نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه خاک‌شناسی، دانشگاه شهرکرد

2 عضو هیئت علمی گروه خاک‌شناسی، دانشگاه شهرکرد

3 پیدایش و رده بندی خاک، پدومتری گروه خاک‌شناسی، دانشگاه ولی عصر (عج) رفسنجان

4 هیئت علمی گروه خاک‌شناسی، دانشگاه شهرکرد

چکیده

چکیده
با توجه به ارتباط بین عملکرد محصول و ویژگی­های خاک و توپوگرافی زمین، شـناخت و آگاهی از ویژگی­ها برای دستیابی به توسعه پایدار در کشاورزی، ضروری است. پژوهش حاضر با هدف ارزیابی و تعیین رابطه بین عملکرد گل محمدی و ویژگی‌های خاک و توپوگرافی زمین با استفاده از مدل‌های رگرسیون خطی چندمتغیره، شبکه عصبی مصنوعی و روش مدل‌سازی معادلات ساختاری در شهرستان بردسیر، استان کرمان اجرا گردید. برای این منظور، نمونه­برداری از خاک و عملکرد محصول، در قالب یک الگوی شبکه­ای منظم صورت گرفت. همچنین، با تهیه مدل رقومی ارتفاع منطقه، برخی ویژگی‌های توپوگرافی زمین محاسبه گردید و برای اجرای مدل روابط ساختاری، سه مدل نظری طراحی و مورد آزمون قرار گرفت. نتایج نشان داد که مدل­های رگرسیون خطی چندمتغیره و شبکه عصبی مصنوعی به‌ترتیب، 68 و 87 درصد از تغییرپذیری عملکرد را توجیه می­کنند که نشان‌دهنده دقت بالاتر مدل شبکه عصبی مصنوعی نسبت به رگرسیون خطی چندمتغیره در تخمین عملکرد می­باشد. نتایج مدل‌سازی معادلات ساختاری نشان داد که کنترل عملکرد گل محمدی در این منطقه، بیشتر در اختیار ویژگی­های شیمیایی خاک، سپس ویژگی­های توپوگرافی زمین و ویژگی­های فیزیکی خاک قرار دارد. سناریوهای مختلف برای انجام مدل‌سازی معادلات ساختاری نشان داد که هر چقدر مدل طراحی‌شده ساده‌تر و دارای سازه‌های پنهان کمتری باشد، می‌تواند برازش مطلوب‌تری داشته باشد. بنابراین، اولین مدل مفهومی این روش با دارا بودن مقادیر جذر میانگین مربعات خطا، شاخص نیکویی برازش و شاخص برازش تطبیقی به‌ترتیب 033/0، 88/0 و 94/0، به­عنوان بهترین مدل انتخاب شد. نتایج کلی نشان داد که مدل شبکه عصبی مصنوعی به‌دلیل لحاظ کردن روابط غیرخطی بین عملکرد و عوامل تأثیرگذار بر آن، کارایی بهتری نسبت به رگرسیون چندمتغیره در تخمین عملکرد داشت. علاوه بر توانایی مدل شبکه عصبی در برآورد عملکرد محصول، مدل‌سازی روابط ساختاری نشان داد که روش اخیر نیز می­تواند توضیحات بیشتری در مورد روابط و تعامل­های همزمان بین متغیرها ارائه کند. به‌طور کلی، کاربرد روش مدل‌سازی روابط ساختاری، با تکیه بر توانایی‌های این روش می‌تواند زمینه ارتقای عملکرد محصولات مختلف را فراهم کند.

کلیدواژه‌ها

عنوان مقاله [English]

Assessment of Relationships between Rose Yield and Soil and Topography Properties Using Multivariate Regression, Artificial Neural Network and Structure Equation Modeling

نویسندگان [English]

  • Morteza Bahmani 1
  • Jahangard Mohammadi 2
  • Isa Esfandiarpour Boroujeni 3
  • Hamidreza Mottaghian 4

1 Dept. of Soil Science, Shahrekord University

2 Professor, Dept. of Soil Science, Shahrekord University

3 Associate Prof, Dept. of Soil Science, Vali-e-Asr Univ. of Rafsanjan

4 Assistant Prof, Dept. of Soil Science, Shahrekord University

چکیده [English]

Abstract
Due to the relationship between crop yield, and soil characteristics and land topography, knowledge and awareness of these characteristics is necessary to achieve sustainable development in agriculture. This study was performed to evaluate and determine the relationships between Rose yield (Rosa Damasceneea Mill) with soil properties and land topography by using Multivariate Linear Regression models (MLR), Artificial Neural Network (ANN) and Structural Equation Modeling (SEM) in Bardsir City, Kerman Province. For this purpose, soil sampling and crop yield were performed in the form of a regular grid pattern. Besides, some topographic features of the land were calculated using digital elevation model (DEM) of the region, and to implement the conceptual models, three theoretical models were designed and tested. The results showed that MLR and ANN models were able to justify 68 and 87 % of the yield variability, respectively, which indicates the higher accuracy of ANN model than MLR in yield estimation. The results of SEM illustrated that Rose yield is mainly controlled by soil chemical properties, topographic features, and soil physical properties, respectively. Different scenarios for SEM showed that simpler models with fewer hidden structures could have a better fitting. Therefore, the first conceptual model of this method with the values of root mean square error, goodness of fit index and comparative fit index of 0.033, 0.88 and 0.94, respectively, was selected as the best model. The overall results showed that the ANN model was more efficient than MLR in yield prediction due to consideration of the nonlinear relationship between crop yield and the factors affecting it. In addition to the ability of the ANN model to estimate crop yield, the SEM also showed that the latter method can provide more explanations about the relationships and simultaneous interactions between variables. In general, the application of SEM method, relying on the capabilities of this method, can improve the yield of various crops.

