F. Bockting
  • Home
  • Software
  • Stack
  • Engagement
  • Research

Open Source Software

Open-source software is central to how I work, as a maintainer of Python packages in Bayesian methodology and climate data pipelines, and as a contributor to established R packages in the Stan ecosystem. For the tooling behind this work, see the Stack page.

Maintainer / Author
elicito Python

Python package for learning prior distributions of model parameters from expert knowledge.

Statistics Bayesian
Paper PyPI Docs
gradient-aware-harmonisation Python

Python package for harmonizing two time series using zero- and first-order gradient information.

Climate Science Time Series
GHG-forcing-for-CMIP Python

Pipeline for constructing a composite greenhouse gas dataset from ground-based and satellite observations, suitable as forcing input for climate models in CMIP.

Climate Science Data Pipeline
Contributor
loo R

Efficient leave-one-out cross-validation and WAIC for Bayesian models.

Statistics Bayesian
bayesplot R

Plotting functions for posterior distributions, prior/posterior checks, and MCMC diagnostics.

Plotting Bayesian
posterior R

Tools for manipulating and summarizing posterior and prior distributions.

Statistics Bayesian
brms R

High-level R interface for fitting Bayesian regression models via Stan.

Statistics Bayesian
CMIP7-GHG-Concentration-Manuscripts Python

Reproducible manuscript workflow. JupyText notebooks compiled to publication-ready LaTeX PDFs.

Climate Science Tooling
input4MIPs_CVs Data

Controlled vocabularies for the input4MIPs project, defining the allowed metadata terms across datasets.

Climate Science Tooling
CMIP7 ScenarioMIP GHG Concentrations Python

Generation of greenhouse gas concentration inputs (forcings) for CMIP7's ScenarioMIP.

Climate Science Data Pipeline

©️ 2026, Florence Bocking