Paper Title
MACHINE LEARNING BASED WATER BODY DETECTION IN FARMS – A SYSTEMATIC REVIEW

Abstract
Abstract - The digital transformation of water bodies enabled Several areas of farm management have been changed into systems based on AI in order to derive value from the increasing amount of data coming from a number of sources. Machine learning, a sort of artificial intelligence, can manage a variety of challenges in the development of experience and understanding agricultural systems. The proposed research seeks to provide clarity on machine learning in agriculture by performing a thorough review of current literature review based on keyword searches, combinations of "machine learning" and "smart farming" and "water management." Only recently published journal papers were deemed suitable. According to the findings, this subject is relevant to several fields that promote worldwide convergence research. Moreover, water body conservation was revealed to be a point of interest. The use of artificial neural network has been the most efficient of the methods for machine learning used. Moreover, apart from farming, were the most studied methods. The works studied were categorized as smart farming applications, which comprised applications for predictive modeling, water management, essential, disease detection, weed detection, agronomic, species recognition, and disease detection The article classification and filtering demonstrate how agriculture will benefit from machine learning technology. Farm management systems are evolving into real-time, AI-enabled apps that provide comprehensive suggestions and insights for farmer predictive modeling and action by integrating machine learning with sensor data. Keywords - AI based water bodies, Environmental irrigation, Machine learning, Smart farming.