The DOI matches its Crossref record; 80 of the 93 references it cites were found in a registry or an index; 11 of the 33 sources its claims cite were checked for support.
On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification
Open accessAbstract
This article aims to investigate how circuit-based hybrid quantum convolutional neural networks (QCNNs) can be successfully employed as image classifiers in the context of remote sensing. The hybrid QCNNs enrich the classical architecture of convolutional neural networks by introducing a quantum layer within a standard neural network. The novel QCNN proposed in this work is applied to the land-use and land-cover classification, chosen as an Earth observation (EO) use case, and tested on the EuroSAT dataset used as the reference benchmark. The results of the multiclass classification prove the effectiveness of the presented approach by demonstrating that the QCNN performances are higher than the classical counterparts. Moreover, investigation of various quantum circuits shows that the ones exploiting quantum entanglement achieve the best classification scores. This study underlines the potentialities of applying quantum computing to an EO case study and provides the theoretical and experimental background for future investigations.
Overview
CoChat Summary
TL;DR
This paper studies circuit-based hybrid quantum convolutional neural networks (QCNNs) for remote sensing land-use/land-cover classification on the EuroSAT benchmark. It reports that QCNNs outperform the classical counterparts, and that circuits with entanglement give the best results.
Key findings
- On EuroSAT multiclass classification, the proposed QCNNs performed better than the classical counterparts; the paper states that the quantum models were “higher than the classical counterparts.”
- Among the tested quantum circuits, those with entanglement achieved the best scores; for the EuroSAT classification, the Real Amplitudes Circuit reached the best overall accuracy of 92%, described as a +10% gain over the second-best approach.
- For the coarse-to-fine land-cover setup, the overall classifier reached 98% accuracy and 98% F1 for the coarse classifier, and 97% accuracy and 97% F1 for the overall coarse-to-fine classifier.
- The paper reports that the fine-grain classifiers reached overall accuracies of 94–99% and overall F1 scores of 94–99%, and that this was “on par” with the best standard approaches while using a much less complex architecture.
Methods
- The study proposes a hybrid QCNN that combines a classical CNN derived from LeNet-5 with a quantum layer implemented using different parameterized quantum circuits.
- The main dataset is EuroSAT, described as 27,000 labeled and georeferenced Sentinel-2 images across 10 classes; the dataset was split 80/20 into training and validation sets.
- The paper compares three quantum circuits and two classical CNN counterparts, training each QCNN for 50 epochs with Adam at learning rate 0.0002 and cross-entropy loss; evaluation uses accuracy, precision, recall, and F1, plus confusion matrices.
- A second experiment adds a coarse-to-fine structured classification scheme with three macroclasses and three fine-grain classifiers, and a final patchwise semantic mapping experiment on Onera Satellite Change Detection Dataset (OSCD) images.
Limitations
- The paper states that current hybrid quantum models are preferred partly because of technology bottlenecks and limitations in the NISQ era.
- It also explicitly notes that the current approach is constrained by the need for a classical component for data embedding given present NISQ device capacity, and says future work should explore more powerful encoding and more quantum processing.
- Evident from the text: the comparison is limited to the circuits and baselines tested here, and the paper does not report statistical significance tests or uncertainty estimates for the reported scores.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
11 Valid · 1 Not valid · 16 Not checked · 35 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“It is worth to highlight that only very few works have addressed the application of quantum machine learning (QML) to remote sensing in the current state of the art.”
§ On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification > I. INTRODUCTION
What the sources say
- Partly supportedcites [22] sourceExperimental — accuracy not yet measured
Our copy never makes the bibliographic scarcity assertion the claim attributes to it: no passage states that only a few works have applied QML to remote sensing. The nearest support is thematic — the Abstract (p. front) speaks of 'a performance improvement over previous quantum efforts in this domain' for satellite image classification, and §1.3 (Quantum machine learning) lists as antecedents essentially only the original QNN test on MNIST [15] and the authors' own earlier DeepSat satellite-image experiment [16]; §2.1 (Caveats and objectives) says 'the state of technology is still nascent'. But that 'nascent' statement is about quantum hardware/QML research in general, not about the number of remote-sensing QML studies, and the paper contains no literature survey or count supporting 'only very few works'. So the framing of an immature, sparsely explored quantum-ML-for-imagery area is present, while the specific claim about the state-of-the-art literature is not. (LLM, conf=0.62)
- Not checked — no full text of the sourcecites [24] source
- Not checked — no full text of the sourcecites [25] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, QC still presents some technological limitations, as reported in [12] with a special concern with noise and limited error correction.”
