تعیین ویژگی‌های مؤثر بر پایداری ساختمان خاک‌های مناطق خشک با استفاده از الگوریتم ترکیبی ژنتیک-شبکه عصبی مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 پیدایش و رده بندی خاک، پدومتری

2 دانشجوی دکتری، گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ولی عصر رفسنجان

3 استاد گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ولی عصر رفسنجان، رفسنجان، ایران

4 استادیار، گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ولی عصر رفسنجان، رفسنجان، ایران

چکیده

پایداری خاکدانه­ها به‌عنوان یکی از کلیدی­ترین شاخص­های کیفیت فیزیکی خاک، بیان‌گر قدرت نسبی خاک در برابر نیروهای فرساینده و تخریب مکانیکی است. در این پژوهش، به‌منظور شناسایی یک زیرمجموعه از مهم‌ترین ویژگی‌های مؤثر بر شاخص میانگین وزنی قطر خاکدانه‌ها (MWD)، از الگوریتم ترکیبی ژنتیک-شبکه عصبی مصنوعی (GA-ANN) استفاده گردید. افزون بر آن، قابلیت شبکه­های عصبی مصنوعی (ANNs) و رگرسیون چند متغیره خطی (MLR) برای کمی‌سازی رابطه بین شاخص MWD و ویژگی‌های خاک مؤثر بر آن، ارزیابی شد. پس از فرآیند مدل‌سازی، اهمیت هر یک از ویژگی‌های انتخاب شده در ارتباط با تغییرات مکانی پایداری خاکدانه‌ها بررسی گردید. به‌منظور دست­یابی به یک مجموعه داده مناسب، شاخص MWD و تعدادی از ویژگی‌های خاک در نمونه‌های خاک‌ جمع‌آوری شده از 90 نقطه مشاهداتی اندازه‌گیری شدند. نتایج حاصل از انتخاب ویژگی نشان داد که شش ویژگی‌ خاک شامل رس، شن، ماده آلی، کربنات کلسیم معادل، قابلیت هدایت الکتریکی و نسبت جذب سدیم، بیش‌ترین تأثیر را بر روی شاخص MWD خاک‌های مورد مطالعه داشتند. با توجه به نتایج به‌دست آمده از برآورد شاخص MWD، مقادیر محاسبه­شده ضریب تبیین (R2)، میانگین درصد خطای مطلق (MAEP) و مجذور میانگین مربعات خطا (RMSE) برای عملکرد شبکه عصبی مصنوعی، به‌ترتیب برابر با 94/0، 39/21 و 075/0 درصد بودند. این نتایج بیان‌گر آن بود که مدل ANN توسعه داده شده به­خوبی توانسته است روابط پیچیده و غیرخطی بین شاخصMWD  و ویژگی‌های خاک انتخاب­شده توسط الگوریتم GA-ANN را پیش‌بینی و کمی‌سازی کند. بر اساس نتایج به‌دست آمده از تحلیل حساسیت، کربنات کلسیم معادل، ذرات شن و ماده آلی به‌عنوان فاکتورهای کلیدی برای تخمین پایداری خاکدانه‌ها معرفی شدند. به‌طور کلی، این پژوهش یک چارچوب قوی برای تخمین پایداری خاکدانه‌ها و شناسایی مهم‌ترین ویژگی‌های مؤثر بر آن در خاک‌های مناطق خشک و نیمه‌خشک فراهم می‌کند که می‌تواند برای سایر مناطق با چالش‌های مشابه، مورد استفاده قرار گیرد.

کلیدواژه‌ها


عنوان مقاله [English]

Determining the Features Influencing the Structural Stability of Soils of Arid Regions Using a Hybrid GA-ANN Algorithm

نویسندگان [English]

  • Iraj Kouchami-Sardoo 2
  • Hossein Shirani 3
  • Ali Asghar Besalatpour 4
2 PhD Student of Soil Science, Department of Soil Science, College of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
3 Professor of Soil Science, Department of Soil Science, Faculty of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
4 Assistant prof. of Soil Science, Department of Soil Science, Faculty of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran
چکیده [English]

