KOH-GPJax: Bayesian Calibration with GPU Acceleration

One of the cornerstones of my PhD research has been the development of KOH-GPJax, a Python package for Bayesian calibration of computer models. In this post, I want to walk through what KOH-GPJax is, why I built it, and how it can be used to dramatically accelerate the calibration process. The Challenge: Calibrating Expensive Computer Models Computer models are used everywhere, from climate science to engineering, to simulate complex real-world systems.

Our Nature Paper: Using Gaussian Processes to Perturb Climate Models

I am excited to share that I am a co-author on a paper recently published in Nature Communications Earth & Environment: “A framework for generating stochastic perturbations in chaotic dynamical systems using machine learning”. This work introduces a novel method for representing model uncertainty in complex climate models. The Challenge of Climate Model Uncertainty Climate models are incredibly complex, and one of the major challenges is accounting for “model uncertainty”. This uncertainty arises from processes that occur at scales smaller than the model’s grid resolution.