This study aimed to evaluate the efficiency of energy consumption and economic analysis of different watermelon cultivation systems in Fars Province of Iran. Watermelon production systems were classified into five systems, namely, custom tillage (group 1), conservation tillage (group 2), traditional planting (group3), semi mechanized planting (group 4), and mechanized planting (group 5). Data were collected from 317 watermelon producers from different parts of the province through face to face interviews. Multi-Layer Perceptron artificial neural networks were used to model the energy flows of watermelon production. The results showed that the greatest energy consumption belonged to mechanized planting system with the value of 81317.72 MJha-1 and with the productivity of 0.61 kgha-1and energy use efficiency of 1.17. Clustering function with three inputs (human resources, machines and diesel fuel) showed that the difference between groups 2 and 4 is more than the other groups. The least energy consumption belonged to the conservative agriculture as78163.86 MJha-1and the energy productivity and energy use efficiency about 0.64 kgha-1 and 1.22, respectively. The results of energy modeling showed that an ANN model with 9-10-1 structure was determined to be optimal for energy flow modeling of this system. Generally, it was concluded that the artificial neural network models can be applicable to prognosticate the energy flows of watermelon production. From an economic point of view, the least net profit belonged to traditional planting with the value of 2618.14$, and the most net return belonged to mechanized planting with the value of 2752.88$/ha. پرونده مقاله

The present study attempts to investigate the potential relationship between input energies, performance production of greenhouse basil, and greenhouse gases emitted from this product. The data were collected from 24 greenhouses using a questionnaire and verbal interaction with farmers. Results of the study showed that the total input energy and total output energy for basil production were 119,852.9 MJ/ha and 61,040 MJ/ha, respectively. The highest rate of energy consumption was related to electricity (52,200 MJ/ha), followed by plastic (23,220 MJ/ha) and chemical fertilizers (13,894 MJ/ha). The energy and productivity indices were estimated at 0.45 and 0.21, respectively, which indicated that the efficiency of energy in the agricultural sector was low. In addition, it was found that the pure energy index and total greenhouse gases emitted from basil production were equal to -722,706.9 and 9,595.6 kg (CO2), respectively. The highest emission of greenhouse gases was attributed to electricity (2,216 kg/CO2). Results of modeling proved that artificial neural networks can predict basil performance and CO2 emissions with a high degree of accuracy (R2=0.99 and MSE= 0.00023). پرونده مقاله