Comparative Analysis of Machine Learning Algorithm Performance in Smart Irrigation

Abstract

Year by year the technologies are developing in most domains and fields to have lower product cost, lower process time and more efficiency. In this thesis we will show how internet of things has improved smart farming and how we merged IOT in water irrigation systems to have what we called precision irrigation or smart irrigation, and we will talk about Machine Learning one of decision-making techniques in smart irrigation. ML help to have best decision in what time and how much amount of water the soil and plant need and for that we use machine learning algorithms such as KNN, SVM, naïve bayes etc. This thesis shows 19 articles each of them gives the best performance algorithm for different smart irrigation field like estimating evapotranspiration, irrigation time, amount of water, water index to conclude the best algorithm.