Fig 1 - uploaded by Mahmoud Omid
Content may be subject to copyright.
Source publication
An artificial neural network (ANN) model was developed to assess mechanization status of potato farms in Iran. Mechanization index (MI) and level of mechanization (LOM) were used to characterize farming system of potato production in the region. To develop ANN model, data were obtained from farmers, government officials as well as from relevant dat...
Context in source publication
Context 1
... LOM = level of mechanization, P i = power of tractors , η = correction factor for utilized power (0.75). Field capacity was multiplied by rated power so the quantification of energy expenditure was made in work units (kWh). The regional normal was obtained after compiling a full dataset of all respondents and then it was defined the mode for the number of passes for each operation as well as the mode in tractor size and field capacity. It is implied that these technologies are mechan- ized agricultural practices that have been successfully incorporated into the farming systems. During the interview, data was recorded on all the mechanized operations performed by farmers in the sample providing an estimation of the field capacity (hours of work per unit land). The ANN models were trained to output these indicators from the data of the 19 input parameters, included in Table 2. There are multitudes of ANN structures and different classification frameworks. For examples, ANN could be classified according to the learning method or to the organi- zation of the neurons (Chester, 1993). The one that have been used in this work is called Multi Layer Perception (MLP), in which neurons are organized in several layers: the first is the input layer (fed by a pattern of data), while the last is the output layer (which provides the answer to the presented pattern). Between input and output layers there could be several other hidden layers (see Fig. 1). The number of hidden layers has an important role in determining the generalization ability of the MLP. MLP represents a tool, which is able to identify the relationships between different data sets, although the form of these relationships is not defined exactly. For this reason they are called ‘‘universal approximation or regression tools’’ (Hornik et al., 1989). The ANN model was calibrated using the Neural Solutions 5.0 software package. During the calibration process, 80 architecture combinations were trained. Variations of the back propagation learning algorithm were applied. As presented by Zhang et al., 1998, the square error of the estimates between the observed and actual output is fed-back through the network causing changes of the weights, with the purpose of preventing that the same error will happen again. Batch back propagation provided smooth curves, with results generally better than those of the other training back propagation methods. At this stage, results from cross- validation analysis in relation to network size and number of training cycles were analyzed to select the best combination to keep the model simple. The data sets of the 68 farm patterns were divided randomly into three subsets, containing 41 ...
Similar publications
Abstract: In Mexico the peanut crop production has declined due to low productivity and profitability of the crop. Since 1983 when the record was 170 433 ton production was obtained with a yield of 2.04 t / Ha. Since today is 94,848.58 production Ton / Ha .With a yield of 1.77 t / ha. The country has a shortage of about 100,000 tons per year to mee...
As is known, the use of mechanization for agriculture production have crucial importance for crop quality and yield in unit area. The mechanization of agricultural production is constantly renewing itself, depending on the time with the development of technology. For this reason, it is necessary to make determinations periodically for the current s...
A single hidden layer Artificial Neural Network (ANN) model was developed to estimate a machinery energy ratio (MER) indicator, used to characterize and assess mechanization status of potato farms in Iran with a view point of energy expenditure in farm machinery. A wide range of variables of farming activities were examined. Initially, 90 attribute...
Agricultural mechanization in developing countries has taken at least two contested innovation pathways—the “incumbent trajectory” that promotes industrial agriculture, and an “alternative pathway” that supports small-scale mechanization for sustainable development of hillside farming systems. Although both pathways can potentially reduce human and...
Citations
... Zangeneh et al. (2010) have given the equation by assessing the Mechanization Index by summing the overall energy used in the cropping area with com-S258 Eco.Env. & Cons. ...
Farm mechanization is the most recent human innovation to boost food grain output. Following the green revolution, mechanization had a huge influence on output and reduced food scarcity. Today, we live in a time when expanding population has produced a scarcity scenario in which increasing agricultural lands appears to be impossible. Farmers are under pressure to adopt new technology that can enhance food crop production as well as income. Farmers are prioritizing the use of modern mechanized tools and equipment in order to save time, effort, and money. The paper attempts to investigate the influence of mechanization on farmer income. This study will calculate the cost of mechanization for each farm and crop. The mechanization intensity was calculated using several recommended scholars and was found that all randomly selected farms have an average of 1.494 hp/ha and nearly 0.895 kW/ha, requiring additional capital investment to boost power and energy supply to the cultivated areas. This affects farmers' farm revenue and demonstrates that mechanization is an important component of modern agriculture.
