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

2026-03-24

AI Summary

This work addresses the challenge of uncovering the dynamical evolution of plasma surrounding a black hole from a single, blurred image captured by the Event Horizon Telescope (EHT). The authors propose BHCast, a novel framework that, for the first time, jointly performs super-resolution reconstruction and long-term dynamic prediction from a single low-resolution frame. BHCast employs an autoregressive neural network with multi-scale pyramid losses for video generation and integrates gradient-boosted trees with spatiotemporal features—such as pattern speed and pitch angle—to infer key black hole physical parameters. By decoupling the prediction and inference modules, the method substantially enhances model interpretability and uncertainty quantification. Validated on both simulated and real EHT observations of Sgr A* and M87*, BHCast accurately recovers the black hole spin and viewing inclination, demonstrating its effectiveness and generalization capability.

Abstract

The Event Horizon Telescope (EHT) delivered the first image of a black hole by capturing the light from its surrounding accretion flow, revealing structure but not dynamics. Simulations of black hole accretion dynamics are essential for interpreting EHT images but costly to generate and impractical for inference. Motivated by this bottleneck, BHCast presents a framework for forecasting black hole plasma dynamics from a single, blurry snapshot, such as those captured by the EHT. At its core, BHCast is a neural model that transforms a static image into forecasted future frames, revealing the underlying dynamics hidden within one snapshot. With a multi-scale pyramid loss, we demonstrate how autoregressive forecasting can simultaneously super-resolve and evolve a blurry frame into a coherent, high-resolution movie that remains stable over long time horizons. From forecasted dynamics, we can then extract interpretable spatio-temporal features, such as pattern speed (rotation rate) and pitch angle. Finally, BHCast uses gradient-boosting trees to recover black hole properties from these plasma features, including the spin and viewing inclination angle. The separation between forecasting and inference provides modular flexibility, interpretability, and robust uncertainty quantification. We demonstrate the effectiveness of BHCast on simulations of two distinct black hole accretion systems, Sagittarius A* and M87*, by testing on simulated frames blurred to EHT resolution and real EHT images of M87*. Ultimately, our methodology establishes a scalable paradigm for solving inverse problems, demonstrating the potential of learned dynamics to unlock insights from resolution-limited scientific data.

Problem

• black hole plasma dynamics
• Event Horizon Telescope
• inverse problem
• accretion flow
• long-term forecasting

Innovation

• neural forecasting
• black hole plasma dynamics
• super-resolution
• inverse problem
• interpretable features