Welcome to BOAR’s documentation!

BOAR is a Python package for Bayesian Optimization. It is designed to be a flexible and easy-to-use tool for researchers and practitioners alike. While it can be used for a wide variety of applications, the implemented agents are specifically designed for solar cell and general research on semiconductor. The package is designed to be modular and extensible, allowing users to easily add new agents.

Most of the agents in BOAR can be used to fit a model to experimental data, yet BOAR can be also used to optimize experimental process condition and guide experimentation in an automated fashion.

See the BOAR GitHub repository for more information.

Authors

• Larry Lüer

• Vincent M. Le Corre

Institution

Institute Materials for Electronics and Energy Technology (i-MEET)

University of Erlangen-Nuremberg (FAU)

Erlangen, Germany

What is currently implemented in BOAR? : The optimizers & agents

The optimizers

The optimizers are used to find the optimal parameters for a given optimization problem.

Available optimizers are:

• scikit-optimize

• scipy.optimize.curve_fit

• Ax & BoTorch

Currently, the main optimizer implemented in BOAR is based on scikit-optimize (skopt). It is the default optimizer used in BOAR and the most tested one.

For more information on the optimizers, see the optimizer section.

The agents

The agents are used to run a model depending on the input parameters given by the user or the optimizers. Users are free to create their own agents. For more information on the agents, see the agents section.

Available agents are:

• Drift-diffusion agent (DD)

• Transient absorption spectroscopy agent (TAS)

• Transient photoluminescence agent (TrPL)

• Transient microwave conductivity agent (TrMC)

• Transfer matrix agent (TM)

Getting started:

• Installation
  • With pip
  • With conda
  • Additional necessary for BOAR with BoTorch/Ax
• Additional necessary installs for the agents
  • Drift-diffusion agent
    • SIMsalabim
    • Parallel simulations
• Disclaimer
• Scientific publications based on the BOAR project
• Change Log
  • v1.0.10
  • v1.0.9

Model fitting examples:

• BOAR with SIMsalabim
  • Define the free parameters to be optimized
  • Check the structure of the device for SIMsalabim
  • Prepare fake data for fitting
  • Start the optimization
• BOAR with SIMsalabim Organic Photovoltaic (OPV) example
  • Import Experimental Data
  • Fit non-ideal diode model
  • Multi-Objective Optimization
    • Define the fitting parameters
  • Start the optimization
• BOAR for TAS fitting
  • Define the free parameters to be optimized
  • Prepare fake data for fitting
  • Start the optimization
• Multi-Objective Fitting of TrPL and TrMC Data
  • Prepare Experimental Data
  • Define the free parameters to be optimized
  • Start the optimization
  • Gradient descent
• Notebooks gallery
  • BOAR with SIMsalabim
    • Define the free parameters to be optimized
    • Check the structure of the device for SIMsalabim
    • Prepare fake data for fitting
    • Start the optimization
  • BOAR with SIMsalabim
    • Define the free parameters to be optimized
    • Check the structure of the device for SIMsalabim
    • Prepare fake data for fitting
    • Start the optimization
  • BOAR with SIMsalabim Organic Photovoltaic (OPV) example
    • Import Experimental Data
    • Fit non-ideal diode model
    • Multi-Objective Optimization
    • Start the optimization
  • BOAR for TAS fitting
    • Define the free parameters to be optimized
    • Prepare fake data for fitting
    • Start the optimization
  • BOAR for TrPL fitting
    • Define the free parameters to be optimized
    • Prepare fake data for fitting
    • Start the optimization
  • Multi-Objective Fitting of TrPL and TrMC Data
    • Prepare Experimental Data
    • Define the free parameters to be optimized
    • Start the optimization
    • Gradient descent

Optimization and DoE examples:

• Design of Experiments to optimize perovskite solar cells efficiency
  • Define the free parameters to be optimized
  • Start the optimization
• Multi-objective optimization for perovskite material composition
  • Define the free parameters to be optimized
  • Start the optimization
• Custom evaluate function for Multi-Objective Optimization - Transfer Matrix example
  • Define the free parameters to be optimized
  • Start the optimization
• Notebooks gallery
  • Design of Experiments to optimize perovskite solar cells efficiency
    • Define the free parameters to be optimized
    • Start the optimization
  • Multi-objective optimization for perovskite material composition
    • Define the free parameters to be optimized
    • Start the optimization
  • BOAR with Transfer Matrix Method
    • Define the free parameters to be optimized
    • Start the optimization
  • Custom evaluate function for Multi-Objective Optimization - Transfer Matrix example
    • Define the free parameters to be optimized
    • Start the optimization
  • BOAR with Transfer Matrix Method
    • Define the free parameters to be optimized
    • Start the optimization

BOAR API:

• boar
  • boar package
    • Subpackages
      • boar.SIMsalabim_utils package
      • boar.agents package
      • boar.core package
      • boar.dynamic_utils package
    • Module contents

Indices and tables

• Index

• Module Index

• Search Page