Artificial intelligence applications for tailored crop-specific lighting in indoor agriculture

Indoor farming presents a promising avenue toward sustainable and localized food production by offering controlled environmental conditions. Among the critical factors influencing crop yield, artificial lighting stands out due to its significant energy demands and direct impact on plant physiology. Traditional lighting regimes, often static and generalized, fail to adapt to the dynamic needs of plants across various developmental stages. Unlike traditional lamps, modern LEDs can emit tailored blends of wavelengths- blue, red, far-red, green, and even UV. This flexibility is the foundation for personalized approaches, making every light photon count. Recent advancements in artificial intelligence (AI) techniques-such as machine learning, deep learning, reinforcement learning, and evolutionary algorithms-offer transformative solutions for optimizing lighting in real time. These AI-driven approaches leverage sensor data and predictive modeling to dynamically adjust spectral composition, light intensity, and photoperiods, aligning artificial lighting with the physiological requirements of plants at each developmental phase. These personalized light managements improve biomass yield, accelerate growth rates, and reduce energy consumption and also offers a powerful way to push yield, flavor, and nutrient density in indoor crops. However, despite promising results, challenges persist in data acquisition, model scalability, and real-world implementation.

کلیدواژه ها:

Biomass ، Light wavelength ، Plant photoreceptors ، Sustainable agriculture