Progressive multi-fidelity learning for physical system predictions

2025-10-15

AI Summary

High-fidelity data for physical system prediction are scarce, while synergistic utilization of heterogeneous multi-source low- and high-fidelity data remains challenging. Method: We propose a progressive multi-fidelity learning framework featuring a dual-path connectivity mechanism and hierarchical encoding architecture, enabling dynamic, adaptive fusion from low- to high-fidelity data. Customized encoders process multimodal inputs, and concatenated plus additive connections facilitate hierarchical cross-fidelity information propagation, preventing performance degradation. Contribution/Results: Evaluated on numerical benchmarks and real-world physical systems, our method significantly improves prediction accuracy and generalization—particularly under temporal evolution and parametric variation—while maintaining robustness. It establishes a scalable, interpretable paradigm for multi-fidelity data-driven scientific modeling.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Highly accurate datasets from numerical or physical experiments are often expensive and time-consuming to acquire, posing a significant challenge for applications that require precise evaluations, potentially across multiple scenarios and in real-time. Even building sufficiently accurate surrogate models can be extremely challenging with limited high-fidelity data. Conversely, less expensive, low-fidelity data can be computed more easily and encompass a broader range of scenarios. By leveraging multi-fidelity information, prediction capabilities of surrogates can be improved. However, in practical situations, data may be different in types, come from sources of different modalities, and not be concurrently available, further complicating the modeling process. To address these challenges, we introduce a progressive multi-fidelity surrogate model. This model can sequentially incorporate diverse data types using tailored encoders. Multi-fidelity regression from the encoded inputs to the target quantities of interest is then performed using neural networks. Input information progressively flows from lower to higher fidelity levels through two sets of connections: concatenations among all the encoded inputs, and additive connections among the final outputs. This dual connection system enables the model to exploit correlations among different datasets while ensuring that each level makes an additive correction to the previous level without altering it. This approach prevents performance degradation as new input data are integrated into the model and automatically adapts predictions based on the available inputs. We demonstrate the effectiveness of the approach on numerical benchmarks and a real-world case study, showing that it reliably integrates multi-modal data and provides accurate predictions, maintaining performance when generalizing across time and parameter variations.

Problem

• Overcoming expensive high-fidelity data acquisition for accurate predictions
• Integrating diverse multi-fidelity data types and modalities sequentially
• Preventing performance degradation when incorporating new input data

Innovation

• Progressive multi-fidelity surrogate model with tailored encoders
• Dual connections enable additive corrections between fidelity levels
• Sequentially incorporates diverse multi-modal data types