Using Different Regression Tree Algorithms to Predict Soil Organic Matter with Digital Color Parameters in Soil Profile Wall

Yıl 2021, Cilt: 7 Sayı: 2, 326 - 336, 25.08.2021

Gafur Gözükara , Yasin Altay

https://doi.org/10.24180/ijaws.907028

Öz

Soil organic matter has a critical role for the physical, chemical and biological properties of the soil and for sustainable soil and agriculture. Quick and cost-effective prediction of soil organic matter can provide basic data support for precision agriculture. The study area is located in the Muttalip pasture of Tepebaşı, Eskişehir. The soil profile wall (1x1 m) was dug and divided into 10x10 cm raster cell. A total of 100 soil samples were taken from center of each raster cell of the soil profile wall. The field-based and lab-based digital color parameters (CIE Lab) were measured depending on the grid sampling model. The ordinary Kriging interpolation method was used in geostatistical distribution maps of the amount of organic matter (OM) and field-based and lab-based CIE Lab values. CHAID, Ex-CHAID, and CART regression tree algorithms were used to predict the OM with field-based and lab-based CIE Lab values. The OM in the soil profile wall varies between 4.65-10.54% in the topsoils, while it varies between 0.01-0.41% in the subsoils. According to the results, lab-based CIE Lab values obtained high predicting performance and more effective than field-based CIE Lab values. It concluded that the CART algorithm can be used rapidly and economically in prediction OM with high prediction performance (R2=0.89) with lab-based digital color parameters.

Anahtar Kelimeler

Data mining algoritms, interpolations, pasture soils, CIE Lab, soil color

Toprak Profil Duvarında Farklı Regresyon Ağacı Algoritmaları Kullanılarak Sayısal Renk Parametreleri ile Organik Maddenin Tahmin Edilmesi

Öz

Toprak organik maddesi toprağın fiziksel, kimyasal ve biyolojik özellikleri ile sürdürülebilir toprak ve tarım için oldukça kritik bir role sahiptir. Toprak organik maddesinin çabuk ve düşük maliyetle tahmin edilmesi hassas tarım için temel veri desteği sağlayabilir. Çalışma alanı Eskişehir ili Muttalıp merası sınırları içerisinde yeralmaktadır. Toprak profil duvarı (1x1m) kazılmış ve 10x10 cm'lik grid hücrelere bölünmüştür. Toprak profil duvarından herbir grid hücreden grid yöntemi ile toplam 100 adet toprak örneği alınmıştır. Toprak örneklerinde sayısal renk parametrelerinin belirlenmesi grid örnekleme modeline bağlı olarak hem arazi hem de lobaratuvar koşullarında gerçekleştirilmiştir. Profil duvarından arazi ve laboratuvar koşullarında elde edilen CIE Lab değerleri ve organik madde miktarının jeoistatistiksel olarak dağılım haritalarında Ordinary Kriging interpolasyon metodu kullanılmıştır. Sayısal renk parametreleri ile organik madde miktarının tahmin edilmesinde CHAID, Ex-CHAID ve CART regresyon ağacı algoritmaları kullanılmıştır. Toprak profil duvarında organik madde miktarı yüzey topraklarda %4.65-10.54 arasında değişirken yüzey altı topraklarda %0.01-0.41 arasında değişmektedir. Araştırma sonuçlarına göre, OM miktarının tahmin edilmesinde laboratuvar koşullarında elde edilen CIE Lab değerlerinin laboratuvar koşullarında elde edilen CIE Lab değerlerinden daha etkilidir. Araştırma, CART algoritmasının laboratuvar koşullarında elde edilen sayısal renk parametreleri ile OM miktarının yüksek başarı performansı (R2=0.89) ile tahmin edilmesinde hızlı ve ekonomik olarak kullanılabileceğini ortaya çıkarmıştır.

