Abstract
Recent theoretical works have shown that the interaction between the signal of demography and selection can lead to bias in the inference of population size and the false identification of adaptive loci in genome scans. The joint estimation is a necessity, however not yet fully implemented. We propose the use of ABC Random-Forests to implement the joint inference in temporal population genomics datasets. Preliminary results showed that the method permits the joint inference of demography and selection, allowing distinguish the true demography (census size) and genetic drift (effective population size), as well the estimation of the genetic load (selection).