AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data

Shaowu Pan, Steven L. Brunton, J. Nathan Kutz

JMLR 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Data assimilation from sparse observations · 52 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use NIF (ShapeNet/ParameterNet) instead of a standard MLP, Swish activationparametric surrogate · 1D parametric K-STest RMSE: 1.10 -> 0.64Improved
use NIF instead of MLP with tanh activationparametric surrogate · 1D parametric K-STest RMSE: 1.17 -> 0.99Improved
replace tanh with Swish activation in NIF (ablation)NIF · 1D parametric K-STest RMSE: 0.99 -> 0.64Improved
replace tanh with Swish activation in MLP (ablation)MLP · 1D parametric K-STest RMSE: 1.17 -> 1.10Improved
use NIF instead of MLP when training data size varies (15, 24, 29 parameter samples) (ablation)NIF-Swish · 1D parametric K-STest RMSE: approximately half of the training dataImproved
use NIF instead of MLP at equal parameter count (7000 to 34000) (ablation)NIF-Swish · 1D parametric K-STest RMSE: lowers the testing error by halfImproved
use NIF instead of CAE on adaptive mesh dataNIF autoencoder · 2D Rayleigh-TaylorRMSE: CAE 10, 5, 1.7 times more error than NIFImproved
use NIF instead of SVD for rank 1 reductionNIF autoencoder · 2D Rayleigh-TaylorRMSEImproved
use NIF instead of SIREN at small widthNIF · 2D turbulence slice x-velocitynormalized error: 0.121 -> 0.071 (width 36); 0.040 -> 0.022 (width 75)Improved
use NIF instead of SIREN at width 150NIF · 2D turbulence slice x-velocitynormalized error: 0.0116 vs 0.0131No clear effect
use NIF instead of Fourier feature networksNIF · 2D turbulence slice x-velocitynormalized error: 0.263 -> 0.071 (width 36)Improved
separate spatial from time input (NIF vs SIREN taking t,x,y,z)NIF · 3D HIT spatial querynetwork size / cost at same errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy