A Systematic Review of Machine Learning Methods in Smart Hydroponic Farming

The burgeoning global population coupled with the increasing scarcity of arable land has necessitated innovative agricultural practices. Hydroponics, a soil-less cultivation method, has emerged as a promising solution to address these challenges by offering efficient and sustainable food production. This systematic review explores the application of machine learning methods in smart hydroponic farming. The analysis reveals a growing trend in the use of machine learning techniques to address challenges such as disease detection, parameter control, and yield prediction. Common methods include decision trees, neural networks, Bayesian networks, and support vector machines. While significant progress has been made, research gaps remain in yield growth prediction and data security. Future research should focus on integrating advanced technologies like IoT, AI, robotics, blockchain, and GIS to enhance the efficiency, sustainability, and scalability of smart hydroponic farming.