تعیین ویژگی‌های موثر بر عملکرد زعفران با استفاده از الگوریتم ترکیبی ژنتیک- شبکه عصبی مصنوعی

نوع مقاله : مقاله کامل علمی پژوهشی

نویسندگان

1 دانشجوی دکتری، علوم خاک،دانشکده کشاورزی،دانشگاه شهرکرد،شهرکرد،ایران

2 استاد، گروه علوم خاک،دانشکده کشاورزی،دانشگاه شهرکرد

3 استادیار، گروه تولیدات گیاهی، دانشکده کشاورزی، دانشگاه تربت حیدریه.

4 استاد، گروه علوم و مهندسی خاک،دانشکده کشاورزی، دانشگاه رفسنجان

5 دانشیار، گروه علوم خاک،دانشکده علوم کشاورزی، دانشگاه گیلان

چکیده

سابقه و هدف:
زعفران یکی از مهم‌ترین گیاهان اقتصادی و دارای اهمیت صادرات در کشور می‌باشد. جهت تعیین ارتباط عملکرد زعفران و تأثیرپذیری آن از ویژگی‌های اقلیمی، خاکی و مدیریتی، و بدلیل پیچیدگی زیاد روابط بین این متغیرها، بررسی قابلیت مدل ترکیبی الگوریتم ژنتیک- شبکه عصبی مصنوعی (GA-ANN) برای شناسایی یک زیر مجموعه مناسب از ویژگی‌های موثر بر عملکرد گیاه زعفران و نیز تعیین میزان اهمیت هر یک از این ویژگی‌ها (آنالیز حساسیت) اهداف پژوهش حاضر می‌باشد.
مواد و روش‌ها:
این پژوهش در 100 مزرعه (مزارع 3 تا 5 ساله) زیر کشت زعفران از استان‌های مختلف خراسان (رضوی، شمالی و جنوبی)، اصفهان، چهارمحال بختیاری، گیلان، فارس و البرز اجرا گردید. از هر کدام از مزارع، یک نمونه مرکب خاک از عمق صفر تا سی‌سانتی‌متری، جمع‌آوری و به آزمایشگاه منتقل شدند. ویژگی‌های فیزیکی و شیمیایی خاک براساس روش-های استاندارد اندازه گیری شد. ویژگی‌های اقلیمی هر منطقه از نزدیک‌ترین ایستگاه‌ مناطق مورد مطالعه جمع‌آوری گردید. هم‌چنین، برای هر مزرعه یک پرسش‌نامه به منظور جمع‌آوری اطلاعات مدیریتی و تعییین مقدار عملکرد تهیه شد. به منظور انتخاب یک زیرمجموعه مناسب از ویژگی‌های مؤثر بر عملکرد زعفران، از مدل ترکیبی الگوریتم ژنتیک-شبکه عصبی مصنوعی(GA-ANN) استفاده گردید. میزان حساسیت عملکرد نسبت به تغییرات ویژگی‌های خاک، اقلیم و مدیریت انتخاب شده توسط مدل ترکیبی GA-ANN به روش استات سافت (Statsoft) تعیین شد.
یافته‌ها:
