PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing

2024-12-26

AI Summary

Thermal photovoltaic (TPV) metasurface inverse design faces challenges in spectral matching between thermal emitters and photovoltaic cells, alongside low optimization efficiency in large design spaces. Method: This paper proposes a novel framework integrating generative modeling and surrogate-based optimization: (i) a Vector Quantized-Variational Autoencoder (VQ-VAE) constructs a discrete latent space for efficient sampling; (ii) a novel Pearson correlation loss function jointly enforces latent-space regularization and surrogate model training; (iii) a Pearson-correlation-based surrogate model guides simulated annealing optimization. Contribution/Results: The approach overcomes the poor generalizability and instability of conventional energy-matching losses. It achieves a design success rate of 97%, accelerates optimization by over one order of magnitude, and significantly outperforms state-of-the-art methods in key performance metrics.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

PearSAN is a machine learning-assisted optimization algorithm applicable to inverse design problems with large design spaces, where traditional optimizers struggle. The algorithm leverages the latent space of a generative model for rapid sampling and employs a Pearson correlated surrogate model to predict the figure of merit of the true design metric. As a showcase example, PearSAN is applied to thermophotovoltaic (TPV) metasurface design by matching the working bands between a thermal radiator and a photovoltaic cell. PearSAN can work with any pretrained generative model with a discretized latent space, making it easy to integrate with VQ-VAEs and binary autoencoders. Its novel Pearson correlational loss can be used as both a latent regularization method, similar to batch and layer normalization, and as a surrogate training loss. We compare both to previous energy matching losses, which are shown to enforce poor regularization and performance, even with upgraded affine parameters. PearSAN achieves a state-of-the-art maximum design efficiency of 97%, and is at least an order of magnitude faster than previous methods, with an improved maximum figure-of-merit gain.

Problem

• Inverse Design
• Thermo-Photovoltaic Metasurfaces
• Optimization Challenge

Innovation

• PearSON
• Machine Learning Optimization
• Pearson Correlation Loss