Paper Title
EnviroNet: A Systemic Approach to Maximize Agricultural Vitalities by Leveraging Automation-Induced Deep Learning Techniques for a Manipulative Monitoring Matrix

Abstract
With automation being at the forefront of ways to satisfy agricultural demand, the maximization of yield is crucial to subsidize it. The proposed way that this maximization could be achieved is by knowing exactly what conditional factors allow it. Such is the focus of EnviroNet, a novel advancement in the parallel workings of deep learning and flexible automation, functioning to attain the parameters of an optimal growing environment for every plant, compromised for individuality. The key intuition behind EnviroNet is that it simultaneously learns from variations in the plants’ health about what physical parameters to adjust for maximum benefit, just from the automated tasks being performed that keep the conditions for the plants balanced. These include variables such as the temperature, humidity, soil nutrient-level (with moisture), sun/ambient light, and air quality. The recurrent web-based monitoring and manipulation of these parameters coupled by constant updates of image data visually portraying the state of the plants, allow deep learning to detect unintuitive patterns in the growth of plants, both cumulatively and personalized, relative to time. Keywords - Flexible Automation, Deep Learning, Agriculture