publications, 348 pages.
Statistical Center of Iran. 2013. Iran statistical yearbook. Tehran: Management and Planning Organization.
Walkley, A., 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.