Interplay between Swampland and Bayesian Machine Learning in constraining cosmological models

Abstract Constraints on a dark energy dominated Universe are obtained from an interplay Bayesian (Probabilistic) Machine Learning and string Swampland criteria. Unlike in previous studies, here, the field traverse itself has been used to constraint theory reveal its connection approach. The based approach is applied two toy models. A parametrization of Hubble constant for first model, while deceleration parameter considered second one. results here allow estimate how high-redshift behavior will affect low-redshift Moreover, adopted may highlight, future, borders help develop new string-theory motivated most important message our study hint that criteria might be tension with recent observations indicating phantom cannot Swampland. Finally, another interesting result spontaneous sign switch equation state when traverses $$z\in [0,5]$$ z ∈ [ 0 , 5 ] redshift range, remarkable phenomenon requiring further analysis.