LSTM-POWERED SMART GROWTH CHAMBER FOR RICE SEEDLING OPTIMIZATION

Abstract Considering the global crisis for food supply, machine learning applications have a significant impact on agriculture and the global economy by transforming the methods for data processing and decision making. This research presents an intelligent system designed to optimize rice cultivation using automated growth chambers managed by Long Short-Term Memory (LSTM) models. The setup employs an IoT-enabled microcontroller integrated with sensors that continuously monitor key environmental parameters such as temperature, humidity, light intensity, CO₂ concentration, and soil moisture. The real-time sensor data is processed by the LSTM model to predict and dynamically adjust environmental conditions for optimal plant growth. This adaptive control system enhances seedling development while reducing resource consumption. The approach minimizes reliance on external weather conditions and ensures efficient use of agricultural inputs, leading to improved crop yield and quality. Furthermore, the system is scalable and adaptable for implementation in diverse and non-traditional agricultural settings. By leveraging machine learning and precision farming techniques, this study contributes to the advancement of sustainable and data-driven agricultural practices that hold potential for application to a wide range of crops in the future.