Anahtar Kelimeler

Veri madenciliği algoritmaları, interpolasyon, mera toprakları, CIE Lab, toprak rengi

Kaynakça

• Acar, M., Celik, I., & Günal, H. (2018). Effects of long-term tillage systems on aggregate-associated organic carbon in the eastern Mediterranean region of Turkey. Eurasian Journal of Soil Science, 7(1), 51-58.
• Aertsen, W., Kint,V., Orshoven, J., Özkan, K., & Muys, B. (2010). Comparison and ranking of different modeling techniques for prediction of site index in Mediterranean mountain forests. Ecological Modelling, 221, 1119-1130.
• Aksahan, R., & Keskin, I. (2015). Determination of the some body measurements effecting fattening final live weight of cattle by the regression tree analysis. Selçuk Journal of Agriculture and Food Science, 2, 53-59.
• Aktaş, T., & Yüksel, O. (2020). Effects of vermicompost on aggregate stability, bulk density and some chemical characteristics of soils with different textures. Journal of Tekirdag Agricultural Faculty, 17(1), 1-11.
• Alaboz, P., Demir, S., & Dengiz, O. (2020). Determination of spatial distribution of soil moisture constant using different interpolation model case study, Isparta Atabey Plain. Journal of Tekirdag Agricultural Faculty, 17(3), 432-443.
• Allison, L. E., Moodie, C. D. (1965). Carbonate, agronomy monograph, methods of soil analysis. Part 2. In: Chemical and Microbiological properties, Agronomy. 9.2. American Society of Agronomy, Wisconsin, pp. 1379-1396.
• Altay, Y., Boztepe, S. Eyduran, E., Keskin, İ., Tariq, M. M., Bukhari, F. A. & Ali, I. (2021). Description of factors affecting wool fineness in Karacabey Merino Sheep using Chaid and Mars Algorithms. Pakistan Journal of Zoology, 53(2), 691-697.
• Altunbaş, S., Demirel, B. Ç., Gözükara, G., & Erol. S. (2020). Determination of land capability classes of some soils developing on alluvial lands. International Journal of Agriculture and Wildlife Science, 6(3), 638-646.
• Barret, L. R. (2002). Spectrophotometric color measurement in situ in well drained sandy soils. Geoderma, 108, 49-77.
• Black, C. A. (1965). Methods of Soil Analysis Part 2, Amer. Society of Agronomy Inc., Publisher Madison, Wisconsin, U.S.A.
• Bouyoucos, G. J. (1953). An improved type of soil hdyrometer. Soil Science, 76, 377-378.
• Budak, M., Günal, H., Süer, M., & Akbaş, F. (2018). Determination of some physical and chemical characteristics of soil properties from digital color parameters. Harran Journal of Agriculture and Food Science, 22(3), 376-389.
• Çelik, İ., Günal, H., Acar, M., Acir, N., Barut, Z.B., & Budak, M. (2020). Evaluating the long-term effects of tillage systems om soil structural quality using visual asessment and classical methods. Soil Use and Management, 36, 223-239.
• Dengiz, O. (2020). Soil quality index for paddy fields based on standard scoring functions and weight allocation method. Archives of Agronomy and Soil Science, 66(3), 301-315.
• DMİ (Devlet Meteoroloji İşleri), 2017. Eskişehir ili iklim verileri. Devlet Meteoroloji İşleri Genel Müdürlüğü, Ankara.
• Doi, R., Wachrinrat, C., Teejuntuk, S., Sakurai, K., & Sahunalu, P. (2010). Semiquantitative color profiling of soils over a land degradation gradient in Sakaerat, Thailand. Environmenal Monitoring Assessment, 170, 301-309.
• Eyduran, E. (2019). ehaGoF: Calculates Goodness of Fit Statistics. R package version 0.1.0. https://CRAN.R-project.org/package=ehaGoF.
