Background : Advanced IoT Agriculture presents a transparent review of emerging technologies like IoT-based smart Agriculture. Today’s Agriculture industry is data-centered, advanced, and smarter than ever. Smart Agriculture moved the industry from a statistical to a quantitative approach.

Objective: The objective of this paper is to monitor the plant growth using machine learning technique, as well as predicting the plant growth patterns; to integrate and analyze machine learning models for assessing data obtained from IoT devices in order to predict plant health and growth; and to assess the performance of several IoT communication protocol LoRa in terms of data transmission, dependability, and energy efficiency in agricultural settings.

Material/Methods : In this paper , we have collected the real-time data through the different IoT sensors, namely soil moisture, temperature, and humidity, that are crucial for plant health. The collected data are transmitted to a cloud-based platform, where they undergo preprocessing and analysis. Advanced IoT devices generally automate environmental responses, requiring control systems. The key feature of this system is the deployment of the smart devices and sensors for the collection of data like average wet growth, plant height rate, average leaf area of the plant, average root length, and decisions based on the monitoring of trees. In this paper, our objective is to estimate the effectiveness of various machine-learning approaches for predicting plant growth outcomes based on the collected data.

Result We used several machine learning classifiers including Decision Trees, Naïve Bayes, and K-Nearest Neighbors. It has been observed that out of all the classifiers, the Support Vector Machine (SVM) performs well as comparison to other classifiers, i.e., by 99.96%. Other models also performed well, with Naïve Bayes and Decision Trees, both achieving 99.91% accuracy, and K-Nearest Neighbors achieving 98.99%. The result reveals the efficacy of integrating IoT solutions with advanced machine-learning techniques to enhance plant growth monitoring.