Artificial Intelligence Assessment of Runoff-Induced Abnormalities in Amphibian Larvae

Abstract

Amphibians can be regarded as one of the most important indicators of ecological well-being due to the high sensitivity of the larval development stage to any freshwater environment changes. Runoff from agricultural, urban and industrial areas leads to pollution of the aquatic environment by pesticides, nutrients, heavy metals, and sediments that induce stress and abnormalities in amphibian larvae. Traditional methods of assessment focus on analysis of each factor independently, which is unable to adequately cover the complicated connections between multiple stress factors. The purpose of this research is the assessment of runoff-induced abnormalities in amphibian larvae with the help of an artificial intelligence-based framework for evaluation. Water parameters like quality, pollutant concentration, turbidity, oxygen level, nutrients and chemicals, and indicators of larval condition like growth abnormalities, morphology, swimming ability and survival reactions were analyzed. Based on the results, it was determined that higher levels of runoff pollution were found to have a strong relationship with abnormal rates, as heavy metal, pesticide, low dissolved oxygen, and high turbidity were found to be strongly affecting the well-being of larvae. The artificial intelligence (AI)-based predictive model proved to be an efficient way of capturing complicated ecological interrelationships and was found to provide enhanced predictions as compared to traditional machine learning methods. This research presents the possibilities of using artificial intelligence as an auxiliary technology in assessing and managing the environment of freshwater ecosystems and amphibians.