Sovereign 8s.is mirror of standardgalactic/FEs-Inverse-Design
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Zhaochen_Xi 538dec46ba
Some checks failed
Python package / build (push) Has been cancelled
Update python-package.yml
2025-12-26 16:11:45 +08:00
.github/workflows Update python-package.yml 2025-12-26 16:11:45 +08:00
Active Leaning Add files via upload 2025-12-25 21:50:09 +08:00
cVAE Delete cVAE/11 2025-12-16 21:57:04 +08:00
README.md Update README.md 2025-12-25 22:31:39 +08:00
workflow.png Add files via upload 2025-12-16 18:04:01 +08:00

FEs-Inverse-Design

This repository contains the source code and datasets for the research paper: "Active learning in latent spaces enables rapid inverse design of ferroelectric ceramics for energy storage".


image

🚀 Key Features

Conditional Variational Autoencoder (cVAE): Constructs a coupled search space that synergistically models chemical constraints and domain structure evolution.

  1. Latent Space Optimization: Implements a two-stage multi-objective genetic algorithm (NSGA-II) to navigate the latent space for Pareto-optimal solutions.

  2. Active Learning Surrogate: Uses symbolic regression and ensemble learning (CatBoost, XGBoost, etc.) to predict energy density and efficiency with uncertainty quantification.

  3. Phase-Field Simulation: Generate reference domain structures for training.

📁Repository Structure

cVAE/: Code for training the Conditional Variational Autoencoder and reconstructing energy landscapes.

ActiveLearning/: Latent space optimization algorithm, Surrogate model as fitness function of optimization algorithm, uncertainty quantification.

README/: Docs