Avoiding toxic levels of essential minerals: a forgotten factor in deer diet preferences

Abstract

Ungulates select diets with high energy, protein, and sodium contents. However, it is scarcely known the influence of essential minerals other than Na in diet preferences. Moreover, almost no information is available about the possible influence of toxic levels of essential minerals on avoidance of certain plant species. The aim of this research was to test the relative importance of mineral content of plants in diet selection by red deer (Cervus elaphus) in an annual basis. We determined mineral, protein and ash content in 35 common Mediterranean plant species (the most common ones in the study area). These plant species were previously classified as preferred and non-preferred. We found that deer preferred plants with low contents of Ca, Mg, K, P, S, Cu, Sr and Zn. The model obtained was greatly accurate identifying the preferred plant species (91.3% of correct assignments). After a detailed analysis of these minerals (considering deficiencies and toxicity levels both in preferred and non-preferred plants) we suggest that the avoidance of excessive sulphur in diet (i.e., selection for plants with low sulphur content) seems to override the maximization for other nutrients. Low sulphur content seems to be a forgotten factor with certain relevance for explaining diet selection in deer. Recent studies in livestock support this conclusion, which is highlighted here for the first time in diet selection by a wild large herbivore. Our results suggest that future studies should also take into account the toxicity levels of minerals as potential drivers of preferences.

Figure 1. Probability of correct assignment of preferred (A) and non-preferred plans (B) in the model obtained through binary regression (see text).

CF1, related to high content of K, Ca, protein, S, Sr and Zn was the only significant factor in the model (with a negative coefficient). CF2, CF3 and plant category (shrubs vs. herbaceous) were not significant in the model. The model was quite effective for identifying preferred plants, but poor for identifying non-preferred ones.