Pith. sign in

REVIEW 3 major objections 1 minor 38 references

A Residual U-Net regresses InSAR coherence directly from detected SAR backscatter images without coregistration.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-27 21:02 UTC pith:2ZWQTA73

load-bearing objection The U-Net regresses coherence from detected SAR magnitudes after training on aligned SLC pairs, but the transfer to misaligned inputs is the part that needs checking. the 3 major comments →

arxiv 2606.07374 v1 pith:2ZWQTA73 submitted 2026-06-05 eess.SP cs.CV

Beyond Backscatter: InSAR coherence from detected SAR images

Francescopaolo Sica , Andrea Pulella , Michael Schmitt This is my paper
classification eess.SP cs.CV
keywords InSAR coherencedeep learningResidual U-NetSentinel-1detected SAR imagesbackscattercoherence regressionSAR interferometry
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a deep learning approach that estimates coherence maps using only detected SAR images instead of requiring precisely coregistered single-look complex pairs. A Residual U-Net is trained on coherence derived from Sentinel-1 12-day SLC data to learn the relationship between backscatter magnitudes and coherence values. This yields higher accuracy than prior intensity-based methods and generalizes to new geographic sites and to temporal baselines absent from training. The framework also runs on open analysis-ready detected products, such as ground-range detected data, supporting broader operational use.

Core claim

The authors show that a Residual U-Net trained on coherence maps from coregistered Sentinel-1 SLC pairs can predict coherence from backscatter magnitudes alone in detected SAR images. The model delivers high-resolution estimates with improved accuracy over existing intensity-based techniques. It maintains performance across diverse locations and on temporal baselines different from the 12-day training pairs, and functions on globally distributed analysis-ready detected data.

What carries the argument

Residual U-Net that maps pairs of backscatter magnitude images to coherence values.

Load-bearing premise

The statistical mapping from backscatter magnitudes to coherence learned on coregistered 12-day Sentinel-1 SLC pairs transfers to detected SAR images that lack coregistration and may have different radiometric or geometric properties.

What would settle it

The trained model producing lower accuracy than conventional intensity-based coherence estimators when tested on a new collection of detected SAR images from an unseen sensor or geographic region.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Coherence estimation becomes possible on widely distributed analysis-ready detected products without coregistration processing.
  • Accuracy exceeds that of existing backscatter-only methods for high-resolution outputs.
  • The same model applies to temporal baselines not present in the training set.
  • Large-scale mapping and change-monitoring tasks can use standard open data sources such as Google Earth Engine products.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Operational pipelines could shift away from SLC data requirements toward simpler detected-image workflows.
  • The approach might combine with multi-temporal stacks to refine coherence estimates in time-series applications.
  • Transfer tests on data from non-Sentinel-1 sensors would clarify how far the learned magnitude-to-coherence relation extends.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 1 minor

Summary. The manuscript proposes a Residual U-Net for regressing InSAR coherence directly from pairs of detected SAR backscatter magnitude images. The network is trained on coherence targets derived from precisely coregistered 12-day Sentinel-1 SLC pairs and is evaluated on multiple datasets spanning coregistered SLC products and analysis-ready data (including GRD) with varying radiometric properties, geometries, and locations. The central claims are that the approach achieves high-resolution coherence estimation without requiring accurate coregistration at inference time, outperforms existing intensity-based methods, and generalizes across unseen geographical locations and temporal baselines.

Significance. If the generalization to misaligned detected-image inputs holds, the method would enable coherence-based applications at scale using globally distributed analysis-ready SAR products (e.g., via Google Earth Engine) without SLC processing or coregistration steps, which would be a practical advance for change monitoring and mapping tasks.

major comments (3)
  1. [Methods / Training procedure] The training inputs are magnitude pairs taken from precisely coregistered SLC data, yet the central claim requires the same weights to produce usable coherence on detected images that have not been coregistered. No description is given of deliberate misalignment augmentation during training or of controlled experiments that measure performance degradation as a function of geometric offset; this assumption is load-bearing for the claim of operating “without the need for accurate coregistration.”
  2. [Experiments / Evaluation datasets] Evaluation on “open access analysis-ready data” is reported to demonstrate generalization, but the manuscript does not state whether these test pairs were coregistered, what the typical residual misalignment is, or provide separate metrics for aligned versus unaligned inputs. Without such quantification, the transfer from the training distribution to the claimed inference distribution cannot be verified.
  3. [Abstract / Results] The abstract asserts “improved accuracy compared to existing intensity-based approaches,” yet the provided summary contains no numerical error metrics, baseline tables, or train/validation split details. If these are absent from the full results section as well, the quantitative support for the accuracy claim is insufficient.
minor comments (1)
  1. [Abstract] The abstract states that the network “generalizes well … across different temporal baselines that were never seen at training time,” but does not name the specific temporal baselines used in training versus testing.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed review. We address each major comment point by point below, indicating where revisions will be made to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Methods / Training procedure] The training inputs are magnitude pairs taken from precisely coregistered SLC data, yet the central claim requires the same weights to produce usable coherence on detected images that have not been coregistered. No description is given of deliberate misalignment augmentation during training or of controlled experiments that measure performance degradation as a function of geometric offset; this assumption is load-bearing for the claim of operating “without the need for accurate coregistration.”