در انتخاب ویژگی‌های موثر بر عملکرد با استفاده از الگوریتم ژنتیک-شبکه عصبی مصنوعی از بین همه‌ی ترکیب‌های ممکن، ترکیبی با 22 ویژگی که کمترین خطا با کمترین تعداد ورودی را داشت، به عنوان بهترین ترکیب در نظر گرفته شد. ویژگی‌های انتخاب شده به وسیله الگوریتم شامل میانگین دمای حداقل چرخه رشد، میانگین دمای حداقل مطلق چرخه رشد، حداکثر رطوبت نسبی چرخه رشد، میانگین رطوبت نسبی چرخه رشد، میانگین ساعات آفتابی هر روز چرخه رشد، میانگین دمای چرخه رشد، دما در اولین آبیاری، میانگین حداکثر رطوبت نسبی چرخه رشد، کربنات کلسسیم معادل خاک، ظرفیت تبادل کاتیونی خاک، نیتروژن کل خاک، آهن، روی و منگنر قابل استفاده (عصاره گیری شده با DTPA) در خاک، نوع کاشت، سیستم پرورش، روش مبارزه با علف هرز، سیستم آبیاری، میانگین تعداد نوبت آبیاری در سال، عمق کاشت، میانگین وزن پیاز و تراکم کاشت می‌باشند. اهمیت متغیرهای انتخاب شده در ارتباط با مقدار عملکرد، به روش استات سافت (Statsoft) مشخص شد. تمامی ویژگی-هایی که در انتخاب ویژگی به عنوان عوامل موثر بر عملکرد شناخته شده بودند با آنالیز حساسیت هم جزو ویژگی‌های مهم و موثر بر عملکرد بودند. مهم‌ترین ویژگی‌های اقلیمی موثر بر عملکرد به ترتیب، شامل میانگین حداکثر رطوبت نسبی، میانگین دما، دمای حداقل، دمای حداقل مطلق در چرخه رشد و دما در اولین آبیاری بود. از میان ویژگی‌های خاکی، به ترتیب، منگنز، روی، آهن قابل استفاده (عصاره گیری شده با DTPA)، ظرفیت تبادل کاتیونی، نیتروژن کل و کربنات کلسیم معادل خاک از متغیرهای موثر بر عملکرد گیاه زعفران بودند. از نظر مدیریت، به ترتیب، مدیریت صحیح آبیاری، وزن و تراکم پیاز زعفران، رعایت عمق مناسب کشت و مدیریت صحیح علف‌های هرز، تاثیر بسزایی بر عملکرد زعفران داشتند.
نتیجه‌ گیری:
نتایج نشان داد که الگوریتم هیبرید شبکه عصبی مصنوعی می‌تواند یک زیر مجموعه مناسب از ویژگی‌های موثر بر عملکرد زعفران را از میان متغیرهای خاک، اقلیم و مدیریت در متاطق مطالعاتی، انتخاب و شناسایی کند. این نتایج می‌تواند در مدیریت پایدار اراضی و نیز تعیین محل مناسب‌تر برای کشت زعفران، کاربرد بسزایی داشته باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Determining Effective Features on Saffron Performance Using a Hybrid Genetic Algorithm-Artificial Neural Network