• Fan, Z., Herrick, J. E., Saltzman, R., Matteis, C., Yudina, A., Nocella, N., Crawford, E., Parker, R., & Van Zee, J. (2017). Measurement of soil color: a comparison between smartphone camera and the munsell color charts. Soil Science Society of America Journal, 81(5), 1139-1146.
• Fang, X. M., Ono, Y., Fukusawa, H., Pan, B. T., Li, J. J., Guan, D. H., Oi, K., Tsukamoto, S., Torii, M., & Mishima, T. (1999). Asian summer monsoon instability during the past 60.000 years: magnetic susceptibility and pedogenic evidence from the western Chinese Loess Plateau. Earth and Planetary Science Letters, 168, 219-232.
• Gozukara, G., Zhang, Y., & Hartemink, A. E. (2021b). Using vis-NIR and pXRF data to distinguish soil parent materials – an example using 136 pedons from Wisconsin, USA. Geoderma, 396, 115091.
• Gözükara, G., Altunbaş, S., & Sarı, M. (2019). The effect of spatial change on the properties of soil formed on alluvial fans. Mediterranean Agricultural Sciences, 32(3), 425-435.
• Gözükara, G., Altunbaş, S., & Sarı, M. (2020a). Effects of temporal and spatial changes on formation, development and morphology of soil in different physiographs. Journal of Agriculture Faculty of Ege University, 57(2), 277-278.
• Gözükara, G., Altunbaş, S., & Sarı, M. (2020b). Temporal and spatial changes in old lake bottom effect on soil formation, development and morphology. Harran Journal of Agriculture and Food Science, 24(1), 96- 110.
• Gözükara, G., Demirel, B. Ç., & Altunbaş, S. (2021a). Effect of soil horizons on the relationship between digital color paremeters and soil properties. Mediterranean Agricultural Sciences, 34(1).
• Grzesiak, W., & Zaborski, D. (2012). Examples of the Use of Data Mining Methods in Animal Breeding, Data Mining Applications in Engineering and Medicine, Adem Karahoca, IntechOpen.
• Günal, H., Erşahin, S., Yetgin, B., & Kutlu, B. (2008). Use of chroma-meter measured color parameters in estimating color related soil variables. Communications in Soil Science and Plant Analysis, 39(6), 726-740.
• Hartemink, A. E., & Minasny, B. (2014). Towards digital soil morphometrics. Geoderma, 230-231, 305-317.
• IBM Corp. Released (2015). IBM SPSS Statistics for Windows, Version 23.0. Armonk, NY: IBM Corp.
• Koç, A., & İleri, O. (2016). Comparison of Cattle and Sheep Grazed Sub-Irrigated Rangelands Vegetation in Eskişehir Plain. Journal of Field Crops Centrel Research Institute, 25, 179-184.
• Kirillova, N. P., Vodyanitskii, Y. N., & Sileva, T. M. (2015). Conversion of soil color parameters from the Munsell system to the CIE-L* a* b* system. Eurasian Soil Science, 48(5), 468-475.
• McBratney, A. B., Stockmann, U., Angers, D. A., Minasny, B., & Field, D. J. (2014). Challenges for soil organic carbon research. In: Hartemink, A., McSweeney, K. (Eds.), Soil Carbon. Progress in Soil Science. Springer, Cham.
• Moritsuka, N., Matsuoka, K., Katsura, K., Sano, S., & Yanai, J. (2014). Soil color analysis for statistically estimating total carbon. total nitrogen and active iron contents in Japanese agricultural soils. Soil Science and Plant Nutrition, 60(4), 475-485.
• Nishiyama K, Kimura, T., Isono, Y., & Inoue, Y. (2011). Color measurements of rocks and soils using colorimeters. Journal of the Japan Society of Engineering Geology, 52, 62–71 (in Japanese).
• R Core Team. (2020). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from https://www.R-project.org/.
• Oruçoğlu, O. (2011). Determination of environmental factors affecting 305-day milk yield of holstein cows by regression tree method. Master Thesis, Süleyman Demirel University, Institute of Science, Isparta.
