Abstract—Developing the agricultural industry for consumption to meet demand has been a factor that has been given importance for a long time. The next factor and the main part for focus at present are factors that affect quality and characteristics desirable to the needs of consumers, especially vegetables that are beneficial to the body. Developing vegetable cultivation that supports urban societies with low space areas but requires large quantities of produce and characteristics that meet consumers’ needs is an important part. Therefore, this article presents a vertical pitch plant with an automatic closed-loop system; this work develops a vertical hydroponic greenhouse with an automatic closed-loop system. The implemented Artificial Intelligence (AI) algorithms, Industrial Internet of Things (IIoT), and Programmable Logic Controllers (PLC) were applied together to predict the application of light and nutrient solutions to feed red oak salad vegetables for properties that desired characteristics consumers. The experiment results showed that when the Artificial Neural Network (ANN) and fuzzy technology were used, they could predict the most appropriate lighting and nutrient solution after using the prediction results to grow salad vegetables. In addition, the research also applies the Convolutional Neural Networks (CNN) algorithm to the inspection process. According to the prediction of the neural network algorithm, which is consistent with the experimental results. The results were consistent and reliable, and the efficiency was satisfactory.

Keywords—vertical farming, adaptive neuro-fuzzy inference system, programmable logic controller, industrial internet of things, optimization

Cite: Sasithorn Chookaew and Suppachai Howimanporn, "Implementing Predictive Analytics to Optimize Parameter for Automation Vertical Farming Using Deep Learning," International Journal of Mechanical Engineering and Robotics Research, Vol. 14, No. 3, pp. 262-275, 2025. doi: 10.18178/ijmerr.14.3.262-275

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).