The Least Limiting Water Range to Estimate Soil Water Content Using Random Forest Integrated with GIS and Geostatistical Approaches

Year 2023, Volume: 29 Issue: 4, 933 - 946, 06.11.2023

Pelin Alaboz , Orhan Dengiz

https://doi.org/10.15832/ankutbd.1137917

Cited By: 1

Abstract

Algorithms that exist in every area today have become the center of our lives with technological developments. The uses of machine learning algorithms are being researched with the new developments in the agricultural field. The present study determined the least limiting water range (LLWR) contents of alluvial lands with different soils distributed in the Bafra Plain, where intensive agricultural activities are carried out, and revealed the compression and aeration problems in the area with distribution maps. Also, the predictability of LLWR was evaluated with the random forest (RF) algorithm, one of the machine learning algorithms, and the usability of the prediction values distribution maps was revealed. The LLWR contents of the soils varied in the range of 0.049-0.273 cm3 cm-3 for surface soils. There were aeration problems in 6.72%, compaction problems in 20.16%, and aeration and compaction problems in 0.8% of the surface soils examined in the study area. Furthermore, 72.32% of the soil was under optimal conditions. For the 20-40 cm depth, an aeration problem in 5.88%, a compaction problem in 28.57%, and both an aeration and a
compaction problem in 2.52% of the points were detected. In estimating LLWR with the RF algorithm, the root mean square error (RMSE) value obtained for 0-20 cm depth was determined to be 0.0218 cm3 cm-3, and for 20-40 cm depth, it was 0.0247 cm3 cm-3. In the distribution maps of the observed and predicted values obtained, the lowest RMSE value was determined by the SK
interpolation methods for 0-20 cm depth and the OK interpolation methods for 20-40 cm. The distribution of obtained and predicted values in surface soils was similar. However, variations were found in the distribution of areas with low LLWR below the surface. As a result of the study, it was determined that LLWR can be obtained with a low error rate with the RF algorithm, and distribution
maps can be created with lower error in surface soils.

