Applying Artificial Neural Networks to Oxidative Stress Biomarkers in Forager Honey Bees (<i>Apis mellifera</i>) for Ecological Assessment

Abstract

Insect pollinators provide an important ecosystem service that supports global biodiversity and environmental health. The study investigates the effects of the environmental matrix on six oxidative stress biomarkers in the honey bee Apis mellifera. Thirty-five apiaries located in urban, forested, and agricultural areas in Central Italy were sampled during the summer season. Enzyme activities in forager bees were analyzed using an artificial neural network, allowing the identification and representation of the apiary patterns in a Self-Organizing Map. The SOM nodes were correlated with the environmental parameters and tissue levels of eight heavy metals. The results indicated that the apiaries were not clustered according to their spatial distribution. Superoxide dismutase expressed a positive correlation with Cr and Mn concentrations; catalase with Zn, Mn, Fe, and daily maximum air temperature; glutathione S-transferase with Cr, Fe, and daily maximal air temperature; and glutathione reductase showed a negative correlation to Ni and Fe exposure. This study highlights the importance of exploring how environmental stressors affect these insects and the role of oxidative stress biomarkers. Artificial neural networks proved to be a powerful approach to untangle the complex relationships between the environment and oxidative stress biomarkers in honey bees. The application of SOM modeling offers a valuable means of assessing the potential effects of environmental pressures on honey bee populations.

Keywords

• biological indicators
• biomarkers
• environmental factors
• metals
• Self-Organizing Map