Optimizing crop yield using hydroponic farming on tomato plants by applying deep neural networks

Deep learning constitutes a recent, modern technique for new variants in agriculture with quality yield, minimal resources, and large potential. As deep learning has been successfully applied in various domains, it has recently entered also the domain of agriculture. In this paper, hydroponic farming is employed using deep learning techniques for tomato plant production addressing major challenges for increasing the production using a small area for cultivation and also in a short span of time. By examining the production and agricultural problems understudy the novel technology of smart farming techniques can be implemented for overall performance. Hydroponic system, multi-planned air flow, moisture, amount of nutrients thresholds of carbon dioxide and nitrogen can be controlled and operated using deep learning techniques. IoT sensors and use of UAVs assist in controlling the other aspects of production. The study evaluates the application of deep learning methods on tomato plants for optimizing high quality yields of production. In this research study 1500 sq. ft. land was used for cultivating the hydroponic farming of tomato plants automating supply of nutrients, water and use of controlled environment with low cost. This study was conducted for about six months from March 2020 to September 2020. The results show that 27% production was increased yielding best quality tomatoes with minimum investment and time span.