نویسندگان [English]

  • Parisa Kabiri samani 1
  • Mohammad Hassan Salehi 2
  • Hamed Kaveh 3
  • Hossein Shirani 4
  • Nafiseh Yaghmaeian Mahabadi 5
1 Soil Science.Faculty of Agriculture.Shahrekord University.Shahrekord.Iran
2 Professor, Department of Soil Science.Faculty of Agriculture.Shahrekord University, Shahrekord, iran
3 Assistant Professor, Department of Plant Production, Faculty of Agriculture, Torbat Heydariyeh University.
4 Professor, Dept. of Soil Science and Engineering, Faculty of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran.
5 Associated Professor, Department of Soil Science, Faculty of Agricultural Sciences, University of Guilan, Iran
چکیده [English]

Background and Objectives
Saffron is one of the most important economic plants and holds significant export value in the country. To determine the relationship between saffron yield and its influence by climatic, soil, and management features, and due to the complexity of the relationships between these variables; the present study aims to investigate the capability of the hybrid Genetic Algorithm-Artificial Neural Network (GA-ANN) model to identify an appropriate subset of features affecting the saffron yield and to determine the importance of each of these features.
Materials and Methods
This research was conducted in 100 farms (3 to 5 years old) under saffron cultivation from various provinces, including Khorasan (Razavi, North, and South), Isfahan, Chaharmahal and Bakhtiari, Gilan, Fars, and Alborz. From each farm, a composite soil sample was collected from a depth of zero to thirty centimeters and transferred to the laboratory. The physical and chemical properties of the soil were measured based on standard methods. Climatic characteristics of each region were collected from the nearest meteorological stations of the studied areas. Additionally, for each farm, a questionnaire was prepared to gather management information and determine the yield. To select an appropriate subset of features influencing saffron yield, the hybrid GA-ANN model was used. The sensitivity of the yield to changes in the soil, climate, and management features selected by the GA-ANN hybrid model was determined using the Statsoft method.
Results
Selection of effective features on yield using Genetic Algorithm-Artificial Neural Network (GA-ANN) Among all possible combinations, the combination with 22 features that had the least error and the least number of inputs was considered the best combination. The features selected by the algorithm included: the average minimum temperature of the growth cycle, the average absolute minimum temperature of the growth cycle, the maximum relative humidity of the growth cycle, the average relative humidity of the growth cycle, the average daily sunshine hours of the growth cycle, the average temperature of the growth cycle, the temperature at the first irrigation, the average maximum relative humidity of the growth cycle, soil calcium carbonate equivalent, soil cation exchange capacity, total soil nitrogen, soil iron, zinc, and manganese, planting type, cultivation system, weed control method, irrigation system, average number of irrigation rounds per year, planting depth, average bulb weight, and planting density. The importance of the selected variables in relation to the yield was determined using the Statsoft method. All features identified as influential factors on yield in feature selection were also among the important and effective features on yield in sensitivity analysis. The most important climatic features affecting yield were, in order, the average maximum relative humidity, average temperature, minimum temperature, absolute minimum temperature during the growth cycle, and temperature at the first irrigation. Among the soil features, in order, manganese, zinc, iron, cation exchange capacity, total nitrogen, and soil calcium carbonate equivalent were the influential variables on saffron yield. In terms of management, correct irrigation management, bulb weight and density, proper planting depth, and proper weed management had a significant impact on saffron yield.
Conclusion
The results showed that using the hybrid artificial neural network algorithm to select and identify an appropriate subset of features affecting saffron yield among soil, climate, and management variables in the study areas, while saving time and cost, can yield more satisfactory results from pattern recognition and data processing processes. These results can have significant applications in sustainable land management and in determining the more suitable locations for saffron cultivation.

کلیدواژه‌ها [English]