Aggregate stability of soils informs about their relative strengths against erosive forces and mechanical disruption. In this research, a hybrid Genetic Algorithm-Artificial Neural Network method was used to select the best subset of features affecting the mean weight diameter (MWD. In addition, the ability of ANNs and multiple linear regression (MLR) for quantifying the relationship between the MWD index and some soil properties was assessed. After the modeling process, the importance of the selected features in relation to spatial variability of aggregate stability was investigated. In order to prepare a suitable data set; MWD index and some soil features were measured in collected soils from 90 sampling points. Feature selection results showed that six soil features including clay, sand, organic matter, calcium carbonate, electrical conductivity, and sodium adsorption ratio had the greatest effect on the aggregates stability of the studied soils. According to the MWD modeling results, the obtained values of coefficient of determination (R2), mean absolute error percentage (MAEP), and root mean square error (RMSE) for the ANN model performance were 0.94, 21.39, and 0.07% respectively. These findings indicated that the developed ANN model was able to predict the complex and nonlinear relationships between the MWD index and the soil properties selected by the algorithm. Based on the sensitivity analysis results, calcium carbonate equivalent, sand particles, and organic matter were identified as key factors in estimating aggregate stability. Overall, this study provides a robust framework for the prediction of aggregate stability and identifying the most determinant parameters influencing it in arid and semi-arid soils that could be applied to other regions with similar challenges.

کلیدواژه‌ها [English]

  • Optimization
  • Mean weight diameter
  • Multiple linear regression
  • sensitivity analysis
Asgari H.R., and Sarparast M. 2013. The impact of Haloxylonplantation on some soil erodibility indices on the sandy lands of Taybad. Environmental Erosion Research Journal, 3 (10): 1-12. (In Persian)

Asghari S., and Najafian M. 2015. Interactive effects of organic matters and earthworm on some physical and chemical properties of two soils under different compaction conditions. Applied Soil Research, 3(1): 89-102. (In Persian)

Besalatpour A.A., Ayoubi S., Hajabbasi M.A., Jazi A.Y., and Gharipour A. 2014. Feature selection using parallel genetic algorithm for the prediction of geometric mean diameter of soil aggregates by machine learning methods. Arid Land Research and Management, 28(4): 383-394.

Bouajila A., and Gallali T. 2008. Soil organic carbon fractions and aggregate stability in carbonated and no carbonated soils in Tunisia. Journal of Agron, 7(2): 127-137.

Curtin J.S., and Mullen G.J. 2002. Spent mushroom compost effect on aggregate stability and percent organic carbon on low organic matter tilled soils. Life Science Department, University of Limerick, Limerick.

Emerson W.W., and Greenland D.J. 1990. Soil aggregates-formation and stability. In: De Boodt, M., Hayes, M., Herbillon, A. (Ed.), Soil colloids and their associations in aggregates. Plenum Press, New York, pp. 485-511.

Esfandiarpour-Borujeni I., Hosseinifard S.J., Shirani H., Zeinadini M., and Besalatpour A.A. 2018. Identifying Soil and Plant Nutrition Factors Affecting Yield in Irrigated Mature Pistachio Orchards. Communications in soil science and plant analysis, 49(12): 1474-1490.

Etminan S., Kiani F., Khormali F., and Habashi H. 2011. Effect of soil properties with different parent materials on aggregate stability: in Shastkola watershed, Golestan province. Journal of Soil Management and Sustainable Production, 1(2): 39-60. (In Persian)

Gee G.W., and Bauder J.W. 1986. Particle size analysis. In: Klute, A. (Ed.), Methods of Soil Analysis: Part 1. American Society of Agronomy and Soil Science Society of America, Madison, pp. 383-411.

Ingleby H.R., and Crowe T.G. 2001. Neural network models for predicting organic matter content in Saskatchewan soils. Canadian Biosystems Engineering, 43 (7): 1–5.

Karimi H., Soufi M., Haghnia G., and Khorasani R. 2008. Investigation of aggregate stability and soil erosion potential in some loamy and sandy clay loam soils: case study in Lamerd watershed (south of Fars province). Journal of Agricultural Sciences and Natural Resources, 14(6): 348-356. (In Persian)

Kemper W.D., and Rosenau R.C. 1986. Aggregate stability and size distribution. In: Methods of Soil Analysis, Part 1. Physical and Mineralogical Methods. Agronomy Monograph No. 9. Society of Agronomy/Soil Science Society of America, Madison, pp. 425-442.

