AI-Driven Pheno-Parenting: A Deep Learning Based Plant Phenotyping Trait Analysis Model on a Novel Soilless Farming Dataset

Abstract

Agriculture 4.0 will be data-driven and utilise modern technology in order to monitor plant life cycles and traits, resulting in better yield. Pheno-parenting, a new concept, derives certain methodologies from plant phenotyping, which monitors plants at various stages of their life cycle and supports their growth by deploying modern tools and technologies. In this work, a small-scale hydroponic system was set up for plant life cycle image data collection and analysis, which consists of thirty plants of three species (i.e., petunia, pansy, and calendula), with ten plants of each species grown. A Deep Neural Network (DNN)-based approach has been adopted to analyse key tasks such as plant species recognition, growth analysis, health analysis, and yield stage identification. Calendula plants have been correctly recognised with above 95% detection accuracy in all test cases. The result thus obtained indicates that side-view images are more effective at identifying species and tracking growth. On the other hand, top-view photographs do a better job of capturing the texture and colour characteristics of leaves and budding flowers. The Growth Development Index (GDI) metric, which first rises with an increase in nutrient input up to 31 ml and then saturates, has been proposed to provide a better understanding of plant growth, health, and productivity.

Keywords

• Computer vision
• deep learning
• hydroponic farming
• life cycle data analysis
• pheno-parenting
• phenotyping