§ On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification > I. INTRODUCTION
What the sources say
- Supportedcites [12] source
The Abstract states that noise is 'the greatest obstacle' limiting achievable precision and sensitivity, and that the repetition frequency required for quantum error correction 'is unachievable with the existing quantum technologies'; the Introduction (p. 1) adds that current error-correction timescales are comparable to dephasing times in spin and superconducting qubit systems and that realistic error correction is hindered by noisy ancillas and imperfect correction. Section 3.3 and 3.4 quantify this (imperfect correction makes the Heisenberg limit unattainable; benchmarked infidelity p = 0.06), so the two concerns the citing sentence flags — noise and limited error correction as a technological constraint — are squarely the paper's own claims. The only difference in framing is that the paper's setting is quantum metrology rather than 'QC' generally, but it treats quantum error correction as the tool borrowed from quantum computation and its limits as properties of current quantum hardware, so the paraphrase does not attribute anything the source fails to say. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, there is not a shared consensus on how and when QML can be advantageous with respect to its classical counterpart on general classes of problems.”
§ On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification > B. Advantages of QML
What the sources say
- Supportedcites [57] source
The Discussion (page not provided) says that quantifying QML advantage over classical methods requires care and that further research is needed to identify practical use cases and evaluate claims of advantage. This supports the broad claim that when QML is advantageous across general problems remains unsettled, although the paper does not explicitly assess a shared consensus. (LLM, conf=0.86)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results of the multiclass classification prove the effectiveness of the presented approach by demonstrating that the QCNN performances are higher than the classical counterparts.”
- Also stated in: § I. INTRODUCTION · plain
“The results of the multiclass novel QCNN classifier prove the effectiveness of the proposed approach, which is able to achieve better results with standard models of comparable complexity and on-par results with best standard models of the state of the art.”
- Also stated in: § I. INTRODUCTION · plain
“QCNN multiclass classification is tackled with respect to the simple binary classification already discussed in [26], and better results are obtained through the quantum-based networks with respect to their fully classical counterpart.”
§ On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification > Abstract
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § I. INTRODUCTION · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Moreover, investigation of various quantum circuits shows that the ones exploiting quantum entanglement achieve the best classification scores.”
- Also stated in: § I. INTRODUCTION · plain
“A comparative and critical analysis is carried out to analyze the performances of different gate-based circuits for hybrid QCNN, showing the advantages of the architecture with entanglement.”
§ On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification > Abstract
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § I. INTRODUCTION · plain
18 more claims
Create a free account to see all 63 claims and to verify the 3 references still open.
- Probably not a substantial claim. 28
- It may state two separate claims as one. 22
- The quote only partly states this claim. 2
Citations
Cites
Quantum Computation and Quantum Information: Bibliography
Nielsen, M. A., & Chuang, I. (2010) · doi:10.1017/cbo9780511976667.023 · Cited by 12,065
Quantum Computation and Quantum Information: 10th Anniversary Edition
Nielsen, M. A., & Chuang, I. L. (2012) · doi:10.1017/cbo9780511976667 · Cited by 8,436
Quantum supremacy using a programmable superconducting processor
Arute, F., Arya, K., Babbush, R., Bacon, D., Bardin, J. C., Barends, R., Biswas, R., Boixo, S., Brandao, F. G. S. L., Buell, D. A., et al. (2019) · Nature · doi:10.1038/s41586-019-1666-5 · Cited by 7,720
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
A variational eigenvalue solver on a photonic quantum processor
Peruzzo, A., McClean, J., Shadbolt, P., Yung, M.-H., Zhou, X.-Q., Love, P. J., Aspuru-Guzik, A., & O’Brien, J. L. (2014) · Nature Communications · doi:10.1038/ncomms5213 · Cited by 4,552 · cited 2×
“By iterating through these classical variations and quantum calculations, a hybrid minimization process is established [14].”