Khazaei A., Mosaddeghi M.R., and Mahboubi A.A. 2008. Test conditions, and soil organic matter, clay and calcium carbonate contents’ impacts on mean weight diameter and tensile strength of aggregates from some Hamadan soils. Journal of Agricultural and Natural Resource Sciences and Technology, 44(4): 123-135. (In Persian)

Mahmoodabadi M., and Ahmadbeygi B. 2013. Effect of primary particle size distribution on aggregate stability at different size classes. Water Soil Science, 23(3): 207-219. (In Persian)

Merdun H., Çınar Ö., Meral R., and Apan M. 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90(2): 108-116.

Nelson R.E. 1982. Carbonate and gypsum. In: Page, A.L. (Ed.), Methods of Soil Analysis: Part 1. Agronomy Handbook 9. American Society of Agronomy and Soil Science Society of America, Madison, pp. 181-197.

Nikpur M., Mahboubi A.A., Mosaddeghi M.R., and Safadoust A. 2012. Assessment of soil intrinsic properties effects on soil structural stability of some soils in Hamadan province. Journal of Agricultural and Natural Resource Sciences and Technology, 15(58): 85-96. (In Persian)

Obalum S.E., Uteau-Puschmann D., and Peth S. 2019. Reduced tillage and compost effects on soil aggregate stability of a silt-loam Luvisol using different aggregate stability tests. Soil and Tillage Research, 189: 217-228.

Schaap M.G., Leij F.J., and Van Genuchten M.T. 1998. Neural network analysis for hierarchical prediction of soil hydraulic properties. Soil Science Society of America Journal, 62(4): 847-855.

Shekofteh H., Ramazani F., and Shirani H. 2017. Optimal feature selection for predicting soil CEC: Comparing the hybrid of ant colony organization algorithm and adaptive network-based fuzzy system with multiple linear regression. Geoderma, 298: 27-34.

Shirani H., 2018. Artificial Neural Networks with an Application in Agricultural and Natural Resource Sciences, 2nd Ed. Vali-E-Asr University of Rafsanjan, 189p. (In Persian)

Shirani H., Habibi M., Besalatpour A.A., and Esfandiarpour I. 2015. Determining the features influencing physical quality of calcareous soils in a semiarid region of Iran using a hybrid PSO-DT algorithm. Geoderma, 259: 1-11.

Shirani H., Hosseinifard S.J., and Hashemipour H. 2018. Factors affecting cadmium absorbed by pistachio kernel in calcareous soils, southeast of Iran. Science of the Total Environment, 616: 881-888.

Singh A.K., Bordoloi L.J., Kumar M., Hazarika S., and Parmar B. 2014. Land use impact on soil quality in eastern Himalayan region of India. Environmental monitoring and assessment, 186(4): 2013-2024.

Singh J., Knapp H.V., Arnold J.G., and Demissie M. 2005. Hydrological modeling of the Iroquois river watershed using HSPF and SWAT 1. JAWRA Journal of the American Water Resources Association, 41(2): 343-360.

Tatarko J., 2001. Soil aggregation and wind erosion: processes and measurements. Annals of Arid Zone, 40(3): 251-264.

Tedeschi A., and Dell’Aquila R. 2005. Effects of irrigation with saline waters, at different concentrations, on soil physical and chemical characteristics. Agricultural Water Management, 77(1-3): 308-322.

Tejada M., Garcia C., Gonzalez J.L., and Hernandez M.T. 2006. Use of organic amendment as a strategy for saline soil remediation: influence on the physical, chemical and biological properties of soil. Soil Biology and Biochemistry, 38(6): 1413-1421.

Ternan J.L., Elmes A., Williams A.G., and Hartley R. 1996. Aggregate stability of soils in central Spain and the role of land management. Earth Surface Processes and Landforms, 21(2): 181-193.

Veihe A., and Quinton J. 2000. Sensitivity analysis of EUROSEM using Monte Carlo simulation I: hydrological, soil and vegetation parameters. Hydrological Processes, 14(5): 915-926.

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.

Whalen J.K., Hu Q., and Liu A. 2003. Compost applications increase water-stable aggregates in conventional and no-tillage systems. Soil Science Society of America Journal, 67(6): 1842-1847.

Wu B., Zhang L., and Zhao Y. 2013. Feature selection via Cramer's V-test discretization for remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2593-2606.

Zaker M., Emami H., Astaraei A., and Fotovat A. 2017. Soil physical properties as affected by potassium and salinity of irrigation water. Applied Soil Research, 6(1): 51-61. (In Persian)