The Elk River, Gulf Wars, and Atlantic Oxybenzone instances proved chemical contamination is a serious threat. HC is a common corticosteroid used to treat skin lesions that hasn't undergone testing. This research will utilize real plant cultivation, mathematical modeling, machine learning, and custom Python3 programming to determine the effect of HC on plant life. Metadata significant at a 0.01 level under 48 degrees of freedom was gathered by cultivating real Raphanus sativus plants treated with various levels of HC contaminated water; the t-test was verified using Java8 computer code. The simulation comprised of three independent algorithms. Because the metadata was very sparse, the first algorithm was dedicated to using modified bootstrapping to iteratively generate synthetic data points with less entropy. The second algorithm was a deep learning substructure incorporating concepts of linear regression and neural networks; the backpropagation used the MSE loss function and ADAM optimizer, which has aspects of previously engineered AdaGrad and RMSProp models. The third algorithm measured the effect of HC on a terrain based on aquatic content. The simulations used an HC contaminator based of the Gulf Wars event and five semi-aquatic terrains in North America, which were the contaminator and terrestrial parameters respectively. The plant cultivation and software simulations supported the research hypothesis stating that the uncontaminated plants would be healthiest was accepted. Future research could use convolutional neural networks to achieve a higher R-squared value and real-time procedural terrain generation to improve the simulations.