Machine Learning Evaluation of Zooplankton Responses to Nutrient Enrichment

Abstract

Zooplankton communities are an essential part of the ecosystem in terms of controlling energy flow, sustaining higher trophic level organisms, and reflecting environmental quality changes. Nutrient enrichment that results from agriculture effluents, sewage, and human activities creates a profound impact on fresh water ecosystems by altering the amount of nutrients present in the environment. Nitrogen and phosphorous enrichment may affect algal growth, oxygen content in the water, and the habitat, causing alterations in the number, biodiversity, and species composition of zooplanktons. The present research paper aims at studying zooplankton community response to nutrient enrichment by applying ecological assessment techniques assisted by machine learning methods.  The results of the predictive analysis revealed that nutrient-related parameters played a significant role in defining the distributions of zooplankton communities. As for different applied techniques, the Random Forest model offered better opportunities for predicting by detecting the interactions between various ecological parameters. The results of the research showed that the process of nutrients enrichment leads to the change in the composition of the zooplankton community, which means that tolerant species dominate in poor environments. It was possible to show that machine learning-assisted assessment may be used as an additional tool for determining aquatic animal reactions.