Abstract
Controlled environment agriculture is uniquely positioned to contribute to the decarbonization of cities due to its low carbon emissions and high energy efficiency in the food supply process. The energy consumed by the horticultural industry to supplemental lighting is enormous, but improvements in the light environment of greenhouse plants are essential. To make light regulation compatible with low carbon and environmentally friendly while improving photosynthetic production, experiments on tomato plant measurements with nested light intensity, spectra, carbon dioxide concentration and temperature were carried out in a solar greenhouse based on an infrared gas analyzer and machine learning. Based on the photosynthetic response to the photosynthetic photon flux density and red–blue ratio under multi–environmental conditions, the photosynthesis prediction model was developed using the least squares support vector regression, and model hyperparameter optimization was achieved by genetic algorithm nested cross–validation. A calculation method of carbon emissions from supplemental lighting was proposed, and the low–carbon light regulation was abstracted into multi–objective optimization for the solution. Based on the comprehensive objective evaluation method, low–carbon targets for light regulation were obtained through decision–making. The results showed that the developed prediction model with root mean square error of 1.069 and determination coefficient of 0.976, which is both accurate and fast, realizes the description and expression of the net photosynthetic rate in response to the environments. The optimal targets contain two–dimensional information of light intensity and spectra, and reduces carbon emissions by a maximum of 14.85% compared to the light saturation objective based on single–objective optimization at 95.49 % of the net photosynthetic rate. The method is energy efficient and suitable for supporting multi–spectral light environment regulation applications and guiding the greenhouse environment management under the demand of carbon reduction.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.