Learning Transient Convective Heat Transfer with Geometry Aware World Models

2026-01-29

AI Summary

Traditional transient conjugate heat transfer simulations are computationally expensive and ill-suited for real-time applications. To address this challenge, this work proposes a geometry-aware world model based on an enhanced LongVideoGAN architecture. The model incorporates a dual-conditioning mechanism that fuses global physical parameters with local geometric masks and extends beyond conventional RGB constraints by supporting arbitrary channel dimensions to accommodate multivariate physical field data. This approach enables controllable generation of complex transient thermal flow fields, accurately reproducing their spatiotemporal dynamics within the training data while demonstrating strong generalization to unseen geometric configurations. The results validate the model’s potential for efficient and controllable physics-based simulation.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Partial differential equation (PDE) simulations are fundamental to engineering and physics but are often computationally prohibitive for real-time applications. While generative AI offers a promising avenue for surrogate modeling, standard video generation architectures lack the specific control and data compatibility required for physical simulations. This paper introduces a geometry aware world model architecture, derived from a video generation architecture (LongVideoGAN), designed to learn transient physics. We introduce two key architecture elements: (1) a twofold conditioning mechanism incorporating global physical parameters and local geometric masks, and (2) an architectural adaptation to support arbitrary channel dimensions, moving beyond standard RGB constraints. We evaluate this approach on a 2D transient computational fluid dynamics (CFD) problem involving convective heat transfer from buoyancy-driven flow coupled to a heat flow in a solid structure. We demonstrate that the conditioned model successfully reproduces complex temporal dynamics and spatial correlations of the training data. Furthermore, we assess the model's generalization capabilities on unseen geometric configurations, highlighting both its potential for controlled simulation synthesis and current limitations in spatial precision for out-of-distribution samples.

Problem

• transient convective heat transfer
• computational fluid dynamics
• surrogate modeling
• geometry-aware simulation
• real-time PDE simulation

Innovation

• geometry-aware world model
• transient convective heat transfer
• conditional generative modeling
• arbitrary channel dimension
• surrogate CFD simulation