• Post, D. F., Levine, S. J., Bryant, R. B. Mays, M. D., Batchily, A. K., Escadafal, R., & Huete, A.R. (1993). Correlations between field and laboratory measurements of soil color. In J. M. Bigham, & E. J. Ciolkosz (Eds.). Soil Color. Soil Science Society of America. Madison.
• Rice, T. D., Nickerson, D., O'Neal, A. M., & Thorp, J. (1941). Preliminary color-standards and color names for soil. Miscellaneous Publication, 425, 1–12.
• Sawada, K, Wakimoto, T., Hata, N., Taguchi, S., Tanaka, S., Tafu, M., & Kuramitz, H. (2013). The evaluation of forest fire severity and effect on soil organic matter based on the L*, a*, b* color reading system. Analytical Methods, 5, 2660–2665.
• Schulze, D. G., Nagel, J. L., Van Scoyoc, G. E., Henderson, T. L., Baumgardner, M. F., & Stott, D. E. (1993). Significance of organic matter in determining soil colors. In J. M. Bigham, & E. J. Ciolkosz (Eds.). Soil Color. Soil Science Society of America. Madison.
• Shen, Z. X., Cao, J. J. Zhang, X. Y., Arimoto, R., Ji, J. F., Balsam, W. L., Wang, Y. Q., Zhang, R. J., & Li, X. X. (2006). Spectroscopic analysis of iron-oxide minerals in aerosol particles from northern China. Science of the Total Environment, 367, 899-907.
• Simonson, R. W. (1993). Soil color standards and terms for field use history of their development. In J. M. Bigham, & E. J. Ciolkosz (Eds.). Soil Color. Soil Science Society of America. Madison.
• Soil Survey Staff. (2010). Soil Taxonomy. 11th ed. USDA National Resources Conservation Services. Washington DC.
• Soil Survey Staff. (2014). Keys to Soil Taxanomy. Twelfth Edition Edition, United States Department of Agriculture, Natural Resources Conservation Service, Washington DC.
• Sönmez, N. K., Sönmez, S., Türkkan, H. R., Altın, R., & Çoşlu, M. (2020). Spatial variability analysis of electrical conductivity (ec) of irrigation water used in agricultural production: an example of Dalaman-Muğla. The Journal of Faculty of Agriculture, 15(1), 12-26.
• Şimşek, O., Altunbaş, S., Demirel, B. Ç., & Gözükara, G. (2020). Land evaluation studies on different soils developing on alluvial physiographies. Mediterranean Agricultural Sciences, 33(1), 129-135.
• Thwaites, R. (2002). Color. In: Lal. R. (ed.) Encyclopedia of Soil Science.. Marcel Dekkers. Inc Torrent, J., Schwertmann, U., & Schulze, D. G. 1980. Iron oxide mineralogy of some soils of two river terrace sequences in Spain. Geoderma, 23, 191-208.
• Torrent, J., & Barrón, V. (1993). Laboratory measurement of soil color: Theory and practice. In J. M. Bigham, & E. J. Ciolkosz (Eds.). Soil Color. Soil Science Society of America. Madison.
• Vodyanitskii, Y. N., & Kirillova, N. P. (2016). Application of the CIE-L* a* b* system to characterize soil color. Eurasian Soil Science, 49(11), 1259-1268.
• Viscarra Rossel, R. A., Minasny, B., Roudier, P., & McBratney, A. B. (2006). Colour space models for soil science. Geoderma, 133, 320-337.
• Wu, C. W., Yang, Y., & Xia, J. X. (2017). A simple digital imaging method for estimating blacksoil organic matter under visible spectrum. Archives Agronomy Soil Sciences, 63(10), 1346-1354.
• Yılmaz, E., Çanakçı, M., Topakçı, M., Sönmez, S., Ağsaran, B., Alagöz, Z., Çıtak, S., & Uras, D. S. (2019). Effect of vineyard pruning residue application on soil aggregate formation, aggregate stability and carbon content in different aggregate sizes. Catena, 183, 104219.