تخمین عملکرد گندم آبی با استفاده از روش الگوریتم ترکیبی شبکه های عصبی مصنوعی و الگوریتم ژنتیک

نوع مقاله : مقالات پژوهشی

نویسندگان

• علی باریکلو ¹
• پریسا علمداری ¹
• کامران مروج ¹
• مسلم ثروتی ²

¹ دانشگاه زنجان

² دانشگاه ارومیه

https://doi.org/10.22067/jsw.v31i3.56158

چکیده

از اهداف کشاورزی پایدار افزایش راندمان تولید محصولات کشاورزی با اعمال مدیریت‌های صحیح بوده و لازمه آن درک کامل‌تر روابط بین میزان تولید محصول با ویژگی‌های خاک و محیط می‌باشد. نخستین قدم یافتن روش‌های مناسبی است که توانایی تعیین روابط صحیح بین ویژگی‌های اراضی با مقدار عملکرد محصول باشد. هدف از این مطالعه بررسی کارایی مدل ترکیبی ژنتیک-عصبی در برآورد عملکرد گندم آبی در غرب شهرستان هریس می‌باشد. منطقه مطالعاتی در شمال‌شرق تبریز واقع شده و رژیم حرارتی و رطوبتی خاک به‌ترتیب مزیک و اریدیک هم مرز با زریک می‌باشد. گندم، هندوانه و یونجه از مهم‌ترین محصولات زراعی منطقه است. بدین منظور تعداد 80 خاکرخ در مزارع گندم انتخاب و از هر افق ژنتیکی نمونه خاک اخذ و به آزمایشگاه منتقل و تجزیه‌های فیزیکی و شیمیایی روی نمونه‌ها صورت گرفت. جهت مدل‌سازی لایه‌های ورودی شامل ویژگی‌های شیمیایی، فیزیکی، زمین‌نما و خروجی عملکرد مشاهده شده گندم آبی می‌باشد. نتایج آنالیز حساسیت نشان داد که نیتروژن کل، فسفر قابل جذب، شیب، درصد سنگریزه، واکنش خاک و ماده آلی به عنوان ویژگی‌های اراضی مهم در عملکرد گندم در اراضی مورد مطالعه هستند. نیتروژن کل خاک به‌عنوان موثرترین ویژگی در کیفیت و کمیت عملکرد گندم بر اساس ماتریس همبستگی پیرسون ایجاد شده بین ویژگی‌ها و عمکرد می‌باشد. کارایی مدل ژنتیک- عصبی با موفقیت برای تشریح رابطه بین عملکرد گندم و ویژگی‌های زودیافت صورت گرفت، به‌طوری‌که دارای ضریب تببین بالا (87/0) و میانگین انحراف مربعات خطا کم (5/473) بود. نهایتاً می‌توان نتیجه گرفت، مدل هیبریدی می‌تواند به‌عنوان یک ابزار قدرتمند در تخمین عملکرد گندم باشد.

کلیدواژه‌ها

• کشاورزی پایدار
• مدلسازی
• مدیریت
• ویژگی های دیریافت و زودیافت

عنوان مقاله [English]

Prediction of Irrigated Wheat Yield by using Hybrid Algorithm Methods of Artificial Neural Networks and Genetic Algorithm

نویسندگان [English]

• Ali Barikloo ¹
• Parisa Alamdari ¹
• kamran Moravej ¹
• Moslem Servati ²

¹ University of Zanjan

² Urmia University

چکیده [English]

