تحلیل جریان انرژی تولید انگور در خراسان شمالی به روش شبکه عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته کارشناس ارشد مکانیزاسیون کشاورزی، واحد آزادشهر، دانشگاه آزاد اسلامی، آزادشهر، ایران

2 گروه مکانیک ماشین های کشاورزی، واحد آزادشهر، دانشگاه آزاد اسلامی، آزادشهر، ایران

چکیده

به منظور مدل‌سازی انرژی مصرفی تولید انگور در استان خراسان شمالی، پژوهشی با استفاده از سیستم‌های شبکه عصبی مصنوعی انجام گرفت. اطلاعات مورد نیاز به­وسیله پرسش‌نامه و مصاحبه حضوری با باغداران در سال زراعی 94-1393 جمع‌آوری شدند. نتایج نشان داد که مجموع انرژی مصرفی، انرژی خروجی و کارایی انرژی انگور در استان خراسان شمالی به ترتیب 61/52553 مگاژول بر هکتار، 17/283513 مگاژول بر هکتار و 39/5 بود. کودهای شیمیایی با 98/35094 مگاژول بر هکتار انرژی مصرفی، سهمی در حدود 67 درصد از مجموع انرژی مصرفی تولید را به خود اختصاص دادند. سهم شکل‌های تجدیدپذیر و غیرتجدیدپذیر انرژی در تولید به ترتیب 15 و 85 درصد به‌دست آمد. نتایج شبکه عصبی مصنوعی نشان داد که بهترین ساختار برای مدل‌سازی جریان انرژی تولید انگور 1-10-6 بود. ضریب تبیین بهترین ساختار برای تولید انگور معادل 98/0 به­دست آمد. بنابراین، این مدل به­عنوان بهترین روش برای برآورد انرژی خروجی تولید انگور بر اساس انرژی‌های ورودی در منطقه مورد مطالعه انتخاب شد.

کلیدواژه‌ها


عنوان مقاله [English]

Analysis of energy flow of grape production in North Khorasan Province by artificial neural networks

نویسندگان [English]

  • Mohammad Hassan Namvar 1
  • fatemeh nadi 2
1 Department of agricultural mechanization, Islamic Azad University, Azadshahr branch
2 Department of Agricultural Machinery Mechanics, Azadshahr Branch, Islamic Azad University, Azadshar, Iran
چکیده [English]

The aim of this study was to model the energy flow of grape production North Khorasan province of Iran. Data were collected through questionnaires and also interviews with producers. The results revealed that the total energy inputs, energy output and energy use efficiency of grape production in North Khorasan were 52553.61 MJha-1, 283513.17 MJha-1 and 5.39, respectively. Chemical fertilizer with 35094.98 was attributed the highest share of energy consumption. The shares of renewable energy and non-renewable energy of production were 15 and 85%, respectively. The results of neural networks showed that the best structure for modeling the energy consumption for broiler production was estimated at 6-10-1. The coefficient determination of the best topology was 0.98 for the grape production.

کلیدواژه‌ها [English]

