A machine learning approach for prediction system and analysis of nutrients uptake for better crop growth in the Hydroponics system

With the ascent of new techniques in farming, Hydroponics, an efficient and smart method of cultivating crops in water is becoming an increasingly popular choice for growing crops. It is likewise being utilized for augmenting crop yield. Water nutrient management thus becomes a vital technique for ensuring optimal requirements for crop growth. A balanced supply of these nutrients is the key to healthy plants. We studied the dynamics of the nutrients uptake for the tomato crop which aids in enhancing its absolute crop growth rate (CGR). This paper proposes a framework to predict the absolute CGR using machine learning technique for the tomato crop in hydroponics. Input variables like Electric conductivity (EC) limit, Nutrient solution (NS), ion concentration uptake, dry weight matter of the fruits are contributing factors for the feasible growth of hydroponic tomato crops. The study shows positive and negative correlations with the growth parameters, dry weights of the fruits and absolute crop growth rate of the plant. The dynamics of uptake of nutrient ions Na, K, Mg, N and Ca during growth of tomato fruits is shown and its effect on the target variable absolute growth is studied. This correlation analysis helped us determine the important variables that affect the CGR and will give us more insights on the correct supply of nutrients for good growth and development of the crops. The proposed system design provides a smart and efficient way to predict and achieve good absolute CGR while estimating the optimum value of the essential parameters will help us in achieving good quality yields.