Prediction and Comparative Analysis Using Ensemble Classifier Model on Leafy Vegetable Growth Rates in DWC and NFT Smart Hydroponic System

Abstract

A comparison of leafy green spinach species growth rates in two different hydroponic systems was performed in a controlled environment. The integration of several sensors to monitor the parameters of plant growth has been deployed using the Internet of things (IoT) technology. Intelligent models to predict the plant growth in the hydroponic system are necessary for better decision making in controlling the parameter during plant growth. This research compares the plant growth dynamics in deep water culture (DWC) and nutrient film technique (NFT) systems. The results demonstrate efficient plant growth in the NFT system compared to DWC in terms of height and number of leaves. The study also discusses the observations during the growth time to analyze the most suitable hydroponic structure for spinach growth. The growth prediction is implemented using an ensemble classifier model, which gives an accuracy rate above 79% on DWC and 64% on the NFT dataset based on binary classification.