AdaField: Generalizable Surface Pressure Modeling with Physics-Informed Pre-training and Flow-Conditioned Adaptation

2026-01-12

arXiv.org

AI Summary

This work addresses the challenge of surface pressure field modeling in data-scarce scenarios such as high-speed trains, where limited training data hinders the application of deep learning in aerodynamic analysis. To overcome this, the authors propose AdaField, a framework that leverages physics-informed pretraining on large-scale public datasets and introduces a Semantic Aggregation Point Transformer (SAPT) backbone, a Flow-field Condition Adapter (FCA), and Physics-Informed Data Augmentation (PIDA) to enable few-shot cross-domain generalization and efficient adaptation. Evaluated on DrivAerNet++, AdaField achieves state-of-the-art performance and successfully transfers to train and aircraft configurations, yielding high-fidelity pressure field predictions with only minimal fine-tuning.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Mobility, Driving & Flight
• Multiagent Systems: Adversarial Agents

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

The surface pressure field of transportation systems, including cars, trains, and aircraft, is critical for aerodynamic analysis and design. In recent years, deep neural networks have emerged as promising and efficient methods for modeling surface pressure field, being alternatives to computationally expensive CFD simulations. Currently, large-scale public datasets are available for domains such as automotive aerodynamics. However, in many specialized areas, such as high-speed trains, data scarcity remains a fundamental challenge in aerodynamic modeling, severely limiting the effectiveness of standard neural network approaches. To address this limitation, we propose the Adaptive Field Learning Framework (AdaField), which pre-trains the model on public large-scale datasets to improve generalization in sub-domains with limited data. AdaField comprises two key components. First, we design the Semantic Aggregation Point Transformer (SAPT) as a high-performance backbone that efficiently handles large-scale point clouds for surface pressure prediction. Second, regarding the substantial differences in flow conditions and geometric scales across different aerodynamic subdomains, we propose Flow-Conditioned Adapter (FCA) and Physics-Informed Data Augmentation (PIDA). FCA enables the model to flexibly adapt to different flow conditions with a small set of trainable parameters, while PIDA expands the training data distribution to better cover variations in object scale and velocity. Our experiments show that AdaField achieves SOTA performance on the DrivAerNet++ dataset and can be effectively transferred to train and aircraft scenarios with minimal fine-tuning. These results highlight AdaField's potential as a generalizable and transferable solution for surface pressure field modeling, supporting efficient aerodynamic design across a wide range of transportation systems.

Problem

• surface pressure modeling
• data scarcity
• aerodynamic design
• generalization
• transportation systems

Innovation

• Physics-Informed Pre-training
• Flow-Conditioned Adaptation
• Point Cloud Modeling
• Data-Efficient Transfer Learning
• Surface Pressure Prediction