AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting

Renbo Tu, Ali SaraerToosi, Nicholas S. Conroy, Gennady Pekhimenko, Aviad Levis

CVPR 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Data assimilation from sparse observations · 0 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
Add multi-scale Laplacian pyramid loss with mean-flux term instead of L2 only (ablation)BHCast U-Net forecaster · Sgr A* forecasting LPIPSLPIPS stability over rolloutImproved
Add mean-flux regularization to the multi-scale pyramid loss (ablation)BHCast U-Net forecaster · Sgr A* forecasting LPIPSLPIPS stability over rollout: stable only for first 20 forecasts without mean fluxImproved
Forecast dynamics then extract plasma features instead of direct ResNet regressionBHCast · Sgr A* blurred inputPattern speed MAE: 0.64 -> 0.46Improved
Forecast then extract features instead of direct ResNet regressionBHCast · Sgr A* blurred inputAsymmetry MAE: 0.23 -> 0.30Hurt
Use forecast-based features with XGBoost instead of direct ResNet classificationBHCast · Sgr A* inclination, 20 µasaccuracy: 47.19% -> 56.41%Improved
Increase input blur to 30 µasResNet baseline · Sgr A* inclinationaccuracy: 47.19% -> 25.47%Hurt
Increase input blur to 30 µasBHCast · Sgr A* inclinationaccuracy: 56.41% -> 53.44%No clear effect
Increase input blur to 25 µasBHCast · Sgr A* spinaccuracy: 69.22% -> 71.09%No clear effect
Autoregressive forecasting with U-Net replaces decoupled EDSR + ConvLSTM baselineBHCast · Sgr A* 100-step forecastLPIPSImproved

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