Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations

About

Effective surrogate models are critical for accelerating scientific simulations. Implicit neural representations (INRs) offer a compact and continuous framework for modeling spatially structured data, but they often struggle with complex scientific fields exhibiting localized, high-frequency variations. Recent approaches address this by introducing additional features along rigid geometric structures (e.g., grids), but at the cost of flexibility and increased model size. In this paper, we propose a simple yet effective alternative: Feature-Adaptive INR (FA-INR). FA-INR leverages cross-attention to an augmented memory bank to learn flexible feature representations, enabling adaptive allocation of model capacity based on data characteristics, rather than rigid structural assumptions. To further improve scalability, we introduce a coordinate-guided mixture of experts (MoE) that enhances the specialization and efficiency of feature representations. Experiments on three large-scale ensemble simulation datasets show that FA-INR achieves state-of-the-art fidelity while significantly reducing model size, establishing a new trade-off frontier between accuracy and compactness for INR-based surrogates.

Ziwei Li, Yuhan Duan, Tianyu Xiong, Yi-Tang Chen, Wei-Lun Chao, Han-Wei Shen• 2025

Related benchmarks

TaskDatasetResultRank
Conditional GeneralizationMPAS-Ocean (test)
Rel L2 Error0.0056
4
Conditional GeneralizationNyx (test)
Relative L2 Error0.0395
4
Conditional GeneralizationCloverleaf3D (test)
Relative L2 Error0.111
4
Conditional GeneralizationNyx low-resolution (x2 reduced) (Unseen Fields)
Rel L2 Error0.0278
4
Conditional GeneralizationNyx Trained Fields low-resolution (x2 reduced)
Relative L2 Error0.0276
4
Conditional GeneralizationCloverleaf3D low-resolution (x2 reduced) (Unseen Fields)
Rel L2 Error0.0992
4
Conditional GeneralizationCloverleaf3D low-resolution (x2 reduced) (train)
Relative L2 Error0.0624
4
Super-ResolutionNyx Unseen Fields (test)
Relative L2 Loss0.0455
4
Super-ResolutionNyx Trained Fields (train)
Rel L20.0729
4
Super-ResolutionCloverleaf3D Unseen Fields (test)
Rel L2 Error0.107
4
Showing 10 of 11 rows

Other info

Follow for update