Hydroponic NFT for Brinjal cultivation using Decision Tree (DT) and K-Nearest Neighbour (KNN)

Hydroponic brinjal cultivation with the Nutrient Film Technique (NFT) is the intended setting for this study’s evaluation of the K Nearest Neighbor (KNN) and Decision Tree (DT) algorithms. This study uses a wide range of inputs relevant to hydroponic systems to assess how well different machine learning approaches can predict brinjal growth, yield, and quality parameters. Data Collection: A wide range of environmental parameters, including pH levels, water temperatures, light exposure, and nutrient concentrations, are measured using the NFT approach. The collection also includes parameters particular to individual plants, such as yield, fruit dimensions, and leaf area. Results: It can be concluded that brinjal production and growth metrics may be predicted with an acceptable degree of accuracy using both the Decision Tree and K Nearest Neighbor algorithms. Nevertheless, in some situations, KNN is more accurate than Decision Tree, and it is also easier to interpret and execute. Conclusion: KNN predicts brinjal yield with an accuracy of 88%, while Decision Tree predicts it with an accuracy of 85%. Depending on the particular parameters being predicted, precision and recall measures change, with KNN typically displaying higher levels of precision.