Autonomous thermal meta-regulators with arbitrary spectral selection by deep learning

Read full text Summarise with VIRAT
Authors: Shaowen Chen, Han Zhou
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Code and dataset for inverse design of Autonomous thermal meta-regulators Description System requirments Dependencies Pytorch > 2.0.1+cu117A Tested Environments python: Python 3.8, Pythorch 2.0.1+cu117, CUDA 10.1,cuDNN 7.6 Python 3.9, Pythorch 2.0.1+cu117, CPU devices MATLAB: MATLAB (version compatible with RETICOLO V10)- RETICOLO V10 (third-party MATLAB package for RCWA and thin-film stack analysis; required for optical simulations and not included in this archive) Other softwares CST Studio Suite and a compatible MATLAB environment for joint simulation and validation screening Installation Miniconda (3 mins) conda create -n design python=3.8 conda activate design pip install torch==2.0.1+cu117 torchvision==0.15.2+cu117 Instrucstionas and demo This program does not provide an external API for calling. Adjustments to the target spectral parameters must be made within the script before running. Dataset colletion (~15 mins per model) Path: AMR_construction 1. Generate Turing Pattern Database Run TULINpattern.m in MATLAB 2. AMR Generation and Spectral Analysis Run AMR_running.m in MATLAB - Generates AMR (Dielectric Metasurface Resonator) modes - Obtains IR spectral responses 3. Optical Analysis Run RCWA_optical_simulation.m in MATLAB with RETICOLO V10 installed. - Calculates reflectivity and transmittance of the multilayer AMR structures 4. Data Integration and Preprocessing Run data_integrate.m in MATLAB - Integrates AMR results - Normalizes spectral data - Exports processed data - Export the processed data to Excel format for further analysis Dimensional reduction (~1 hours) Path: Dimensional reduction 1. Spectral Data Dimensionality Reduction Run AE_DR.py in Python - Compresses high-dimensional IR spectral data into a low-dimensional latent representation 2. Graphic Parameter Data Dimensionality Reduction Run VAE-main2.py in Python - Compresses high-dimensional AMR graphic parameters into a low-dimensional latent vector that follows a probabilistic distribution This combined latent representation serves as the input for the subsequent training and generation of MCGANs Prediction (~1 hours) Path: Prediction Run Simulator_VIS_ref.py - Train and save the visible reflectivity prediction module. Run Simulator_VIS_trans.py - Train and save the visible transmittance prediction module. Run Simulator_IR.py - Train and save the IR emissivity prediction module. Inverse design (~8 hours) Path: MCGAN Run General_GAN_con_VIS_IR.py - Loads the concatenated low-dimensional data and pre-trained prediction modules (Simulators) - Undergoes the lengthy adversarial training process for the Multi-Conditional Generative Adversarial Network (MCGAN) - You can use TensorBoard to monitor the training progress - Saves the final trained generator and discriminator models Run General_GAN_con_VIS_IR_test.py Loads the trained generator model - Performs inverse design to generate the AMR structure parameters for specific targets (e.g., AMR1 ~ AMR12) - Outputs the designed AMR parameters and their predicted optical performance Simulation and Validation (AMR-1 as demo) Path: Validation Run AMR1.py in python - Loads the trained generator model and target specifications for AMR1 - Executes the inverse design process to generate 1000 candidate AMR structure models - Note: Some of these generated models may be duplicates.

Fields of Study & Subjects

Metamaterials and Metasurfaces Applications Thermal Radiation and Cooling Technologies Machine Learning in Materials Science

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
22 March 2026
Language
EN