SAR and InSAR Change Detection with Quantum Generative Models

Abstract

Change detection in synthetic aperture radar (SAR) and interferometric synthetic aperture radar (InSAR) underpins disaster response, infrastructure monitoring and land-use enforcement. Detection is limited by the background estimator, which conventionally forms a conditional expectation directly from observed pixel statistics and degrades where those statistics are sparse, including the regime produced by the heavy-tailed marginals of sub-meter-resolution radars. In this work, we integrate state-of-the-art satellite imagery with quantum machine learning on IonQ trapped-ion-based quantum processors. By replacing the empirical conditional with a quantum circuit Born machine (QCBM)-sampled generative model in Copula space, we substantially improve change detection on sparse real-world images. On Capella Space satellite image acquisitions, the generative estimator matches conventional methods when the observed statistics are adequate, and substantially outperforms them when they are not. Executing the trained model on IonQ trapped-ion based hardware reproduces the results of the ideal and noisy simulations and demonstrates up to par, or even better, performance with the classical state-of-the-art methods. For a SAR dataset of an airport, QPU circuit evaluations for both training and inference achieved a maximized filtered F1 score of 0.32, compared with 0.16 and 0.24 for the two classical baselines. For an InSAR dataset of a volcanic lava flow, all three methods reached a maximum filtered F1 of approximately 0.66. These experiments demonstrate the feasibility of executing a QCBM-based background estimator on trapped-ion hardware. We further demonstrate that the QCBM method successfully extends to interferometric coherence data, achieving performance comparable to classical approaches.

Generative Quantum Machine Learning Methods for Cancer Detection using Augmented Datasets
Sophia Knutson, Nandika Goyal, Gennaro De Luca +3
arXiv10 Oct 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
Quantum Feature Amplification Network (QFAN) as An Autoregressive Quantum Generative Model
Jamal Slim, Saverio Monaco, Florian Rehm +2
arXiv8 Oct 2026PreprintCC BY 4.0Full textComputational physics Quantum physics & quantum informationarXiv
Warning of infrastructure deformation anomaly through probabilistic analysis of InSAR observations
Hao Kuai, Na Hao, Pantelis Karamitopoulos +2
arXiv9 Oct 2026PreprintCC BY 4.0Full textStatistics Computational physicsarXiv
Generative learning of time series with holographic quantum circuit sampling
Bingzhi Zhang, Matthew W. Lee, Tom Finke +1
arXiv10 Oct 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
On Certifying Source Sampling Hardness in Quantum Generative Modeling
Chen-Yu Liu, Leonardo Placidi, Enrico Rinaldi
arXiv23 Sep 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv

Cite

BibTeX RIS

BibTeX

@misc{sekwao2026insar,
  title = {{SAR and InSAR Change Detection with Quantum Generative Models}},
  author = {Samwel K. Sekwao and Shaunak De and Alexis Hocken and Scott Staniewicz and Evgeny Epifanovsky and Craig Stringham and Gordon Farquharson and Martin Roetteler and Panagiotis Kl. Barkoutsos and Jason Iaconis},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.05313},
  eprint = {2609.05313},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05313},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - SAR and InSAR Change Detection with Quantum Generative Models
AU  - Samwel K. Sekwao
AU  - Shaunak De
AU  - Alexis Hocken
AU  - Scott Staniewicz
AU  - Evgeny Epifanovsky
AU  - Craig Stringham
AU  - Gordon Farquharson
AU  - Martin Roetteler
AU  - Panagiotis Kl. Barkoutsos
AU  - Jason Iaconis
PY  - 2026
DA  - 2026/09/04
PB  - arXiv
DO  - 10.48550/arxiv.2609.05313
UR  - https://arxiv.org/abs/2609.05313
AB  - Change detection in synthetic aperture radar (SAR) and interferometric synthetic aperture radar (InSAR) underpins disaster response, infrastructure monitoring and land-use enforcement. Detection is limited by the background estimator, which conventionally forms a conditional expectation directly from observed pixel statistics and degrades where those statistics are sparse, including the regime produced by the heavy-tailed marginals of sub-meter-resolution radars. In this work, we integrate state-of-the-art satellite imagery with quantum machine learning on IonQ trapped-ion-based quantum processors. By replacing the empirical conditional with a quantum circuit Born machine (QCBM)-sampled generative model in Copula space, we substantially improve change detection on sparse real-world images. On Capella Space satellite image acquisitions, the generative estimator matches conventional methods when the observed statistics are adequate, and substantially outperforms them when they are not. Executing the trained model on IonQ trapped-ion based hardware reproduces the results of the ideal and noisy simulations and demonstrates up to par, or even better, performance with the classical state-of-the-art methods. For a SAR dataset of an airport, QPU circuit evaluations for both training and inference achieved a maximized filtered F1 score of 0.32, compared with 0.16 and 0.24 for the two classical baselines. For an InSAR dataset of a volcanic lava flow, all three methods reached a maximum filtered F1 of approximately 0.66. These experiments demonstrate the feasibility of executing a QCBM-based background estimator on trapped-ion hardware. We further demonstrate that the QCBM method successfully extends to interferometric coherence data, achieving performance comparable to classical approaches.
ER  -

Abstract

Related

Cite