... Zangeneh et al. (2010) have given the equation by assessing the Mechanization Index by summing the overall energy used in the cropping area with com-S258 Eco.Env. & Cons. ...
Farm mechanization is the most recent human innovation to boost food grain output. Following the green revolution, mechanization had a huge influence on output and reduced food scarcity. Today, we live in a time when expanding population has produced a scarcity scenario in which increasing agricultural lands appears to be impossible. Farmers are under pressure to adopt new technology that can enhance food crop production as well as income. Farmers are prioritizing the use of modern mechanized tools and equipment in order to save time, effort, and money. The paper attempts to investigate the influence of mechanization on farmer income. This study will calculate the cost of mechanization for each farm and crop. The mechanization intensity was calculated using several recommended scholars and was found that all randomly selected farms have an average of 1.494 hp/ha and nearly 0.895 kW/ha, requiring additional capital investment to boost power and energy supply to the cultivated areas. This affects farmers’ farm revenue and demonstrates that mechanization is an important component of modern agriculture.
... Other authors recommend the ratio between the mechanised operation and the total cultivated area as a mean to be implemented in the description of the amount of mechanisation in a cultivated area. A mechanisation index was created by Zangeneh et al. [14] based on an artificial neural network model to measure how much a farm's amount of machine work deviates from values at the regional level. Based on the slope local length of auto-correlation, Maheshwari and Tripathi [15] evaluated a novel method for calculating a mechanisation index that accounts for the strength of machines and animals as well as the time it takes for humans, machines, and animals to carry out cultivation operations. ...
Management of pastures and meadows in the Alpine area of Northern Italy often implies mechanizable practices. In order to optimise and achieve economic sustainability of such practices, agricultural machinery implementation is needed. Thus, the present work introduces a methodology aimed to assess the potential for agricultural mechanisation of pastures and meadows based on rational and quantitative criteria. In particular, a mechanisability index is here proposed, based on GIS analysis of landscape parameters as mean and maximum slope, size, mean altitude, distance from the nearest road and shape regularity of the fields. For the scope, 11.093 fields in the Province of Trento were identified and considered to analyse their mechanisability potential. The results give evidence of a medium to low mechanisability potential of pastures and meadows in the area, the most limiting factors being elevated slopes, altitude and distance from roads. The methodology here reported might be applied to other mountainous areas, helping the decision-making processes of institutions and farmers.
... Other Pre-planting Activities: Two papers using diagnostic methods applied supervised feature selection to define traits affecting water content in maize and Spearson's rank correlation to determine association between climatic indices and maize and sorghum yields (Byakatonda et al., 2018;Shekoofa et al., 2011). Six studies used predictive methods in various aspects; for drought assessment and water planning, for forecasting seasonal variability and temperature, and for appraising mechanization on farms to predicting the success of an agricultural enterprise based on their capital (Bakhshi et al, 2016;Osman et al., 2015;Park et al., 2016;Smith et al., 2009;Zangeneh et al., 2010;). Prescriptive methods was the focus of the larger number of studies done in this area with the eight studies found devoted to prescribing and simulating management routes based on seeding density, land use conversion, and crop sequence (Delgado et al., 2008;Dornelles et al., 2018;Jimenez et al., 2009;Rajeswari et al., 2017;Renaud-Gentie et al., 2014;Rizzo et al., 2014;Snow & Lovattb, 2008;). ...
... Using satellite imagery to estimate water usage Supervised Maximum Likelihood Classification (L. Predicting machinery energy ratio for target farming systems Artificial Neural Networks (Zangeneh et al., 2010) Predicting crops present in a given field using crop sequence of previous years Markov Logic Networks (Osman et al., 2015) Drought assessment and monitoring Random Forest, Boosted Regression Trees, Cubist (Park et al., 2016) Year-round temperature prediction Artificial Neural Networks (Smith et al., 2009) ...
The United Nations (UN) Food and Agriculture (FAO) estimates that farmers will need to produce about 70% more food by 2050. To accommodate the growing demand, the agricultural industry has grown from labor-intensive to smart agriculture, or Agriculture 4.0, which includes farm equipment that are enhanced using autonomous unmanned decision systems (robotics), big data, and artificial intelligence. In this chapter, the authors conduct a systematic review focusing on big data and artificial intelligence in agriculture. To further guide the literature review process and organize the findings, they devise a framework based on extant literature. The framework is aimed to capture key aspects of agricultural processes, supporting supply chain, key stakeholders with a particular emphasis on the potential, drivers, and challenges of big data and artificial intelligence. They discuss how this new paradigm may be shaped differently depending on context, namely developed and developing countries.
