IoT and AI-based Intelligent Agriculture Framework for Crop Prediction

Background: Currently, Artificial Intelligence (AI) and the Internet of Things (IoT) have transformed the field of agriculture with the innovative idea of automation and intelligence. The agriculture field completely relies on the uncertainty parameter of soil, atmosphere, and water. Technological advancement in IoT and AI assist in resolving this uncertainty factor and recommend the best crops to the farmers so that they can also enhance the productivity of the crops and meet the world's large food demand smartly. Objective: In this paper, we have suggested an IoT and AI-based model which trained with 2200 records of the dataset and seven attributes in Python. The model suggests 22 different crops to farmers after collecting samples through different sensor data. We used soil, temperature, humidity, pH, and rainfall sensors. Soil sensors were used to measure the amount of N, P, and K in soil. Methods: Various supervised machine learning algorithms such as KNN, Decision Tree, Naïve Bayes and Logistic Regression classifiers have applied to build the proposed model. The model is continuously monitoring the field via various sensor data as a sample data for the prediction of best crops to be grown for farmers. Results: In this research, we investigated the contribution of supervised machine learning classifiers like KNN, Decision Tree, Naïve Bayes and Logistic Regression classifiers. The maximum accuracy has been observed as 99.39% of the Naïve Bayes classifier. Conclusion: In this paper an AI and IoT based model is used to recommend/predict the best crop based on environmental factors. The proposed model will collect the real time sensor data to predict the crops and plants smartly.