How to have absolute importance of predictor variables in boosted regression trees (BRT) model?

Thank you very much for your time.

I would like to compare the contribution of predictor variables (X1) from different BRT (Boosted regression trees) models, which are from different spatial scales (Radius= 250m, 160m, 80m, 40m, 10m). But the contribution in BRT is a relative contribution. I want to know each variable's absolute contribution (absolute importance), then I can compare them.

I used the formula R-squared = 1 - (Residual sum of squares/Total sum of squares) to calculate R-squared (total R2) in R studio. At first, I would like to use partial R2 instead, but it only belongs to the linear regression model in ‘relaimpo’ package in R. So, my question is can I use the formula: (X1 's contribution) * (total R2) = X1's R2 in BRT model?

For example, in the figure uploaded, I want to compare the predictor variable X1's contribution (yellow bar) on the model of 250m and 160m, which is higher? if we only compare the relative contribution of the models in 250m (52%) and 160m (44%), it's 250m that higher. But if we consider the total R2, it's different, the 160m model (0.233) has a higher R2 than the 250m model (0.129). Thus, can I use the formula: 0.12952%=0.067 for X1’s R2 in 250m model; and 0.23344%=0.1 for X1’s R2 in 160m model? Then the result should be that X1 in the 160m (R2=0.1) contribute more than X1 in 250m (R2=0.067).