| """ | |
| Physics-Informed Bayesian Optimization Platform (PIBO) | |
| A platform for designing experiments using physics-informed surrogate models | |
| with Bayesian optimization. Supports BoTorch, AX, GPyTorch, and BoFire backends. | |
| Core concept: Use physical models as structured priors (mean functions) for | |
| Gaussian Processes, so the GP learns residuals between physics predictions | |
| and real observations. This dramatically improves sample efficiency. | |
| """ | |
| from physics_informed_bo.models.base import SurrogateModel | |
| from physics_informed_bo.models.physics_model import PhysicsModel, PhysicsMeanFunction | |
| from physics_informed_bo.models.hybrid_model import HybridSurrogate | |
| from physics_informed_bo.experiment.designer import ExperimentDesigner | |
| from physics_informed_bo.experiment.parameter_space import ParameterSpace, ContinuousParameter, CategoricalParameter | |
| from physics_informed_bo.experiment.campaign import OptimizationCampaign | |
| __version__ = "0.1.0" | |
| __all__ = [ | |
| "SurrogateModel", | |
| "PhysicsModel", | |
| "PhysicsMeanFunction", | |
| "HybridSurrogate", | |
| "ExperimentDesigner", | |
| "ParameterSpace", | |
| "ContinuousParameter", | |
| "CategoricalParameter", | |
| "OptimizationCampaign", | |
| ] | |