... Zangeneh et al. [17] developed a mechanisation index based on an artificial neural network model evaluating the deviation of the amount of machine work of a farm from the values at the regional level. Sofia et al. developed a method for classification of land geomorphology based on slope local length of auto-correlation [18]. ...
Planting criteria of new vineyards should comply with rational and sustainable criteria, taking into account the potential mechanisability of existing viticultural areas. However, an established methodology for this assessment is still lacking. This study aimed at analysing the parameters which influence the vineyard mechanisability, with the objective to propose a new mechanisability index. The mechanisability index proposed was based on GIS-analysis of landscape and management parameters such as mean slope, shape of the vineyard block, length-width ratio, headland size, training system and row spacing. We identified a sample of 3686 vineyards in Italy. Based on the above-mentioned parameters, vineyards were categorised by their level of mechanisability (l.m.) into four classes. Moreover, we analysed the correlation between l.m. and economic indicators (area planted with vineyard and wine production). Results showed that the main factors limiting the mechanisability potential of some Italian regions are the elevated slopes, horizontal training systems and narrow vine spacings. The l.m. showed a moderate positive correlation with the size of vineyards and the volume and value of production. The methodology presented in this study may be easily applied to other viticultural areas around the world, serving as a management decision-making tool.
... Other Pre-planting Activities: Two papers using diagnostic methods applied supervised feature selection to define traits affecting water content in maize and Spearson's rank correlation to determine association between climatic indices and maize and sorghum yields (Byakatonda et al., 2018;Shekoofa et al., 2011). Six studies used predictive methods in various aspects; for drought assessment and water planning, for forecasting seasonal variability and temperature, and for appraising mechanization on farms to predicting the success of an agricultural enterprise based on their capital (Bakhshi et al, 2016;Osman et al., 2015;Park et al., 2016;Smith et al., 2009;Zangeneh et al., 2010;). Prescriptive methods was the focus of the larger number of studies done in this area with the eight studies found devoted to prescribing and simulating management routes based on seeding density, land use conversion, and crop sequence (Delgado et al., 2008;Dornelles et al., 2018;Jimenez et al., 2009;Rajeswari et al., 2017;Renaud-Gentie et al., 2014;Rizzo et al., 2014;Snow & Lovattb, 2008;). ...
... Using satellite imagery to estimate water usage Supervised Maximum Likelihood Classification (L. Predicting machinery energy ratio for target farming systems Artificial Neural Networks (Zangeneh et al., 2010) Predicting crops present in a given field using crop sequence of previous years Markov Logic Networks (Osman et al., 2015) Drought assessment and monitoring Random Forest, Boosted Regression Trees, Cubist (Park et al., 2016) Year-round temperature prediction Artificial Neural Networks ...
The United Nations (UN) Food and Agriculture (FAO) estimates that farmers will need to produce about 70% more food by 2050. To accommodate the growing demand, the agricultural industry has grown from labor-intensive to smart agriculture, or Agriculture 4.0, which includes farm equipment that are enhanced using autonomous unmanned decision systems (robotics), big data, and artificial intelligence. In this chapter, the authors conduct a systematic review focusing on big data and artificial intelligence in agriculture. To further guide the literature review process and organize the findings, they devise a framework based on extant literature. The framework is aimed to capture key aspects of agricultural processes, supporting supply chain, key stakeholders with a particular emphasis on the potential, drivers, and challenges of big data and artificial intelligence. They discuss how this new paradigm may be shaped differently depending on context, namely developed and developing countries.
... In their categorizations, a highly mechanized operation means most of the work was done with machines, while a low mechanization level means there was little use of farm machinery. Zangeneh et al. (2010) identified 19 farming activities as explanatory parameters and developed an artificial neural network model to assess the mechanization levels of potato farms in Iran. Similarly, Zangeneh et al. (2015) developed an artificial neural network model to assess the level of mechanization in Potato Production of Italy. ...
... Although none of the studies reviewed above are from the construction domain, they are informative and helpful to this study. Especially for Zangeneh et al. (2010), which identified a group of activities to help assess the mechanization level in potato farming. It inspired the research team that establishing a comprehensive framework consisting of different construction work types and activities is extremely necessary, because the assessment of the mechanization should be performed based on these work types and activities. ...
