Comparative Evaluation of AI Algorithms for Real-Time IoT based Plant Assessment

Plants are essential for sustaining life by providing oxygen, food, and maintaining ecological balance. Their growth and health depend on number of environmental factors such as soil moisture, humidity, temperature, and water availability. Traditionally, human intervention in plant care relies on manual observation, which can be insufficient and prone to errors. However, by combining AI, IoT and cloud computing technologies, this research enables real time monitoring and data driven decision-making, ensuring optimal plant health while promoting efficient resource utilization and sustainability. This study presents a comparative evaluation of AI algorithms for real time plant condition assessment using an IoT-based system. The environmental parameters like soil moisture, humidity, water level, and temperature of plants were utilized to analyze the plant conditions. Various AI models, including Random Forest, Decision Tree, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and XG Boost, were trained to predict the plant conditions. Upon evaluation, Random Forest demonstrated the highest accuracy and reliability in predicting the plant needs. Consequently, this model is integrated into an IoT framework comprising a Raspberry Pi and respective environmental sensors like DHT11, Soil moisture sensor, Water level sensor. The system processes real time sensor data, analyses it through the trained AI model, and also stores it in a cloud and provides automated recommendations on motor activation when required. The cloud storage allows historical data tracking, performance analysis, and future improvements in predictive accuracy. This ensures efficient water usage while maintaining optimal plant health. The study emphasizes how well AI-powered decision-making works in precision farming and highlights the importance of model selection for improving prediction accuracy. The findings contribute to the advancement of smart farming technologies, demonstrating the potential of AI-IoT-cloud convergence in optimizing resource management and enhancing sustainability in agriculture.