  • Sensitivity analysis
  • artificial neural network
  • saffron
  1. Ziyaratniya, S. M., Filabi, A., & Senobari, S. (2019). Effect of concentration of different growth regulators on onion dormancy period and saffron flower yield in hydroponic conditions. Saffron Research, 7(1), 43-54. [In Persian]. https://doi.org/10.22077/jsr.2018.1839.1070
  2. Cardone, L., Castronuovo, D., Perniola, M., Cicco, N., & Candido, V. (2020). Saffron (Crocus sativus), the king of spices: An overview. Scientia Horticulturae, 272, 109560. https://doi.org/10.1016/j.scienta.2020.109560
  3. Shahnoushi, N., Abolhassani, L., Kavakebi, V., Reed, M., & Saghaian, S. (2020). Economic analysis of saffron production. Woodhead Publishing, 337-356. https://doi.org/10.1016/B978-0-12-818638-1.00021-6                                          
  4. Omidi, H., Naghdi Badi, H., Golzad, A., Torabi, H., & Footoukian, M. (2009). The effect of chemical and biofertilizer source of nitrogen on qualitative and quantitative yield of saffron (Crocus sativus L.). Journal of Medicinal Plants, 8(30), 98-109. [In Persian]. dor: 20.1001.1.2717204.2009.8.30.11.4
  5. Zakiaghl, M., Khorramdel, S., Koocheki, A., Nabati, J., Nezami, A., Mirshamsi Kakhki, A., Mollafilabi, A., Rezvani Moghaddam, P., & Nassiri Mahallati, M. (2021). Criteria for production of standard pathogen- free saffron corms. Saffron Agronomy & Technology, 9(2), 121-141. [In Persian]. https://doi.org/10.22048/jsat.2021.233278.1401
  6. Khakural, B.R., Robert, P.C., & Huggins, D.R. (1999). Variability of corn/soybean yield and soil/landscape properties across a southwestern Minnesota landscape. In Proceedings of the fourth international conference on precision agriculture, 573-579. https://doi.org/10.2134/1999.precisionagproc4.c51 
  7. Pourmohammadali, B., Hosseinifard, S. J., Salehi, M. H., Shirani, H., & Boroujeni, I. E. (2019). Effects of soil properties, water quality and management practices on pistachio yield in Rafsanjan region, southeast of Iran. Agricultural water management, 213, 894-902. https://doi.org/10.1016/j.agwat.2018.12.005         
  8. Bahmani, M., Mohammadi, J., Esfandiarpour Boroujeni, I., & Mottaghian, H. (2020). Assessment of relationships between rose yield and soil and topography properties using multivariate regression, artificial neural network and structure equation modeling. Applied Soil Research, 8(2), 142-157.
  9. Schultz, A., Wieland, R., & Lutze, G. (2000). Neural networks in agroecological modelling—stylish application or helpful tool?. Computers and Electronics in Agriculture, 29(1-2), 73-97. https://doi.org/10.1016/S0168-1699(00)00137-X
  10. Shirani, H., Habibi, M., Besalatpour, A. A., & 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. https://doi.org/10.1016/j.geoderma.2015.05.002
  11. Wu, B., Zhang, L., & 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. DOI: https://doi.org/10.1109/TGRS.2013.2263510
  12. Gee, G.W., & Bauder, J.W. (1986). Particle size analysis. In: Klute, A. (ed.) Methods of Soil Analysis. Part 1. Physical properties. American Society of Agronomy. Madison. Wisconsin. 383-411.
  13. Bremner, J. M., & Mulvaney, C. S.(1982). Nitrogen total. In: Page, A. L.(Ed.), Methods of Soil Analysis, Part 2. American Society of Agronomy. Madison. Wisconsin. U.S.A. Pp: 595-624.
  14. Nelson, R.E. (1982). Carbonate and gypsum. In: Prade A.L. et al. (eds.) Methods of Soil Analysis. Part 2. Chemical and microbiological properties. American Society of Agronomy. Madison. Wisconsin. 9.181-197.
  15. Al-Kanani, T., Mackenzie, A. F., & Ross, G. J. (1984). Potassium status of some Quebec soils: K released by nitric acid and sodium tetra phenyl boron as related to particle size and mineralogy. Canadian journal of soil science, 64(1), 99-106. https://doi.org/10.4141/cjss84-009
  16. Olsen, S. R., & Sommers, E. L. (1982). Phosphorus soluble in sodium bicarbonate. Methods of soil analysis, part, 2, 404-430.
  17. Lindsay, W. L., & Norvell, W. (1978). Development of a DTPA soil test for zinc, iron, manganese, and copper. Soil Science Society of America journal, 42(3), 421-428.
