Optimization of Aquaponic Lettuce Evapotranspiration Based on Artificial Photosynthetic Light Properties Using Hybrid Genetic Programming and Moth Flame Optimizer

Abstract

Land and water resources, climate change, and disaster risks significantly affect the agricultural sector. An effective solution for growing crops to improve productivity and optimize the use of resources is through controlled-environment agriculture (CEA). Evapotranspiration (ET) is an important greenhouse crop attribute that can be optimized for optimum plant growth. Light intensity and radiation are significant for controlling ET. To address this challenge, this study successfully determined the properties of optimum artificial light for minimum evapotranspiration rate of head development-stage and harvest-stage lettuce under light-period and dark-period using genetic programming and bio-inspired algorithms namely, grey wolf optimization (GWO), whale optimization algorithm (WOA), dragonfly algorithm (DA), and moth flame optimization (MFO). MFO provided the optimized global solution for the configured models. Results showed that head development-stage lettuce requires higher light intensity with lower visible to infrared radiation ratio (Vis/IR) than harvest-stage lettuce when exposed to light. On the other hand, harvest-stage lettuce requires higher light intensity with lower Vis/IR than head development-stage under dark-period respiration reaction. Findings of this study can be utilized in growing and improving yield crops in controlled-environment agriculture.