Pressurized irrigation systems are widespread among other alternatives in Mediterranean countries. Since the initial investment costs of pressurized irrigation systems are quite high, it is crucial to determine design parameters such as pipe diameter. Most of the current optimization techniques for pipe diameter selection are based on linear, non-linear, and dynamic programming models. The ultimate aim of these techniques is to produce solutions to problems with less cost and computation time. In this study, a novel approach for determining pipe diameter was proposed
using Artificial Neural Networks (ANN) as an alternative to existing models. For this purpose, three pressurized irrigation systems were investigated. Different ANN architectures were created and tested using hydrant level parameters of the irrigation systems, such as irrigated area per hydrant, hydrant discharge, pipe length, and hydrant elevation. Different training algorithms, transfer functions, and hidden neuron numbers were tried to determine the best ANN model for each irrigation system. Using multilayer feed-forward ANN architecture, the highest coefficients of determination were found to be 0.97, 0.93, and 0.83 for irrigation systems investigated. It was concluded that pipe diameters could be determined by using artificial neural networks in the planning of pressurized irrigation systems.
Machine learning Optimization techniques Irrigation water management Network performance analysis Hydraulic parameters
Birincil Dil | İngilizce |
---|---|
Konular | Mühendislik |
Bölüm | Makaleler |
Yazarlar | |
Erken Görünüm Tarihi | 18 Ocak 2023 |
Yayımlanma Tarihi | 31 Ocak 2023 |
Gönderilme Tarihi | 11 Mayıs 2021 |
Kabul Tarihi | 13 Şubat 2022 |
Yayımlandığı Sayı | Yıl 2023 Cilt: 29 Sayı: 1 |
Journal of Agricultural Sciences is published open access journal. All articles are published under the terms of the Creative Commons Attribution License (CC BY).