VIS Full Papers

FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles

Ziwei Li (The Ohio State University), Yuhan Duan (The Ohio State University), Tianyu Xiong (The Ohio State University), Yi-Tang Chen (The Ohio State University), Wei-Lun Chao (The Ohio State University), Han-Wei Shen (The Ohio State University)

Surrogate modelensemble visualizationimplicit neural representationmixture-of-experts

Jump to Discussion

Presentation

Session
Let me through, I'm a scientist!
Time
Tuesday, Nov 10, 15:24 – 15:36 (US/Eastern) · session 15:00 – 16:30
Room
Hall America north
Presenting from
Boston

Links

Top of the first page of the paper “FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles”.

Abstract

Surrogate models are essential for efficient exploration of large-scale ensemble simulations. Implicit neural representations (INRs) provide a compact and continuous framework for modeling spatially structured data, but they often struggle with learning complex localized structures within scientific fields. Recent INR-based surrogates address this by augmenting INRs with explicit feature structures, but at the cost of flexibility and substantial memory overhead. In this paper, we present Feature-Adaptive INR (FA-INR), an adaptive INR-based surrogate model for high-fidelity and interpretable exploration of ensemble simulations. Instead of relying on structured feature representations, FA-INR leverages cross-attention over a learnable key-value memory bank to allocate model capacity adaptively based on the data characteristics. To further improve scalability, we introduce a coordinate-guided mixture of experts (MoE) framework that enhances both efficiency and specialization of feature representations. More importantly, the learned experts produce an interpretable partition over the simulation domain, enabling scientists to identify complex structures and perform localized parameter-space exploration. Beyond quantitative and qualitative evaluations, we also demonstrate that our learned expert specialization can reveal meaningful scientific insights and support localized sensitivity analysis.

For Practitioners

simulation scientists