کلیدواژه‌ها [English]

  • Bardsir of Kerman
  • Comparative fit index
  • Digital Elevation Model
  • Goodness fit index
  • Sustainable agriculture
References
Alexandra K.N., and Bullock D.G. 2000. Correlation of corn and soybean grain yield with topography and soil properties. Agronomy Journal, 92(1): 75-83.
Al-Kanani T., Mackenzi A.F., and Ross G.J. 1984. Potassium status of some Quebec soils: K release by nitric acid and sodium tetraphenylboron as related to particle size and mineralogy. Canadian Journal Soil Science. 64:99-106.
Alvarez R. 2009. Predicting average regional yield and production of wheat in the Argentina Pampas by an artificial neural network approach. European Journal of Agronomy, 30(2): 70-77.
Ayoubi SH.A., and Jalalian A. 2010. Land Evaluation (Agricultural and Natural Resources Secend Edition), Isfahan University of Technology Publication Center, Isfahan, Iran, 385p. (In Persian)
Ayoubi Sh.A., Khormali F., and Sahrawat K.L. 2009. Relationships of barley biomass and grain yields to soil properties within a field in the arid region: Use of factor analysis. Acta Agriculturae Scandinavica, Section B — Soil and Plant Science, 59(2): 107-117.
Babaei F., Vaezi A., Teheri M., Zarrinabadi E., and Eslami F. 2016. Development a regression relationship between rainfed wheat yield and soil properties in a semiarid region, Zanjan Province. Iranian Journal of Soil and Water Research, 46(4): 715-725. (In Persian)
Brahim N., Blavet D., Gallali T., and Bernoux M. 2011. Application of structural equation modeling for assessing relationships between organic carbon and soil properties in semiarid Mediterranean region. International Journal of Environmental Science and Technology, 8(2): 305-320.
Bremner J.M., and Mulvaney C.S. 1982. Total nitrogen. PP. 595-624. In: A. L. Page (Ed.), Methods of Soil Analysis. Agron. No. 9, Part 2: Chemical and Microbiological Properties, 2nd ed., Am. Soc. Argon., Madison, WI, USA.
Cox M.S., Gerard P.D., and Abshire M.J. 2006. Selected soil properties variability and their relationships with yield in three Mississippi fields, Soil science, 171(7): 541-551.
Dion P.A. 2008. Interpreting Structural Equation Modeling Results: A Reply to Martin and Cullen. Journal of Business Ethics. 83: 365–368.
Foroughifar H., Jafarzadah A.A., Torabi Gelsefidi H., Aliasgharzadah N., Toomanian N., and Davatgar N. 2010. Spatial variations of surface soil physical and chemical properties on different landforms of Tabriz plain, Journal of Soil and Water Science, 21(3): 1-21. (In Persian with English abstract)
Gee W., and Bauder J.W. 1986. Particle size analysis. In: Klute A (Eds.), Method of soil analysis. Part 1. SSSA. Madison, Wisconsin Pp. 383-411.
Gholami Sh., Hosseini S.M., Mohammadi J., and Mahini A.S. 2011. Spatial variability of soil macrofauna biomass and soil properties in riparian forest of Karkhe river, Journal of Water and Soil, 25(2):248-257. (In Persian with English abstract)
Goodarzinejad A. 2001. Artificial Intelligence and Modeling. Shahid Chamran University of Ahvaz Publications. 325 p. (In Persian)
Govaerts B., Sayre K.D., and Deckers J. 2006. A minimum data set for soil quality assessment of wheat and maize cropping in the highlands of Mexico. Soil and Tillage Research, 87:163–174.
Green T.R., Erskine R.H., Fogarty E.A., Dunn G.H. and Salas J.D. 2003. Analysis of spatial soil hydraulic properties to investigate soil–water movement and scaling in an agricultural field. American Geophysical Union. 717 p.
Hongfen Z., Ying Z., Feng N., Yonghong D., and Rutian B. 2016. Relative influence of soil chemistry and topography on soil available micronutrients by structural equation modeling. Journal of Soil Science and Plant Nutrition, 16 (4): 1038-1051.
Hoyle R.H. 2012. Handbook of Structural Equation Modeling. 1st (Ed.) New York: The Guilford press. 740 p.
Iqbal J., Read J.J., Thomasson A.J., and Jenkins J.N. 2005. Relationships between soil-landscape and drylnd cotton lint yield. Soil Science Society of America Journal, 69:1-11.
Jenness Jeff. 2013. DEM Surface Tools for ArcGIS, USA, Online available.
Jiang P., and Thelen K.D. 2004. Effect of soil and topographic properties on crop yield in a north-central corn-soybean cropping system. Agronomy Journal. 96: 252–258.
