Intelligent modeling of tomato production cost functions in Syria using a multi-layer neural network (MLP)

Authors

  • mjd namaa Tishreen University

Abstract

The research aimed to develop a mathematical model for the costs of producing tomato crops, and to determine the optimal size of production to achieve economic efficiency through standard analysis of the cost functions of producing one kilogram of tomato fruits.

To achieve the research objectives, a feed-forward multi-layer neural network (Multi-layer Perceptron) was used to model the time series of the research variables during the period (1993-2021), where 23 years of data were used in the training phase, and 6 years in the testing phase.

 The neural network used consisted of three layers (input, processing, and output). The input layer consisted of 6 neurons, the processing layer included 2 neurons, and the output layer included one cell. The hyperbolic tangent activation function was used in the processing layer, and the Identity function was used. ) In the output layer, the sum of squared error in the training phase was 0.07, decreasing to 0.01 in the testing phase, indicating the quality of the model.

The research results showed that the costs of production inputs constitute the greatest relative importance in the function of the total costs per hectare of tomato crop according to the proposed neural network model, followed by the costs of agricultural operations, then the interest on capital.

The results of the analysis of the total cost function for the tomato crop showed that increasing the costs of production inputs by one unit leads to an increase in total costs by 16.97 units. Likewise, increasing the costs of agricultural operations by one unit leads to an increase in total costs by 1.36 units, and that increasing the interest on capital by one unit leads to a decrease in total costs. By 8.52 units.

The results also showed that the actual production volume is far from the production volume that achieves economic efficiency, as the production volume that achieves the lowest cost is 38,732.05 kg/ha compared to the actual production volume in 2021, which amounts to 98,914 kg/ha.

Downloads

Published

2024-11-02

How to Cite

نعامه م. (2024). Intelligent modeling of tomato production cost functions in Syria using a multi-layer neural network (MLP). Tishreen University Journal -Biological Sciences Series, 46(4), 73–85. Retrieved from https://journal.tishreen.edu.sy/index.php/bioscnc/article/view/17974

Issue

Vol. 46 No. 4 (2024): Tishreen University Journal for Research and Scientific Studies - Biological Sciences Series

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

The authors retain the copyright and grant the right to publish in the magazine for the first time with the transfer of the commercial right to the Tishreen University Journal for Research and Scientific Studies - Biological Sciences Series   

 Under a CC BY- NC-SA 04 license that allows others to share the work with of the work's authorship and initial publication in this journal. Authors can use a copy of their articles in their scientific activity, and on their scientific websites, provided that the place of publication is indicted in Tishreen University Journal for Research and Scientific Studies - Biological Sciences Series  .  The Readers have the right to send, print and subscribe to the initial version of the article, and the title of Tishreen University Journal for Research and Scientific Studies - Biological Sciences Series    Publisher

journal uses a CC BY-NC-SA license which mean

You are free to:

  • Adapt — remix, transform, and build upon the material
  •  
  • The licensor cannot revoke these freedoms as long as you follow the license terms.

 

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • NonCommercial — You may not use the material for commercial purposes.
  • ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.