ISSN 1119-4618
 

Original Research 
JPAS. 2022; 22(4): 744-750


Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI)

Mohammed Isa Bammami, Mohammed Kamal Rowshon, Aliyu Umar Shelleng.

Abstract
Subsurface drip irrigation (SDI) provides a potential solution to the problem of low water use efficiency. However, SDI performance depends on the soil properties in the field. Hence, an investigation is essential to explain this effect for maintaining the best performance of SDI. Thus, this paper presents the application of artificial neural networking (ANN), Gene expression programming (GEP), and Multiple Linear Regression Model as an advance tool in predicting the variation of discharge rate in SDI performance due to soil compaction and to find ways of improving emitter performance. To achieve this objective, an intensive experiment was carried out consisting of an air tank, water reservoir, digital flow meter, digital penetrologer, pressure gauge, and emitters with three discharge rates of 2, 4, and 8 L/hr, three different soils, and a metal rectangular lysimeter. At first, the emitters were buried at 10 cm, 20 cm, and 30 cm in the loosely packed soils in a metal box. The discharge rate and soil cone index were measured at normal and different compaction levels and consequent emitter discharge rates. A relationship was established for soil cone index, lateral depth, operating pressure, and emitter discharge rate to explain the soil compaction effects on emitter performance. The prediction performance of three regression methods was evaluated using Root mean square error (RMSE) and R square. The ANN model has better performance than the rest of the models in the prediction of emitter performance in different soil dynamics and operating pressures (R^2 of 0.83) in the prediction of decrease in percentage of emitter discharge rate (q). To ameliorate the effect of compaction on the emitter performance, the emitter operating pressure was increased from 1 bar to 1.5 bars even at higher soil cone index the discharge rate of emitter improved with the increase in operating pressure. Emitters buried at deeper lateral depth have shown a higher resistance to soil compaction. This study concludes that the emitter discharge rate decreases with an increase in soil cone index and encourages deeper lateral depth and higher operating pressure depending on the soil cone index.

Key words: Soil compaction, Discharge variation, Emitter performance, SDI


 
ARTICLE TOOLS
Abstract
PDF Fulltext
How to cite this articleHow to cite this article
Citation Tools
Related Records
 Articles by Mohammed Isa Bammami
Articles by Mohammed Kamal Rowshon
Articles by Aliyu Umar Shelleng
on Google
on Google Scholar

How to Cite this Article
Pubmed Style

Bammami MI, Rowshon MK, Shelleng AU, . Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). JPAS. 2022; 22(4): 744-750.


Web Style

Bammami MI, Rowshon MK, Shelleng AU, . Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). https://www.atbuscienceforum.com/?mno=64418 [Access: January 16, 2023].


AMA (American Medical Association) Style

Bammami MI, Rowshon MK, Shelleng AU, . Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). JPAS. 2022; 22(4): 744-750.



Vancouver/ICMJE Style

Bammami MI, Rowshon MK, Shelleng AU, . Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). JPAS. (2022), [cited January 16, 2023]; 22(4): 744-750.



Harvard Style

Bammami, M. I., Rowshon, M. K., Shelleng, A. U. & (2022) Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). JPAS, 22 (4), 744-750.



Turabian Style

Bammami, Mohammed Isa, Mohammed Kamal Rowshon, Aliyu Umar Shelleng, and . 2022. Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). Science Forum (Journal of Pure and Applied Sciences), 22 (4), 744-750.



Chicago Style

Bammami, Mohammed Isa, Mohammed Kamal Rowshon, Aliyu Umar Shelleng, and . "Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI)." Science Forum (Journal of Pure and Applied Sciences) 22 (2022), 744-750.



MLA (The Modern Language Association) Style

Bammami, Mohammed Isa, Mohammed Kamal Rowshon, Aliyu Umar Shelleng, and . "Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI)." Science Forum (Journal of Pure and Applied Sciences) 22.4 (2022), 744-750. Print.



APA (American Psychological Association) Style

Bammami, M. I., Rowshon, M. K., Shelleng, A. U. & (2022) Application of Machine Learning Models in Predicting Emitter Discharge Rate Variation due to Soil Compaction in Sub-Surface Drip Irrigation (SDI). Science Forum (Journal of Pure and Applied Sciences), 22 (4), 744-750.