A smart IoT-based irrigation system design using AI and prediction model

Implementing intelligent irrigation and adjusting the irrigation system is essential in today’s agricultural system to control the amount of water required for the plant. This study focuses on data obtained from sensors measuring (soil temperature and humidity, temperature and humidity of ambient an...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2023-12, Vol.35 (35), p.24843-24857
Main Authors: Behzadipour, Faeze, Ghasemi Nezhad Raeini, Mahmod, Abdanan Mehdizadeh, Saman, Taki, Morteza, Khalil Moghadam, Bijan, Zare Bavani, Mohammad Reza, Lloret, Jaime
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Genetic algorithms
Humidity
Image processing
Image Processing and Computer Vision
Irrigation
Irrigation systems
Moisture content
Original Article
Prediction models
Probability and Statistics in Computer Science
Regression models
Sensors
Software
Soil temperature
Standard error
Systems design
Water conservation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Implementing intelligent irrigation and adjusting the irrigation system is essential in today’s agricultural system to control the amount of water required for the plant. This study focuses on data obtained from sensors measuring (soil temperature and humidity, temperature and humidity of ambient and light) and image processing of plant leaves. To analyze the data, two models were implemented including a regression model in SPSS software and another model by genetic programming in MATLAB 2018 software. The optimal model was a combined model of sensors and images in genetic programming with higher R 2 and lower standard error of 0.88 and 0.03, respectively. This model was superior to the regression model which had an R 2 and standard error of 0.86 and 0.21, respectively, so this optimal model was selected to adjust the microcontroller for the intelligent irrigation system. The following year by replanting the crop, the intelligent irrigation system was presented as the superior system with 11% water saving compared to the previous year (irrigation by the user). Also, no changes were observed in the yield and color indicators of the plant at the level of 5%, which indicates the superiority of the intelligent irrigation system and its high accuracy of this system.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-023-08987-y