Post Views:
117
Abstract
The integration of Artificial Intelligence offers transformative solutions to modern-day challenges, especially in sectors like agriculture that are pivotal for human sustenance. This study underscores the profound impact of Artificial Intelligence in conditioned agricultural practices within greenhouses, based on data from an agricultural competition where teams optimized greenhouse performance using Artificial Intelligence-driven mechanisms. Results indicate that Artificial Intelligence-enhanced control strategies can drastically reduce energy consumption, particularly heating loads, without compromising crop yield, quality, or profitability. In some instances, performance even surpassed conventional methods. However, there are areas like Carbon Dioxide emissions and water usage where enhancements are still essential. Building on these insights, the study further ventures into AI’s potential to predict greenhouse production outcomes. Through rigorous assessment of various machine learning models, the Radial Basis Function model exhibited commendable performance, achieving an Root Mean Squared Error of 0.8 and an R-squared value of 0.98 post-optimization. This establishes the feasibility of precisely forecasting greenhouse production rates in terms of kg/m2. While this research predominantly centers on production volume, it lays a strong foundation for the predictive potential of AI in greenhouse operations and underlines the benefits of input optimization. It paves the way for future research focused on both the quality and quantity of greenhouse production.