Keywords

Physical properties, Moisture constants, Machine learning, Bafra delta plain

References

• Akar Ö& Güngör Ö (2013). Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation 1(2):139-146.
• Aksakal EL (2004). Soil compaction and its importance for agriculture. Atatürk University Journal of Agricultural Faculty 35(3-4): 247-252.
• Alaboz P, Başkan O & Dengiz O (2021). Computational intelligence applied to the least limiting water range to estimate soil water content using GIS and geostatistical approaches in alluvial lands. Irrigation and Drainage. DOI: 10.1002/ird.2628
• 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): 432-444.
• Blake G R & Hartge K H (1986). Methods of soil analysis: physical and minerological analysis. Madison (WI): American Society of Agronomy. Chapter 14 Bulk density and particle density : 363–381.
• Breiman L (2001). Random Forests,Machine learning, Kluwer Academic Publishers 45(1): 5-32.
• Brus D J & Heuvelink G B (2007). Optimization of sample patterns for universal kriging of environmental variables. Geoderma 138(1-2):86-95.
• Busscher WJ (1990). Adjustment of flat- tipped penetrometer resistance data to a common water content. http://naldc. nal.usda. gov/download/18014/PDF. Accessed 25 June 2020.
• Chan K, Oates A, Swan A, Hayes R, Dear B & Peoples M, (2006). Agronomic consequences of tractor wheel compaction on a clay soil. Soil and Tillage Research 89 (1): 13-21
• Christensen R (1990) The equivalence of predictions from universal kriging and intrinsic random-function kriging. Mathematical Geology 22(6): 655-664.
• Da Silva A, Kay B & Perfect E (1994). Characterization of the least limiting water range of soils, Soil Science Society of America Journal 58 (6): 1775-1781.
• Da Silva AP & Kay B (1997). Estimating the least limiting water range of soils from properties and management. Soil Science Society of America Journal 61 (3): 877-883.
• Dengiz O (2010). Morphology, Physico-Chemical Properties and Classification of Soils on Terraces of the Tigris River in the South-East Anatolia Region of Turkey Journal of Agricultural Sciences 16 (3): 205-212.
• Eijkelkamp (1990). Equipment for soil research. Giesbeek (The Netherlands): Eijkelkamp Corporation.
• Gee G W & Bauder J W (1986). Methods of soil analysis: physical and minerological analysis. Madison (WI): American Society of Agronomy Particle-size analysis: 388–409.
• Haghighi Fashi, F, Gorji M & Sharifi, F (2017). Least limiting water range for different soil management practices in dryland farming in Iran. Archives of Agronomy and Soil Science 63(13): 1814-1822.
• Kahlon M S & Chawla K (2017). Effect of tillage practices on least limiting water range in Northwest India. International Agrophysics 31(2): 83-194.
• Karahan G, Erşahin S & Öztürk H S (2014). Field Capacity Dynamics Affected by Soil Properties. Journal of Agricultural Faculty of Gaziosmanpasa University 30(1): 1-9.
• Kay B D & Anger D A (2002). Soil structure in soil physics companion (AWarrick, Ed) 249-296.
• Klute A. (1986). Methods of soil analysis: physical and minerological analysis. Madison (WI): American Society of Agronomy. Water Retention: 635–662.
• Leão T P, Da Silva A P, Perfect E & Tormena CA (2005). An algorithm for calculating the least limiting water range of soils. Agronomy Journal 97(4): 1210-1215.
• Letey J (1958). Relationship between soil physical properties and crop production. In Advances in soil science (pp. 277-294). Springer, New York, NY.
• Lewis CD (1982). Industrial and Business Forecasting Methods. Londra: Butterworths Publishing, 40 p
• Li J & Heap A D (2008). A review of spatial interpolation methods for environmental scientists.
• Liaw A & Wiener M (2002). Classification and Regression by Random Forest, R News, Vol.2/3, December.
• Machado G, Vilalta C, Recamonde-Mendoza M, Corzo C, Torremorell M, Perez A & VanderWaal K (2019). Identifying outbreaks of Porcine Epidemic Diarrhea virus through animal movements and spatial neighborhoods Scientific Reports 9: 12.
• Max K (2020). caret: Classification and Regression Training. R package version 6.0-86.https://CRAN.R-project.org/package=caret.
• Mihalikova M, Özyazıcı M A & Dengiz O (2016). Mapping soil water retention on agricultural lands in central and eastern parts of the Black Sea Region in Turkey. Journal of Irrigation and Drainage Engineering 142(12): 05016008-1.
• Munsuz N (1985) Soil Mechanics and Technology. Ankara University. Faculty of Agriculture Publications: 922 Textbook: 260: Ankara
• Negiş H, Şeker C & Çetin A. (2020). Effects of different organic materials on soil compaction and least limiting water range. Journal of Soil Science and Plant Nutrition 8(2):118-127.
• Oliver M A & Webster R (2015). Basic steps in geostatistics: the variogram and kriging (pp. 15-42). Cham, Switzerland: Springer International Publishing.
• Pal M (2005). Random Forest Classifier for Remote Sensing Classification, International Journal of Remote Sensing 26(1): 217-222.
• Prasad A M, Iverson L R & Liaw A. (2006). Newer classification and regression tree techniques: Bagging and random forests for ecological prediction. Ecosystems 9:181-199
• Safadoust A, Feizee P, Mahboubi A, Gharabaghi B, Mosaddeghi M & Ahrens B (2014). Least limiting water range as affected by soil texture and cropping system. Agricultural Water Management 136: 34-41.
• Soil Survey Staff (1999). Soil taxonomy: a basic of soil classification for making and interpreting soil survey. 2nd ed. Washington (DC): NRCS, USDA, Agriculture Handbook No 436.
• Soil Survey Staff (2014). Keys to Soil Taxonomy (12th ed.), USDA National Resources Conservation Services, Washington DC.
• Stum A K, Boettinger J L, White MA & Ramsey R D (2010). Random forests applied as a soil spatial predictive model in arid Utah. In Digital soil mapping (pp. 179-190). Springer, Dordrecht.
• Şenol H, Alaboz P, Demir S & Dengiz O (2020). Computational intelligence applied to soil quality index using GIS and geostatistical approaches in semiarid ecosystem. Arabian Journal of Geosciences 13(23): 1-20.
• Tavanti R F, Freddi O D S, Tavanti T R, Rigotti A & Magalhães W D A (2019). Pedofunctions applied to the least limiting water range to estimate soil water content at specific potentials. Engenharia Agrícola 39(4): 444-456.
• Tunçay T, Başkan O, Bayramin İ, Dengiz O & Kılıç Ş (2018). Geostatistical approach as a tool for estimation of field capacity and permanent wilting point in semiarid terrestrial ecosystem. Archives of Agronomy and Soil Science 64 (9): 1240-1253.
• Watts J D & Lawrence R.L (2008). Merging random forest classification with an object-oriented approach for analysis of agricultural lands, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII(B7).
• Wilding LP (1985). Spatial variability: Its documentation, accommodation and implication to soil surveys. 166-194p. In D.R. Nielsen and J. Bouma (eds.). Soil Spatial Variability: Pudoc. Wageningen Netherlands.
• WRB (2014). World reference base for soil resources. International soil classification system for naming soils and creating legends for soil maps. Food and Agriculture Organization of United Nations, World Soil Resources Reports6 :203
• Wright GB (2003). Radial basis function interpolation: numerical and analytical developments. University of Colorado at Boulder.
• Wu L, Feng G, Letey J, Ferguson L, Mitchell J, Mc Cullough-Sanden B & Markegard G (2003). Soil management effects on the nonlimiting water range. Geoderma 114(3-4): 401-414.
• Van Buuren S & Groothuis-Oudshoorn K (2011). "mice: Multivariate imputation by chained equations in R." Journal of statistical software 45:1-67.