Introduction: In recent decades, the most important issue for agricultural activities is maximizing the productions. Today, wheat is grown on more lands than any other commercial crops and continues to be the most important food grain source for humans. Sustainable agriculture is a scientific activity based on ecological principles with focus on achieving sustainable production. It requires a full understanding of the relationships between crop production with soil and land characteristics. Furthermore, one of the objectives of sustainable agriculture is enhancing the agricultural production efficiency through applying proper management, which requires a deep understanding of relationships between production rate, soil and environment characteristics. Hence, the first step in this process is finding appropriate methods which are able to determine the correct relationships between measured characteristics of soil and environment with performance rate. The aim of this study was evaluating the performance of neuro-genetic hybrid model in predicting wheat yield by using land characteristics in the west of Herris City.
Materials and Methods: The study area was located in the northwest of east Azarbaijan province, Heris region. In this study, 80 soil profiles were surveyed in irrigated wheat farms and soil samples were taken from each genetic horizon for physical and chemical analyses. In this region, soil moisture and temperature regimes are Aridic border to Xeric and Mesic, respectively. The soils were classified as Entisols and Aridisols. We used 1×1 m woody square plots in each profile to determine the amounts of yield. Because of nonlinear trend of yield, a nonlinear algorithm hybrid technique (neural-genetics) was used for modeling. At first step, the average weight of soil characteristics (from depth of 100 cm) and landscape parameters of selected profiles were measured for modeling according to the annual growing season of wheat. Then, land components and wheat yield were considered as inputs and output of model, respectively. For this reason, genetic algorithm was investigated to train neural network. Finally, estimated wheat yield was obtained using input data. Root mean square error (RMSE) and Coefficient of determination (r2), Nash-Sutcliffe Coefficient (NES) indices were used for assessing the method performance.
Results and Discussion: The sensitivity analysis of model showed that soil and land parameters such as total nitrogen, available phosphorus, slope percentage, content of gravel, soil reaction and organic matter percentage played an important role in determining wheat yield in the studied area. The soil organic matter and total nitrogen had the highest and lowest correlation with wheat yield quantity and quality, respectively, indicating the total nitrogen was the most important soil property for determination of wheat yield in our studied area. We found that network learning process based on genetic algorithms in the learning process had lower error. The findings showed that beside of confirming the desired results in the case of using sigmoid activation function in the hidden layer and linear activation function in the output layer of all neural networks, it is demonstrated that the proposed hybrid technique had much better results. These findings also confirm better prediction ability of neural network based on error back propagation algorithm or Levenberg-Marquardt training algorithm compared to other types of neural network confirms.
Conclusion: Using nonlinear techniques in modeling and forecasting wheat yield due to its nonlinear trend and influencing variables is inevitable. Recently, genetic algorithms and neural network techniques is considered as the most important tools to model nonlinear and complex processes. Despite the advantages of these techniques there are a lot of weaknesses. Imposing specific conditioned form by researchers in the techniques of genetic algorithms and stopping neural network learning at the optimal points are the main weaknesses of these techniques, while searching for global optimal point and not imposing a specific functional forms are the robustness of genetic algorithm techniques and neural networks, respectively. Results of this study indicated that the proposed hybrid technique had much better results. Correlation coefficient (0.87) and average deviation square error (473.5) were high and low, respectively. It can be concluded that the surveyed soil properties have very strong relationship with the yield. Implementation of appropriate land management practices is thus necessary for improving soil and land characteristics to maintain high yield, preventing land degradation and preserving it for future generations required for sustainable development.

کلیدواژه‌ها [English]

• Hard and Readily measured properties
• management
• Modelling
• Sustainable agriculture

مراجع

1. Ashraf S.H., Ashraf V., and Abbaspour H. 2011. Assessment of land production potential for barley using geographic information system (GIS) method. Indian Journal of Science and Technology, 4(12):1775-1777.

2. Andonie R. 2010. Extreme Data Mining: Inference from small data sets. International Journal of Computes Communications and Control, 5(3): 280-291.

3. Allen R.G., Pereira, L.S Raes D., and Smith M. 1998. Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. FAO, Rome, 300(9):D05109.

4. Ayoubi SH.A Givi J., Jalalian A., and Amini., A.M. 2002. Quantitative land suitability evaluation in north Baron Region (esfahan province) for wheat, barley, maize and rice, Journal of Agricultural and Natural resource research and Technology, 3(6): 105-118. (In Persian).

5. 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).

6. Azadeh A., Saberi M., Gitiforouz Z., and Saberi Z. 2009. A Hybrid simulation adaptive network based fuzzy inference system for improvement of electricity consumption estimation. Expert System Applied Journal, 36(8): 11108-11117.

7. Bremner J.M. 1965. Inorganic forms of nitrogen. In: Black (Ed.), Methods of soil analysis. Part 2, Monograph NO, 9: 1179-1232. Am. Soc. Agron., Madison, WI.

8. De la Rosa D., Moreno JA., Garcia LV., and Almorza, J. 1992. Microleis: A microcomputer-based Mediterranean land evaluation information system. Soil Use and Management 8: 89-96.

9. Demuth H., and Beale, M. 2000. Neural Network Toolbox Users Guideline. By The Math Works, Inc, Version 4, 840pp.

10. Dep K., and Beyer G. 2001. Self-adaptive Genetic Algorithms with Simulated Binary Cross over. Evolution Computer Journal, 9:197-221.

11. Eftekhar Ardebili, M. 2004. Artificial Neural Network Modelling. MSc Thesis of AL Zahra university of Tehran, Tehran.

12. Etedali1 S., Givi J., and Nouri M.R. 2012. Comparison Between Land Production Potential Prediction for Maize, Using FAO and Wageningen Models and Assessment of Management Level for Its Cultivation Around Shahrekord City. Journal of Water and soil, 26 (4): 873-855. (in Persian).

13. Gee G. W., and Bauder J. W. 1986. Particle size analysis. p. 383-411. In: A. Klute (Ed), Methods of soil analysis. Part I. Physical and mineralogical methods, 2nd ed., Agronomy Monograph. No: 9. ASA and SSSA. Madison, WI.

14. Halder J.C. 2013. Land suitability assessment for crop cultivation by using remote sensing and GIS. Journal of Geography and Geology, 5(3): 65-78.

15. Jalalian A., Rostaminia M., Ayoubi SH.A., and Amini Am. Qualitative, Quantitative and economic land suitability evaluation for wheat, maize and sesame in Mehran plain. Journal of Agricultural and Natural resource research and Technology, 4(3): 393-403. )In Persian).

