Automated SMART Greenhouse Environmental Control & Predictive Yield Optimization

Project Overview Modern agricultural operations in rural New Mexico face persistent challenges, including extreme temperature fluctuations, unpredictable microclimates, and water scarcity. This project proposes designing an automated, sensor-driven SMART Greenhouse system paired with computational modeling to optimize growing conditions and conserve natural resources. Technical & Computational Approach The hardware architecture relies on an Arduino microcontroller integrated with a suite of environmental sensors to monitor ambient temperature, soil moisture, relative humidity, and light intensity in real time. Actuators, including automated ventilation fans, drip irrigation valves, and LED growth lighting, dynamically adjust internal conditions based on programmed sensor thresholds. To transition from basic control to predictive computational science, real-time telemetry from the Arduino will be logged and analyzed using a Python-based computational model. By implementing regression analysis and cellular automata modeling, the software will simulate microclimate trends, predict crop water demands, and evaluate daily growth trajectories under varying climate scenarios. sciences Expected Outcomes & Impact By evaluating data collected across multiple trial runs, the computational model will identify ideal operational parameters for crop yield while minimizing energy and water expenditure. This project demonstrates how combining low-cost embedded hardware with predictive computational modeling can empower sustainable, local food production in arid regions.