BoFire
A Bayesian optimization framework designed for experimental design in chemistry and materials science. It optimizes black-box functions with mixed features, constraints, and multi-objective targets, supporting design of experiments (DoE) workflows.
Features
- Optimization: Bayesian, multi-objective
- Constraints: linear, nonlinear, discrete
- DoE: Latin hypercube, Sobol sequences
- Integration: BoTorch, GPyTorch backend
Citation
BASF Digital Solutions GmbH. BoFire: Bayesian Optimization Framework for Industrial Research and Engineering. https://github.com/experimental-design/bofire