A new Soil Management System in Enhancing the Yield of Plantation Using IoT Technique and Machine Learning for Smart Pineapple Farming

Abstract

The machine learning technique is studied to aid farmers in decision-making and analysing soil quality based on the nitrogen, phosphorus, and potassium NPK nutrients as the current soil in Malaysia experience degradation of soil organic that affect in production of the nutrient for the crops. The research aim is to study and analyse the Artificial Neural Network model in analysing the quality of soil based on the prediction of NPK level class, which the data collected from Smart Agri-Scan. Next objective is to evaluate the prediction and accuracy of the model. The ANN model is constructed in Neural Net Fitting App in MATLAB. A feedforward neural network is applied to the ANN model and trains it with two different training functions and a different number of neurons of hidden layers. The model with the smallest Mean Square Error is chosen for data analysis as it means the model has the best performance. From the prediction graph, the output of training and validation that corresponds to the prediction model is observed. The points of the output prediction close to the reference line are considered a good prediction model, which means it can analyse soil quality accurately. In future, the model might be able to do the analysis and decision directly at the monitoring platform based on the real-life prediction data.