Table 6. Summary of multivariate random forest regression modeling for each isotopic system.

Variables are ranked by importance in the regression model. The predictors have either a significant positive (italics) or negative (underline) correlation with isotope data (Pearson correlation; p-value<0.01). R² = Coefficient of Determination.

	δ15Nhair		δ13Chair		δ34Shair
Best model	Perf. Metrics	Variables Imp.	Perf. Metrics	Variables Imp.	Perf. Metrics	Variables Imp.
Diet Demographic data	R2 0.05	Vegetarian Seafood	R2 0.18	Soda Age Sex	R2 0.05	Seafood
Diet Demographic data Longitude Latitude	R2 0.12	Vegetarian Longitude Seafood	R2 0.26	Longitude Latitude Soda Sex	R2 0.53	Longitude Seafood Latitude
Diet Demographic data Longitude Latitude Environnemental variables	R2 0.12	Vegetarian Longitude Seafood	R2 0.32	Corn Province Soda Sex	R2 0.62	Precipitation Salt aerosol Seafood Soil pH