  18. Page A.L., Miller, R.H., & Keeny, D.R., (1982). Methods of soil analysis, Part 1: Chemical and microbiological properties. Soil Science Society of America. Madison. Wisconsin, 1-12.
  19. Knudsen, D., Peterson, G. A., & Pratt, P. F. (1982). Lithium, sodium, and potassium. Methods of soil analysis: part 2 chemical and microbiological properties, 9, 225-246. https://doi.org/10.2134/agronmonogr9.2.2ed.c13
  20. Ranjbar, A., Emami, H., Karimi, A. R., & Khorassani, R. (2015). Determining the most important soil properties affecting the yield of saffron in the Ghayenat area. Water and Soil, 29(3), 673-682. [In Persian]. https://doi.org/10.22067/jsw.v0i0.31230
  21. Sharifi, H., Nabipour, Z., & Tavakkoli Kakhki, H. R. (2021). Evaluation of the effect of compensatory behavior of planting density, mother corm weight and planting depth on vegetative characteristics and yield of saffron (Crocus sativus). Saffron Agronomy and Technology, 9(3), 227-248. [In Persian]. https://doi.org/10.22048/jsat.2021.272865.1420.  
  22. Shirani, H., (2018). Artificial Neural Networks with an Application in Agricultural and Natural Resource Sciences, 2nd Ed. Press. Vali-E-Asr University of Rafsanjan. 320p. [In Persian].  
  23. Wilding, L.P. & Dress, L.R. (1983). Spatial variability and pedology. In Wilding, L.P., Smeckand, N.E. & Hall G.F. (eds.), Pedogenesis and Soil Taxonomy: Concepts and Interactions. Elsvier Science Pub. 83-116.
  24. Bayat, M., Rahimi, M., & Ramezani, M. (2016). Determining the most effective traits to improve saffron (Crocus sativus) yield. Physiology and molecular biology of plants, 22, 153-161. https://doi.org/10.1007/s12298-016-0347-1
  25. Nassiri Mahallati, M., & Koocheki, A., (2019). Yield monitoring for wheat and sugar beet in Khorasan province: 1- Analysis of methods for estimating potential yield. Journal of Agroecology, 16(4), 723-741. [In Persian]. http://dx.doi.org/10.22067/gsc.v16i4.62556
  26. Vafaei, M., Ziaei, S., Mohammadi, H., & Borazjani, M.A.,(2024).Spatial analysis of the impact of climate change on saffron yield (case study of the cities of Khorasan Razavi Province, North and South).Journal of Agricultural Economics Researches. 16(2). 91. [In Persian]. https://doi.org/10.30495/jae.2024.29492.2307
  27. Koocheki, A., & Khajeh-Hosseini, M. (Eds.). (2020). Saffron: science, technology and health. Woodhead Publishing. 563p.
  28. Rashed-Mohassel, M. H. (2020). Evolution and botany of saffron (Crocus sativus) and allied species. In A. Koocheki & M. Khajeh-Hosseini (Eds.), Saffron: science, technology and health. Elsevier. 37-55. https://doi.org/10.1016/B978-0-12-818638-1.00004-6.
  29. Pirasteh-Anosheh, H., Hashemi, S. E., Del Borghi, A., Spasiano, D., Rad, M., & Race, M. (2022). Feasibility study of saffron cultivation using a semi-saline water by managing planting date, a new state-ment. Environmental Research, 203, 111853. https://doi.org/10.1016/j.envres.2021.111853
  30. Koozegaran S., Mousavi Baygi, M., Sanaeinejad, H., & Behdani, M. (2011). Study of the minimum, average and maximum temperature in South Khorasan to identify relevant areas for saffron cultivation using GIS. Soil and Water, 25, 892-904. [In Persian]. https://doi.org/10.22067/jsw.v0i0.10257
  31. Molina, R. V., García-Luis, A., Coll, V., Ferrer, C., Valero, M., Navarro, Y., & Guardiola, J. L. (2004). Flower formation in the saffron crocus (Crocus sativus). The role of temperature. Acta Horticulturae, 39-48.    https://doi.org/10.17660/ActaHortic.2004.650.
  32. Bashiri, M., Seyyidi, S.M., & Tosan, M., (2014). The effect of the number of sunshine hours on saffron yield in Khorasan Razavi Province. third national ranking of the latest scientific and saffron rankings in 2014, National Article. http://irdoi.ir/532-012-714-456
  33. Hashemi, S. E., Madahhosseini, S., Pirasteh-Anosheh, H., Sedaghati, E., & Race, M. (2022). The role of nitrogen in inducing salt stress tolerance in crocus sativus l.: Assessment based on plant growth and ions distribution in leaves. Sustainability, 15(1), 567. https://doi.org/10.3390/su15010567                                                        
