Predicting and Optimizing Tillage Draft Using Artificial Network Technique
Tillage as one of the agricultural practices consumes the largest amount of energy, which reflects on the total production cost. The artificial neural network (ANN) technique was utilized in the current study to opti-mize the performance of the tillage process. The ANN-modeled multilayer perceptron...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
The Union of Arab Universities
2023-06-01
|
| Series: | Arab Universities Journal of Agricultural Sciences |
| Subjects: | |
| Online Access: | https://ajs.journals.ekb.eg/article_288347_bd46c15ba86e90c2faae886a5669efa5.pdf |
| _version_ | 1797269896183152640 |
|---|---|
| author | Yasmin Shehta Nabil Awady Abdel-Fadil Kabany Mohammed Abd-Elwahed Waleed Elhelew |
| author_facet | Yasmin Shehta Nabil Awady Abdel-Fadil Kabany Mohammed Abd-Elwahed Waleed Elhelew |
| author_sort | Yasmin Shehta |
| collection | DOAJ |
| description | Tillage as one of the agricultural practices consumes the largest amount of energy, which reflects on the total production cost. The artificial neural network (ANN) technique was utilized in the current study to opti-mize the performance of the tillage process. The ANN-modeled multilayer perceptron network with a backpropagation learning algorithm and momen-tum term was used by the PYTHON program. The ANN inputs were: the implement type, soil texture, moisture, bulk density, width, speed, and depth. The draught was the output (kN). Five layers composed the ANN model's optimal configuration (13-64-16-4-1). The linear and rectified linear units (ReLU) functions were utilized with hidden layers and the output layer, re-spectively. Momentum term and learning rate were 0.00003 and 0.9 respec-tively. The iteration number was 1000 epochs and stopped at 290 epochs. The coefficient of determination in the test datasets was high (0.92) while the difference between actual and predicted output was low (2.08). Bulk den-sity and depth were the main determinants of the draft. The evaluation of the developed model for chisel, moldboard, and disk plow gave satisfactory re-sults of 0.985, 0.924, and 0.917. In comparison to the ANNs, the regression model's correlation coefficient for predicting draught force was the lowest (0.373). |
| first_indexed | 2024-04-25T01:55:39Z |
| format | Article |
| id | doaj.art-bbed7854a89046519fdd473c82db5a1c |
| institution | Directory Open Access Journal |
| issn | 1110-2675 2636-3585 |
| language | Arabic |
| last_indexed | 2024-04-25T01:55:39Z |
| publishDate | 2023-06-01 |
| publisher | The Union of Arab Universities |
| record_format | Article |
| series | Arab Universities Journal of Agricultural Sciences |
| spelling | doaj.art-bbed7854a89046519fdd473c82db5a1c2024-03-07T17:27:35ZaraThe Union of Arab UniversitiesArab Universities Journal of Agricultural Sciences1110-26752636-35852023-06-01311152810.21608/ajs.2023.171425.1500288347Predicting and Optimizing Tillage Draft Using Artificial Network TechniqueYasmin Shehta0Nabil Awady1Abdel-Fadil Kabany2Mohammed Abd-Elwahed3Waleed Elhelew4Agricultural Engineering Department, Faculty of Agriculture, Ain Shams University, Cairo, Egypt.Agricultural Engineering Department, Faculty of Agriculture, Ain Shams University, Cairo, Egypt.Agricultural Engineering Department, Faculty of Agriculture, Ain Shams University, Cairo, Egypt.Soil Sci dept., Faculty of Agric., Ain Shams Univ., Cairo EgyptAgricultural Engineering Department, Faculty of Agriculture, Ain Shams University, Cairo, Egypt.Tillage as one of the agricultural practices consumes the largest amount of energy, which reflects on the total production cost. The artificial neural network (ANN) technique was utilized in the current study to opti-mize the performance of the tillage process. The ANN-modeled multilayer perceptron network with a backpropagation learning algorithm and momen-tum term was used by the PYTHON program. The ANN inputs were: the implement type, soil texture, moisture, bulk density, width, speed, and depth. The draught was the output (kN). Five layers composed the ANN model's optimal configuration (13-64-16-4-1). The linear and rectified linear units (ReLU) functions were utilized with hidden layers and the output layer, re-spectively. Momentum term and learning rate were 0.00003 and 0.9 respec-tively. The iteration number was 1000 epochs and stopped at 290 epochs. The coefficient of determination in the test datasets was high (0.92) while the difference between actual and predicted output was low (2.08). Bulk den-sity and depth were the main determinants of the draft. The evaluation of the developed model for chisel, moldboard, and disk plow gave satisfactory re-sults of 0.985, 0.924, and 0.917. In comparison to the ANNs, the regression model's correlation coefficient for predicting draught force was the lowest (0.373).https://ajs.journals.ekb.eg/article_288347_bd46c15ba86e90c2faae886a5669efa5.pdfmachine learning modelsartificial neural networktillage performanceenergy needsdraught |
| spellingShingle | Yasmin Shehta Nabil Awady Abdel-Fadil Kabany Mohammed Abd-Elwahed Waleed Elhelew Predicting and Optimizing Tillage Draft Using Artificial Network Technique Arab Universities Journal of Agricultural Sciences machine learning models artificial neural network tillage performance energy needs draught |
| title | Predicting and Optimizing Tillage Draft Using Artificial Network Technique |
| title_full | Predicting and Optimizing Tillage Draft Using Artificial Network Technique |
| title_fullStr | Predicting and Optimizing Tillage Draft Using Artificial Network Technique |
| title_full_unstemmed | Predicting and Optimizing Tillage Draft Using Artificial Network Technique |
| title_short | Predicting and Optimizing Tillage Draft Using Artificial Network Technique |
| title_sort | predicting and optimizing tillage draft using artificial network technique |
| topic | machine learning models artificial neural network tillage performance energy needs draught |
| url | https://ajs.journals.ekb.eg/article_288347_bd46c15ba86e90c2faae886a5669efa5.pdf |
| work_keys_str_mv | AT yasminshehta predictingandoptimizingtillagedraftusingartificialnetworktechnique AT nabilawady predictingandoptimizingtillagedraftusingartificialnetworktechnique AT abdelfadilkabany predictingandoptimizingtillagedraftusingartificialnetworktechnique AT mohammedabdelwahed predictingandoptimizingtillagedraftusingartificialnetworktechnique AT waleedelhelew predictingandoptimizingtillagedraftusingartificialnetworktechnique |