While mechanization has been widely adopted in the current construction industry, little research has been done to assess the level of mechanization in building construction projects. The aims of this study are to propose a framework that can assess the level of mechanization in building construction projects, to develop a computer-based tool that can help assess mechanization levels, and to collect the views of industry practitioners regarding mechanization. To achieve these goals, a comprehensive literature review was conducted first, and based on which a six-layer assessment framework, namely Mechanization Index for Building Construction Projects, was proposed. After that, Mechanization Index Assessment Tool, a computer-based tool that can assess the level of mechanization in building construction projects, was developed. The developed tool was adopted in 14 construction projects in Singapore. Assessment results showed that the mechanization level of the projects was 48.54 percent out of 100, which is moderate. Results also reported that ‘site preparation’ and ‘underground piping’ were two work types that are more mechanized, while work types of ‘formwork’, ‘tiling’, and ‘painting’ were relatively less mechanized. Additionally, industry practitioners perceived that the mechanization levels in the current building construction projects and industry were moderate and more efforts should be put in this regard, especially from the perspective of the industry. This study is the first piece of research work that assesses the level of mechanization in building construction projects and thus, it contributes to the body of knowledge. Furthermore, the assessment tool developed can easily be used either by industry practitioners or by construction authorities to do mechanization assessment. Thus, this study contributes to the practice as well.
... The best models for estimating leaf area of guava according to L, W and L*W of the leaf blade, follow the following criteria: Pearson's coefficient of linear correlation coefficient (r) and of determination (R 2 ) closest to one [16][17][18] , mean absolute error (MAE) and root mean square error (RMSE) closest to zero as reported by Zangeneh et al. 19 , and d Willmott and CS indexes closest one. Statistical analysis of the results of the experiment was carried out using the Office Excel program and ASSISTAT version 7.6 beta as concluded by Silva and Azevedo 20 . ...
In order to obtain an equation that permits the estimation of guava leaf area through the dimensional linear parameters of the leaves, a study was conducted in the Polytechnic School of the Universidade Federal de Santa Maria. The guava leaves were collected on four occasions, at 30, 45, 60 and 75 days after pruning. The leaf area was determined by the method of discs. Linear models, linear without intercept, quadratic, cubic and power between leaf area and length or width and its products (Length * Width) were adjusted, and those that had a coefficient of determination less than 0.90 were eliminated. The statistic used to evaluate the performance of models was the Pearson correlation coefficient (r), the determination coefficient (R²), the root mean square error (RMSE), the mean absolute error (MAE), the index d of Willmott and CS index. The models that best fit the data were: the linear, linear without intercept, power and quadratic, considering the relation (Length * Width), as independent variable, and when considering only one dimension, the model power that used the length of the limb leaf was more realistic.
... Appropriate indicators must be selected to determine levels of mechanization like variable that allow describing and monitoring the processes (Wan Ishak, 2010). States and tendencies of system at the farm, regional, national and worldwide level (Morteza et al., 2010). As stated in righteous book, Al-Quran in sura Yassin verse 82, Allah SWT when intends something, He just ask without ant help from others. ...
Ubi Gadong (Dioscorea hispida) is a toxic plant which contains toxic poison. It can only be consumed after the poison of dioscorin is removed. It is normally found in wildlife forest and planted in clay soil condition in Asia region. The advancement of technology should introduce in most important area; agriculture, as for benefit of mankind. The solid mod-eling software may use for design, model and simulate the workability of the designed equipment in CAD environment system. The simulation analysis will make the designer choose the best decision for fabrication stage of agriculture mechanization tool. The farm mechanization for ubi gadong is help to produce the good quality and output in this new exploration of wildlife food for commercialization.
... The Artificial Neural Network (ANN) gives estimations of the mechanization indicators using limited data available from the target region, without the need to calculate them directly, which would require more data (Zangeneh et al., 2010). According to Ghasemi (2008) in Hamedan and most researchers in other regions (Kisi, 2006, Kumar et al., 2008, Moghaddamnia et al., 2009, ANN is the most appropriate method for reference evapotranspiration estimating. ...
The purpose of this study was to determine the water requirement, single and dual crop coefficient of garlic using a drainage lysimeter. The lysimeter experiments were conducted during 2008-2009. According to the experimental results, garlic water requirements (ET(C)) in this period were 546.5 mm and 519.2 mm, respectively, during the growing season. A reference evapotranspiration (ET(0)) was simulated with artificial neural network (ANN) method during garlic growth season. Results showed that crop coefficient value (K(C)) in initial and final stages were 0.53, 1.4 and 0.3, respectively. The results were compared to the single and dual crop coefficients from the FAO-56 procedure. Results showed that maximum differences between ETC of single and dual K(C) values were observed at initial and final stages. Also, this study showed that dual crop coefficient is more precise (RMSE=38%) but the advantage of single crop coefficient is simpler for a user.