  • renewable energy
  • Energy output prediction
  • Eenergy efficiency
  • Energy modeling
Amid, S., & Mesri-Gundoshmian, T. (2017). Prediction of output energies for broiler production using linear regression, ANN (MLP, RBF), and ANFIS models. Environmental Progress & Sustainable Energy, 36 (2) 577–585.
D’Agostino, R.B. (1986). Tests for the normal distribution. Goodness-of-fit techniques, 68, p.576.
Einset, J., & Dratt, C. (1975). Grape. In: Janick, J., and Moore, J. N. (Eds.), Advances in Fruit Breeding, (pp. 130-153).Purdu University Oress, West Lafayette.
Emadi, B., Nikkhah, A., Khojastehpour, M., & Payman, S. H. (2015). Effect of farm size on energy consumption and input costs of peanut production in Guilan province of Iran. Journal of Agricultural Machinery, 5(1) 217-228.  (In Farsi)
Erdal, G., Esengun, K., Erdal, H., & Gunduz, O. (2007). Energy use and economical analysis of sugar beet production in Tokat province of Turkey. Energy, 3235–41.
Firouzi, S., Nikkhah, A. and Rosentrater, K.A. (2017). An integrated analysis of non‐renewable energy use, GHG emissions, carbon efficiency of groundnut sole cropping and groundnut‐bean intercropping agro‐ecosystems. Environmental Progress & Sustainable Energy. DOI 10.1002/ep
Firouzi, S., Nikkhah, A., Khojastehpour, M. and M Holden, N. (2016). Energy use efficiency, GHG emissions, and carbon efficiency of paddy rice production in Iran. Energy Equipment and Systems, 4(2), 169-176.
Ghaffari-Gharebagh, A., Aghkhani, M. H., & Emadi, B. (2014). Energy and economic analysis of grape production in the Urmia city with study of effect of planting system and garden size. In: Proceedings of  8th National Congress on Agr. Machinery Eng. (Biosystem) & Mechanization of Iran. 28-29 Jan., Mashhad, Iran (In Farsi).
Hosseini, S.M.T., Sioseh Mardeh, A., Fathi, P., & Siosehmardeh, M. (2007). Application of artificial neural network (ANN) and multiple regressions for estimating assessing the performance of dry farming wheat yield in Ghorveh region, Kurdistan province. Agriculture Research, 7 (1):41-54.
Khojastehpour, M., Nikkhah, A. and Hashemabadi, D. (2015). A comparative study of energy use and greenhouse gas emissions of canola production. International Journal of Agricultural Management and Development, 5(1), 51-58.
Khoshnevisan, B., Rafiee, Sh., Omid, M., Mousazadeh, H., & Rajaeifar, M.A. (2014). Application of artificial neural networks for prediction of output energy and GHG emissions in potato production in Iran. Agricultural Systems, 123 120-127.
Khoshroo, A., Mulwa, R., Emrouznejad, A., & Arabi, B. (2013). A non-parametric Data Envelopment Analysis approach for improving energy efficiency of grape production. Energy, 63 189-194.
Mamarabadi, M., & Rohani, A. (2017). Clustering of fungal hexosaminidase enzymes based on free alignment method using MLP neural network. Neural Computing & Applications, 28 1-11.
Mandal, K.G., Saha, K.P., Ghosh, P.K., Hati, K.M., & Bandyopadhyay, K.K. (2002). Bioenergy and economic analysis of soybean-based crop production systems in central India. Biomass and Bioenergy. 23 33–45
Mardani, A., & Taghavifar, H. (2016). An overview on energy inputs and environmental emissions of grape production in West Azerbayjan of Iran. Renewable and Sustainable Energy Reviews, 54 918-924.
Mohammadi, A., Rafiee, S., Mohtasebi, S.S., & Rafiee, H. (2010). Energy inputs – yield relationship and cost anal‌ysis of kiwifruit production in Iran. Renewable Energy. 35 1071-1075.
Nabavi-Pelesaraei, A., Abdi, R., & Rafiee, S. (2016). Neural network modeling of energy use and greenhouse gas emissions of watermelon production systems. Journal of the Saudi Society of Agricultural Sciences, 15(1), 38-47.
Ozkan, B., Fert, C. & Karadeniz, C.F. (2007). Energy and cost analysis for greenhouse and open-field grape production. Energy, 32 (8) 1500-1504.
Pishgar-Komleh, S. H., Omid, M., & Heidari, M.D. (2013). On the study of energy use and GHG (greenhouse gas) emissions in greenhouse cucumber production in Yazd province. Energy, 59 (15) 63–71.
Rajabi-Hamedani, S.R., Keyhani, A., & Alimardani, R. (2011). Energy use patterns and econometric models of grape production in Hamadan province of Iran. Energy, 36 (11) 6345-6351.
Sefeedpari, P., Shokoohi, Z., & Behzadifar, Y. (2014). Energy use and carbon dioxide emission analysis in sugarcane farms: a survey on Haft-Tappeh Sugarcane Agro-Industrial Company in Iran. Journal of Cleaner Production, 83 (15 212–219.
Singh, J. (2002). On farm energy use pattern in different cropping systems in Haryana, India. MSc. thesis, International Institute of Management University of Flensburg; Sustainable energy systems and management. Flensburg, Germany.
Singleton, V. L., & Esau, P. (1969). Phenolic Substances in Grapes and Wine and Their Significance. NewYork: Academic Press.
Snedecor, G.W., & Cochran W.G. (1989). Statistical methods. Iowa City: Iowa State University Press.
Soltanali, H., Emadi, B., Rohani, A., Khojastehpour, M. and Nikkhah, A. (2016). Optimization of Energy Consumption in Milk Production Units through Integration of Data Envelopment Analysis Approach and Sensitivity Analysis. Iranian Journal of Applied Animal Science, 6(1), 15-23.
Soltani, A., Rajabi, M. H., Zeinali, E., & Soltani, E. (2013). Energy inputs and greenhouse gases emissions in wheat production in Gorgan, Iran. Energy, 50 54-61.
Taghavifar, H. & Mardani, A. (2015). Prognostication of energy consumption and greenhouse gas (GHG) emissions analysis of apple production in West Azarbayjan of Iran using Artificial Neural Network. Journal of Cleaner Production, 87159-167.
Taheri-Rad, A., Khojastehpour, M., Rohani, A., Khoramdel, S. and Nikkhah, A. (2017). Energy flow modeling and predicting the yield of Iranian paddy cultivars using artificial neural networks. Energy, 135, 405-412.