A Bayesian hierarchical model for bias predicition of climate model output that considers underlying spatial correlation is developed. The model is developed in Python and utilises the model building framework and inference schemes of Numpyro. Additionally, the TinyGP package is utilised for generating Gaussian process objects and the ArviZ package for computing summary statistics.

The model is applied to simulated examples, where the data generation, model fitting and prediction scripts are available under the scripts/Data_Generation_and_Model_Fitting folder. Hierarchical and non-hierarchical examples are given. Scripts that generate figures in the paper 'Bias Correction of Climate Models using a Bayesian Hierarchical Model' J.Carter et. al. are available in the scripts/Paper_Figures_Generation folder. The actual PDFs of the figures themselves are available in the results/ folder. Modules that include the functions that define the model as well as general helper functions are available in the src/ folder.