BackgroundMethodDOTA: A Large-Scale Dataset for Object Detection in Aerial Images
Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., & Zhang, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00418 · Cited by 3,414
Quantum computational advantage using photons
Zhong, H.-S., Wang, H., Deng, Y.-H., Chen, M.-C., Peng, L.-C., Luo, Y.-H., Qin, J., Wu, D., Ding, X., Hu, Y., et al. (2020) · Science · doi:10.1126/science.abe8770 · Cited by 2,405
Noisy intermediate-scale quantum algorithms
Bharti, K., Cervera-Lierta, A., Kyaw, T. H., Haug, T., Alperin-Lea, S., Anand, A., Degroote, M., Heimonen, H., Kottmann, J. S., Menke, T., et al. (2022) · Reviews of Modern Physics · doi:10.1103/revmodphys.94.015004 · Cited by 2,231 · cited 2×
“Specific algorithms, namely the Noisy Intermediate-Scale Quantum Computing (NISQ) algorithms, have been designed to tackle these issues [13].”
BackgroundMethodQuantum Support Vector Machine for Big Data Classification
Rebentrost, P., Mohseni, M., & Lloyd, S. (2014) · Physical Review Letters · doi:10.1103/physrevlett.113.130503 · Cited by 1,951
EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2918242 · Cited by 1,951
Research works printed but not linked: 1
- 10.1017/cbo9780511976667 · DOI · Paper page
Cited by
Remote Sensing and Geospatial Analysis in the Big Data Era: A Survey
Dritsas, E., & Τρίγκα, Μ. (2025) · Remote Sensing · doi:10.3390/rs17030550 · Cited by 203
Hybrid Quantum-Classical Convolutional Neural Network Model for Image Classification
Fan, F., Shi, Y., Guggemos, T., & Zhu, X. X. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3312170 · Cited by 190
Quantum Computing and Simulations for Energy Applications: Review and Perspective
Paudel, H. P., Syamlal, M., Crawford, S. E., Lee, Y., Shugayev, R., Lu, P., Ohodnicki, P. R., Mollot, D., & Duan, Y. (2022) · ACS Engineering Au · doi:10.1021/acsengineeringau.1c00033 · Cited by 189
Artificial Intelligence for Trusted Autonomous Satellite Operations
Thangavel, K., Sabatini, R., Gardi, A., Ranasinghe, K. C., Hilton, S., Servidia, P. A., & Spiller, D. (2023) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2023.100960 · Cited by 144
Self-citationQuantum Machine Learning: Scope for real-world problems
Jadhav, A., Rasool, A., & Gyanchandani, M. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.01.235 · Cited by 84
Metadata
- Authors
- Sebastianelli, A., Zaidenberg, D. A., Spiller, D., Le Saux, B., & Ullo, S.
- Affiliations
- University of Sannio (IT)
- Massachusetts Institute of Technology (US)
- European Space Agency (FR)
- Venue
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Published
- 2022
- Volume
- 15
- Pages
- 565-580
- ISSN
- 1939-1404 (ISSN-L)
- 2151-1535
- OpenAlex
- W3201342863
- Cited by
- 162
- References
- 93
- Citations by year
- 2026: 35 · 2025: 42 · 2024: 43 · 2023: 31 · 2022: 11
- FWCI
- 7.51
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Massachusetts Institute of Technology
- European Space Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- hybrid quantum neural networks, quantum convolutional neural networks, remote sensing image classification, land use and land cover classification, EuroSAT dataset, quantum entanglement, quantum circuits, Earth observation, quantum machine learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification. https://app.cochat.ai/papers/10.1109/jstars.2021.3134785
- The paper
- Sebastianelli, A., Zaidenberg, D. A., Spiller, D., Le Saux, B., & Ullo, S. (2022). On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/jstars.2021.3134785
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.