FLINT: Learning-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization

TL;DR

FLINT is a deep learning method that estimates flow fields and interpolates temporal data in scientific ensembles, even when original flow information is missing, improving visualization and analysis of complex scientific data.

Contribution

FLINT introduces a flexible, learning-based approach for flow estimation and temporal interpolation in scientific ensemble data, handling cases with partial or no available flow fields.

Findings

Effective flow estimation in various scientific datasets

High-quality temporal interpolation achieved

First approach to estimate flow without original flow data

Abstract

We present FLINT (learning-based FLow estimation and temporal INTerpolation), a novel deep learning-based approach to estimate flow fields for 2D+time and 3D+time scientific ensemble data. FLINT can flexibly handle different types of scenarios with (1) a flow field being partially available for some members (e.g., omitted due to space constraints) or (2) no flow field being available at all (e.g., because it could not be acquired during an experiment). The design of our architecture allows to flexibly cater to both cases simply by adapting our modular loss functions, effectively treating the different scenarios as flow-supervised and flow-unsupervised problems, respectively (with respect to the presence or absence of ground-truth flow). To the best of our knowledge, FLINT is the first approach to perform flow estimation from scientific ensembles, generating a corresponding flow field for each discrete timestep, even in the absence of original flow information. Additionally, FLINT produces high-quality temporal interpolants between scalar fields. FLINT employs several neural blocks, each featuring several convolutional and deconvolutional layers. We demonstrate performance and accuracy for different usage scenarios with scientific ensembles from both simulations and experiments.