Open AccessAn assessment of Energy Consumption for Canola Production System in Iran (A Case Study: Amirkabir Agro-Industry)
Author(s) -
Nasim Monjezi,
Esmaeil Hosseinzadeh
Publication year - 2021
Publication title -
maǧallaẗ al-baṣraẗ al-ʻulūm al-zirāʻiyyaẗ
Language(s) - English
Resource type - Journals
eISSN - 2520-0860
pISSN - 1814-5868
DOI - 10.37077/25200860.2021.34.1.03
Subject(s) - canola , production (economics) , mathematics , environmental science , energy consumption , agricultural science , agricultural engineering , hectare , statistics , engineering , agriculture , agronomy , geography , economics , biology , electrical engineering , macroeconomics , archaeology
Canola production increased significantly in Iran due to its high yield in recent years. Khuzestan province is the main centre of canola production in Iran. This paper presents a data mining study of samples of canola obtained from farms in Amirkabir Agro-Industry of Khuzestan province. Data were collected from 48 farms. The farms were chosen by random sampling method. The purpose of this study is to determine energy consumption of input and output used in canola production. And Output energy of canola farms is predicted using data mining and multi-layer perceptron neural network. This is an analytic research and its database consists of 432 records. Data required for this research was obtained during growing seasons in 2017-2018. Data analysis was done by IBM SPSS modeler 14.2. The results showed that the amount of energy consumed in canola production was 28927.43 MJ ha-1. About 40% of this was generated by fertilizers and 37% from electricity and diesel fuel. Concerning the model used in the research, it was found that variables of chemical fertilizer, fuel, electricity energy and irrigation, respectively had the highest effect on output variable (productive energy). Amount of prediction precision in neural network algorithm meaning ratio of correctly predicted records to total records was 86.5%. Also, linear correlation between actual values and predicted values was 0.84 and 0.88 respectively for training data and testing data suggesting strong correlation. Results obtained in this research can be effective for canola farmers in Amirkabir Agro-Industry in direction of evaluation and optimization of energy consumption in process of canola production and reduction of consumption of energy inputs.