GCA

Work Description:
Glyphosate-based herbicides (GBHs) are among the most widely used pesticides and are considered ubiquitous in ecosystems. Among contaminated environments, soil plays a critical role in the dissipation of glyphosate into other natural resources. The presence of GBHs in the environment is linked to ecological imbalances and poses risks to human and animal health. However, current methods for detecting glyphosate are costly and time-intensive, leading to minimal or absent monitoring in many countries. In this context, mathematical and computational models, which facilitate outcome prediction and variable classification, can be employed to detect environmental contaminants. Therefore, this project proposes the application of mathematical models and machine learning algorithms to identify the presence of glyphosate-based herbicides (GBHs) in soil, using biological indicators (earthworms) and physicochemical soil variables. Earthworms were selected as representatives of soil fauna due to their sensitivity to pollutants, making them effective bioindicators. The general objectives of this project are as follows: (1) To evaluate whether exposure to agronomically relevant doses of glyphosate-based herbicides (GBHs) alters the biological and physicochemical properties of the soil environment, and (2) to determine whether, and which, mathematical and computational models can be applied to detect the presence of GBHs in soil, using biological variables of earthworms and physicochemical soil data as input.