16. Kim S., and Kim S.H. 2008. Neural Networks and genetic algorithm approach for nonlinear evaporation and evapotranspiration modeling. Journal of Hydrology, 351: 299-317.

17. Koza J.R. 2008. htpp://www.genetic-programming.com,The home page of john R. Koza at Genetic Programming Lnc.

18. Liu J., and Goering C.E. 1999. Neural network for setting target corn yields. ASAE paper 99-3040, Toronto, Ontario,Canada, July 18-21.

19. Manhaj, M.B. 2005. Fundamental of Artificial Neural Network. Amir kabir University of Technology Center, 712p.

20. McLean E.O. 1982. Soil pH and Lime requirement. Pp. 199-224. In: Page AL, Miller RH and Keeney DR (eds). Methods of Soil Analysis. Part 2. Chemical and Micromorphological Properties. 2nd ed. Agron, Monogr. 9. ASA and SSSA, Madison, WI.

21. Mohammadi J. 2006. Pedometrics: Classical Statistics. Pelk publication. (in Persian).

22. Mohammadi J. 2006. Pedometrics: Fuzzy Systems Theory. Pelk publication. (in Persian).

23. Nelson R.E. 1982. Carbonate and gypsum. Pp. 181-197. In: Page AL, Miller RH and Keeney DR (eds). Methods of Soil Analysis. Part 2. Chemical and Microbiological Methods. 2nd ed. Agron. Monogr. 9. ASA and SSSA, Madison, WI.

24. Nelson R.E., and Sommers L. 1982. Total carbon, organic carbon and organic matter. Pp. 532-581. In: Page AL, Miller RH and Keeney DR (eds). Methods of Soil Analysis. Part 2. Chemical and Microbiological Methodes. 2nd ed. Agron. Monogr. 9. ASA and SSSA, Madison, WI.

25. Newhall F., and Berdanier C.R. 1996. Calculation of soil moisture regimes from the climatic record. Natural Resources Conversations Service, Soil Survey Investigation. Report No. 46, 13p.

26. Norouzi M., Ayoubi SH.A., Jalalian A., Khademi H. and Dehghani, A. 2010. Predicting rainfed wheat quality and quantity by artificial neural network using terrain and soil characteristics. Acta Agriculturae Scandinavica Section B–Soil and Plant Science, 60(4): 341-352.

27. Olsen S.R., Cole C.V., Watanable, F.S., and Dean, L.A. 1954. Estimation of available phosphorus in soil by extraction with sodium bicarbonate. USDA. Circ. 939. U. S. Government. Print. Office, Washington, DC.

28. Sayegh A.H., Khan P., and Ryan, J. 1978. Factors affecting gypsum and cation exchange capacity determination in gypsiferous soils. Soil Science Journal, 125: 294-300.

29.Schoeneberger P.J., Wysocki D.A., Benham E.C. and Broderson, W.D. 2006. Field Book

for Describing and Sampling Soils. Natural Resources Conservation Service, USDA,National Soil Survey Center, Lincoln, NE, 280p

30. Servati M, Jafarzadeh, A.A., Ghorbani M.A., Shahbazi F. and Davatgar N. 2014. Comparison of the FAO and Albero Models, in Prediction of Irigated Wheat Production Potentials in the Khajeh region.Water and Soil Science Journal, 24: 1-14. (in Persian).

31. Sette S., and Boullart L. 2001. Genetic programming: principles and applications. Engineering Applications of Artificial Intelligence, 14: 727–736.

32. Shite N, Khaje. Geological survey and Mineral Exploration of Iran. 2006. Geology Map of Iran, 1:100000series.

33. Sohrabi vafa H. 2012. Forecasting of energy demand in Iran by soft computation technic. Msc thesis of shahid abbaspour energy and water Industry university.

34. Soil Survey Field and Labra Methods Manuals. 2014. Soil Survey Investigations Report No.51.Version.2. Issued 2014.

35. Sudduth K.A., Drummond S.T., Birrell S.J., and Kitchen, N.R. 1996. Analysis of spatial factors influencing crop yield, in Proc. 3rd Int. Conf. On Precision Agriculture, P.C. Robert et al. (ed.), pp. 129-140.

36. Sys C., Van Ranset E., and Debaveye J. 1991a. Land Evaluation, Part I, Principle in Land Evaluation and Crop Production Calculation, International Training Center for Post Graduate Soil Scientists, Ghent University, Ghent., Belgium.

37. Sys C., Van Ranset E., and Debaveye J. 1991b. Land Evaluation, Part II, Methods in Land Evaluation. International Training Center for Post Graduate Soil Scientists, Ghent University, Ghent, Belgium.

38. Taghizadeh Mehrjerdi R., Seyedjalali S.A., and Sarmadian F. 2016. Prediction of Corn Spatial yield by soil digital mapping in Gotend region (Khuzestan Province, IRAN). Jornal of plant production, 19 (4): 70-96.

39. Yang Y., and Cai Y. 2000. Sustainable evaluation on rural resources, environment and development of China – the SEEA method and its applications. Acta Geographica Sinica, 55 (5): 596–606.