Bayesian methods for palaeoclimate reconstruction
Bayesian modelling is especially useful when palaeoclimate evidence is incomplete, heterogeneous or uncertain. These studies use hierarchical models, structural time series and latent-state approaches to combine records while representing uncertainty explicitly.
Regional synthesis
A multilevel Bayesian model combines 33 eastern Mediterranean temperature reconstructions.
Missing-data reconstruction
Lake Ohrid proxy gaps are reconstructed with latent state-space models and SSVS.
Environmental transitions
Hierarchical change-point models estimate transition dates from multiple Lake Bafa proxies.
Related concepts
Bayesian inference · MCMC · environmental time series · palaeoclimate proxy data · uncertainty quantification · reproducible quantitative analysis