HXI-DLA2: A Physics-Constrained Deep Learning Algorithm for the ASO-S Hard X-ray Imager
Abstract
Solar flare hard X-ray imaging is a key diagnostic of flare energy release and electron acceleration. The Hard X-ray Imager (HXI) aboard ASO-S compresses the two-dimensional source distribution into counts measured by 91 sub-collimators, making image reconstruction an inherently underdetermined inverse problem. Conventional algorithms such as CLEAN rely on point-source priors and manual tuning, whereas recent deep-learning methods offer no guarantee that their reconstructions obey the instrument's modulation-sampling forward equation. In this work we show that the counts decompose into two nearly decoupled quantities---the counts average energy, which tracks the total source flux, and the normalized counts distribution, which encodes the source spatial structure---and we exploit this property to construct a physics-constrained network, the Hard X-ray Imager Deep Learning Algorithm 2 (HXI-DLA2). Non-negativity and exact counts-average-energy closure are enforced at the network output, while a distribution-consistency loss aligns the re-projected counts with the measurement, so that the reconstruction satisfies the forward equation by construction. Tests on simulated Gaussian sources, observed soft X-ray morphologies, and a real HXI flare event show two main improvements over existing methods: the limiting resolvable dynamic range of double sources is pushed well beyond that of conventional imaging algorithms and our previous method; and complex morphologies on which prior reconstructions degrade, such as ring-like and diffuse structures, are reliably reconstructed, with the real-event result consistent with contemporaneous SDO/AIA imaging. Embedding the instrumental forward equation as a hard constraint while learning source priors from data offers a general inversion framework for modulation imaging.
Related
- A deep learning algorithm for black hole spin estimation using hot spot secondary images
- Metaheuristic physics-informed extreme-learning machine for initial orbit determination of near-Earth asteroids from too-short arcs
- The MICADO first light imager for the ELT: the PSF Reconstruction Software
- Lightweight Soft X-ray Imager (LSXI) with glass-based coded mask
- A deep learning algorithm for black hole spin estimation using hot-spot secondary images
BibTeX
@misc{sizhong2026hxidla2,
title = {{HXI-DLA2: A Physics-Constrained Deep Learning Algorithm for the ASO-S Hard X-ray Imager}},
author = {Zou SiZhong and Liu Hui and Su Yang and Hong JunChao and Bin Wang and Chen Wei and KaiFan Ji and ZhenYu Jin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.09646},
eprint = {2608.09646},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.09646},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - HXI-DLA2: A Physics-Constrained Deep Learning Algorithm for the ASO-S Hard X-ray Imager
AU - Zou SiZhong
AU - Liu Hui
AU - Su Yang
AU - Hong JunChao
AU - Bin Wang
AU - Chen Wei
AU - KaiFan Ji
AU - ZhenYu Jin
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2608.09646
UR - https://arxiv.org/abs/2608.09646
AB - Solar flare hard X-ray imaging is a key diagnostic of flare energy release and electron acceleration. The Hard X-ray Imager (HXI) aboard ASO-S compresses the two-dimensional source distribution into counts measured by 91 sub-collimators, making image reconstruction an inherently underdetermined inverse problem. Conventional algorithms such as CLEAN rely on point-source priors and manual tuning, whereas recent deep-learning methods offer no guarantee that their reconstructions obey the instrument's modulation-sampling forward equation. In this work we show that the counts decompose into two nearly decoupled quantities---the counts average energy, which tracks the total source flux, and the normalized counts distribution, which encodes the source spatial structure---and we exploit this property to construct a physics-constrained network, the Hard X-ray Imager Deep Learning Algorithm 2 (HXI-DLA2). Non-negativity and exact counts-average-energy closure are enforced at the network output, while a distribution-consistency loss aligns the re-projected counts with the measurement, so that the reconstruction satisfies the forward equation by construction. Tests on simulated Gaussian sources, observed soft X-ray morphologies, and a real HXI flare event show two main improvements over existing methods: the limiting resolvable dynamic range of double sources is pushed well beyond that of conventional imaging algorithms and our previous method; and complex morphologies on which prior reconstructions degrade, such as ring-like and diffuse structures, are reliably reconstructed, with the real-event result consistent with contemporaneous SDO/AIA imaging. Embedding the instrumental forward equation as a hard constraint while learning source priors from data offers a general inversion framework for modulation imaging.
ER -