  34. Aminifard, M.H., Shakeri, M., Behdani, M.A., & Tabatabaei, S.J.,(2022).Effect of Height Plant Density and Corm Weight on Vegetative, Reproductive and Photosynthetic Pigments of Saffron (Crocus sativus). Saffron Research, 10(1), 1-13‎ [In persian]. https://doi.org/10.22077/jsr.2018.1579.1061
  35. Parsapour, F., Moghaddam, P. R., & Khorramdel, S. (2020). Optimizing the effect of mother corm and urban waste compost levels on flower and corm yield of saffron using surface-response modeling in the first year. Saffron Agronomy & Technology, 8(2), 165-184. [In Persian]. https://doi.org/10.22048/jsat.2019.184094.1350
  36. Tavakkoli-Kakhki, H.R., Sharifi, H.R., & Nabipour, Z., (2020). Assessment of the effects of plant density, vegetation covering, and shading on regulation of soil temperature and yield of saffron (Crocus sativus). Saffron Agronomy and Technology, 8 (4), 527-542. [In Persian]. https://doi.org/10.22048/jsat.2020.232941.1397
  37. MAJ (Ministry of Agriculture Jihad of the I.R. of Iran)., (2018). Planning and Economics Department, Statistics Bank of Iranian Agriculture. http://www.maj.ir/english/Statistic/Default.
  38. Yarami, N., & Sepaskhah, A. R. (2015). Saffron response to irrigation water salinity, cow manure and planting method. Agricultural Water Management, 150, 57-66. http://dx.doi.org/10.1016/j.agwat.2014.12.004
  39. Koocheki, A., & Seyyedi, S. M. (2019). Mother corm origin and planting depth affect physiological responses in saffron (Crocus sativus) under controlled freezing conditions. Industrial Crops and Products, 138, 111468. https://doi.org/10.1016/j.indcrop.2019.111468
  40. Nadeem, M. A., Tanveer, A., Naqqash, T., Jhala, A. J., & Mubeen, K. (2013). Determining critical weed competition periods for black seed. The Journal of Animal & Plant Sciences, 23(1), 216-221.
  41. Molafylaby, A. (2000). Modern agricultural production of Saffron. Industrial & Scientific Publications Research Organization of Iran-Central Khorasan, in the Saffron (Crocus sativus). The Role of Temperature. Acta Horticulture.39-48.
  42. Patil, B. C., Hosamani, R. M., Ajjappalavara, P. S., Naik, B. H., Smitha, R. P., & Ukkund, K. C. (2010). Effect of foliar application of micronutrients on growth and yield components of tomato (Lycopersicon esculentum Mill.). Karnataka Journal of Agricultural Sciences, 21(3).
  43. Behnia M. (1992). Agronomy of saffron. Tehran University press. 300p. [In Persian].
  44. Kabala, C., & Singh, B.R., (2001). Fractionation and mobility of copper, lead and zinc in soil profiles in the vicinity of copper smelter. Journal of environmental quality. 30(2) 485–492. https://doi.org/10.2134/jeq2001.302485x.
  45. Shirmardi, M., Hayatzadeh, M., Ghaneei Bafghi, M., Hemat, N., & Fooladi Doghzloo, M. (2024). Soil Fertility Assessment in Saffron Cultivated Fields (Case Study: in Bahabad city, Yazd province). Journal of Soil and Plant Relations-Isfahan University of Technology, 15(3), 25-26. [In Persian].
  46. Moshiri, F., Balali, M. R., Rejali, F., & Sedaghat, A. (2022). A framework for integrated soil fertility and plant nutrition management in Iran. Land Management Journal, 10(1), 17-35. [In Persian]. doi:10.22092/lmj.2022.124054.
  47. Shukla, M.K., Lal, R., & Ebinger, M. (2004). Principal component analysis for Predicting corn biomass and grain yields. Soil Science, 169: 215-224. https://doi.org/10.1097/01.ss.0000122521.03492.eb
  48. Koocheki, A., & Seyyedi, S. M. (2015). Relationship between nitrogen and phosphorus use efficiency in saffron (Crocus sativus) as affected by mother corm size and fertilization. Industrial Crops and Products, 71, 128-137. https://doi.org/10.1016/j.indcrop.2015.03.085
  49. Esmailian, Y. & Sedaghat, S., (2011). Evaluation of the effect of calcium carbonate application in alleviating the negative effects of salinity stress on saffron (Crocus sativus) in Gonabad region, Sixth National Saffron Conference, Gonabad. [In Persian].