Khadem A., Golchin A., Mashhadi Jafarloo A., Zaree E., and Naseri E. 2014. Effect of Highly Acidified Soil on Soil Nutrient Availability and Corn (Zea mays L.) Growth. Agronomy Journal (Pajouhesh and Sazandegi) No: 107 pp: 1-7. (In Persian with English abstract)
Kashani A., Arab M., Tabaei R., Zeinali H., and Roozban M. 2012. The relationship between flower yield and yield components in Damask Roes in different region of Iran. Agricultural Crop Management (Journal of Agriculture), 14(1): 13-19.
Kaul M., Hill R.L., and Walthall C. 2005. Artificial neural networks for corn and soybean yield prediction. Agricultural Systems, 85: 1-18.
Khodami A., Bouzari S., and Shafiei A. 2011. Morphotectonic Indices of Lalezar Fault in South of Bardsir. Journal of Geoscience. 5(1): 103-110. (In Persian)
Lindsay W.L., and Norvell W.A. 1978. Development of a DTPA soil test for zinc, iron, manganese and copper. Soil Sci. Soc. Am. J. 42: 421–428.
Liu J., Georing C.E., and Tian L. 2001. A neural network for setting target corn yields.  American Society of Agricultural and Biological Engineers, 44: 705-713.
Lopez-Granados F., Jurado-Exposito M., Atenciano S., Garcia-Ferrer A., De la Orden M.S., and Garcia-Torres L. 2002. Spatial variability of agricultural soil parameters in southern Spain. Plant and Soil, 246:97-105.
Mansour Ghanaei F., Samieezadeh H., Rabaie B., and Shoaii M. 2014. Study the relationship between yield and yield components in tobacco (Nicotiana tabacum L.) varieties. Applied Field Crop Resarch. 27: 29-37.
Marcus V.S., Seldon A., and Gama-Rodrigues A.C. 2017. Structural equation modeling for the estimation of interconnections between the P cycle and soil properties. Nutrient Cycling in Agroecosystems,14: 225-232.
Mehnatkesh A. 2008. Soil-landscape modeling and rainfed wheat yield prediction using different models in some regions of central Zagros. Thesis for the degree of Ph.D. Department of Soil Science, Isfahan University of Technology. Iran. (In Persian)
Menhaj M. 2003. Basics of Neural Networks (Computational Intelligence). Amir Kabir University of Technology. 715 pages. (In Persian)
Miao Y., Mulla D.J., and Robert P.C. 2006. Identifying important factors influencing corn yield and grain quality variability using artificial neural networks. Precision Agriculture, 7: 117-135.
Mohammadi J. 2018. Pedomining, Volume 9, Structure Equation Modeling. Pelk Publishing, 396 pages. (In Persian)
Nelson D.W., and Sommers L.E. 1982. Total carbon, organic carbon, and organic matter, p. 539-579. In: A. L. Page (Ed.) Methods of Soil Analysis Part 2. 2nd Ed. Agron. Monogr 9. ASA and SSSA, Madison, WI.
Norouzi M., Ayoubi S., Jalalian A., Khademi H., and Dehghani A.A. 2010. Prediction rainfed wheat quality by artificial neural network using terrain and soil characteristics. Acta Agriculturae Scandinavica, Section B - Soil and Plant Science. 60: 341-352.
Olsen S.R., and Sommers L.E. 1982. Phosphorus. PP. 403-430. In: A. L. Page (Ed.), Methods of soil analysis, Agron. No. 9, Part2: Chemical and Microbiological Properties, 2nd ed., Am. Soc. Agron., Madison, WI, USA.
Page A.L., Miller R.H., and Keeny D.R. 1982. Methods Methods of soil analysis, Part 1: Chemical and microbiological properties. Soil Science Society of America. Madison. Wisconsin, pp. 1-12.
Pour-mohammadali B., Hosseinifard J., Salehi MH., and Shirani H. 2018. Modeling of Pistachio Yield Using Linear Multivariate Regression and Artificial Neural Network. National Conference on Scientific Approaches in the Green Gold Industry, Pistachio. Islamic Azad University of Moghan Branch, 6 p. (In Persian)
Shukla M.K., Lal R., and Ebinger M. 2004. Principal component analysis for Predicting corn biomass and grain yields. Soil Science, 169: 215-224.
Stage F.K., Carter H.C., and Nora A. 2004. Path analysis: an introduction and analysis of a decade of research. Journal of Educational Research, 98(1): 5-12.
StatSoft Inc. 2004. Electronic statistics textbook (Tulsa, OK, USA).
Zeinali H., Tabaei S.R., Asgarzadeh M., Kiyanipor A., and Abtahi M. 2007. Study the relationship between yield and flower yield components in Rosa damascena Mill. Genotypes of. Iranian Journal of Medicinal and Aromatic Plants. 23(2):195-203