    Authors: We agree that the manuscript does not describe misalignment augmentation or controlled offset experiments. Training used coregistered SLC pairs to obtain reliable coherence targets, with the model intended to generalize to detected products at inference. To support the claim, the revised manuscript will include a new subsection with controlled misalignment experiments reporting accuracy degradation versus offset. revision: yes

  2. Referee: [Experiments / Evaluation datasets] Evaluation on “open access analysis-ready data” is reported to demonstrate generalization, but the manuscript does not state whether these test pairs were coregistered, what the typical residual misalignment is, or provide separate metrics for aligned versus unaligned inputs. Without such quantification, the transfer from the training distribution to the claimed inference distribution cannot be verified.

    Authors: The analysis-ready datasets (e.g., GRD) were used as distributed without additional coregistration. We will add explicit statements on their processing status and residual misalignment characteristics in the revised manuscript. Separate aligned/unaligned metrics will be provided where the data permits; otherwise we will note the limitation. revision: partial

  3. Referee: [Abstract / Results] The abstract asserts “improved accuracy compared to existing intensity-based approaches,” yet the provided summary contains no numerical error metrics, baseline tables, or train/validation split details. If these are absent from the full results section as well, the quantitative support for the accuracy claim is insufficient.

    Authors: The full results section contains quantitative error metrics, baseline comparisons, and train/validation details supporting the abstract claim. We will add explicit cross-references from the abstract to the relevant tables and figures in the revised version to make this support clearer. revision: no

Circularity Check

0 steps flagged

No circularity detected; supervised regression is self-contained

full rationale

The paper trains a Residual U-Net on magnitude pairs extracted from coregistered Sentinel-1 SLC data, with targets given by independently computed InSAR coherence maps from the identical SLC pairs. This constitutes a standard supervised learning setup in which the supervision signal is generated by a separate interferometric process rather than by the network itself or by any self-referential equation. No load-bearing claim reduces to a fitted parameter renamed as a prediction, no self-citation chain is invoked to justify uniqueness, and the generalization statements are presented as empirical results on held-out datasets rather than as derivations that collapse to the training inputs by construction.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The claim rests on the domain assumption that backscatter magnitudes contain sufficient information to regress coherence, plus the empirical transferability of the learned model; the network itself introduces many fitted parameters.

free parameters (1)
  • Residual U-Net weights and training hyperparameters
    All network parameters are fitted to the target coherence maps derived from Sentinel-1 SLC pairs.
axioms (1)
  • domain assumption Coherence is a learnable function of backscatter magnitude alone
    Invoked by the choice to train the regression model directly on magnitude images without phase or coregistration inputs.

pith-pipeline@v0.9.1-grok · 5696 in / 1319 out tokens · 49290 ms · 2026-06-27T21:02:47.811920+00:00 · methodology

0 comments
read the original abstract

In this work, we propose a deep learning framework for coherence regression directly from detected SAR images, without the need for accurate coregistration. A Residual U-Net is trained using coherence maps derived from precisely coregistered Sentinel-1 SLC data to learn the relationship between backscatter magnitudes and coherence. The model is trained on 12-day SLC pairs and evaluated across different datasets, including coregistered SLC products and open access analysis-ready data, covering diverse radiometric properties, geometries, and locations. Experimental results demonstrate that the proposed method achieves high-resolution coherence regression with improved accuracy compared to existing intensity-based approaches. The network generalizes well across diverse geographical locations and even across different temporal baselines that were never seen at training time. Additionally, the ability to operate on globally available analysis-ready data, such as ground range detected data, e.g., distributed through Google Earth Engine, enables its large-scale application in mission design, change monitoring, and diverse mapping tasks.

Figures

Figures reproduced from arXiv: 2606.07374 by Andrea Pulella, Francescopaolo Sica, Michael Schmitt.

Figure 1
Figure 1. Figure 1: Sentinel-1 processing workflow adopted for reference coherence generation from [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Residual U-Net architecture adopted for coherence regression. The encoder progressively [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Fine-tuning strategy adopted for adapting the proposed framework from slant-range [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: NLCD land-cover map over the San Francisco Bay area, United States, used as a [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Coherence regression results obtained on a 12-day Sentinel-1 interferometric pair [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Three selected crops, A, B, and C, over the San Francisco Bay area are shown, with [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Temporal coherence analysis over Crop A. From top to bottom: input backscatter images, reference coherence maps, coherence estimated using the baseline approach [20], coherence predicted by the proposed framework, and absolute prediction error for 6-, 12-, and 36-day temporal baselines. where the SNR is estimated as: SNR = |z| 2 Pnoise , (8) with z denoting the complex SAR signal and Pnoise the estimated n… view at source ↗
Figure 8
Figure 8. Figure 8: Temporal coherence analysis over Crop B using the same visualization layout as in [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Temporal coherence analysis over Crop C using the same visualization layout as in [PITH_FULL_IMAGE:figures/full_fig_p015_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Temporal coherence analysis at zero baseline. From top to bottom: input backscatter [PITH_FULL_IMAGE:figures/full_fig_p016_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Coherence regression results on VH-polarized Sentinel-1 data over the three represen [PITH_FULL_IMAGE:figures/full_fig_p016_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Coherence regression results over three geographically distinct Sentinel-1 scenarios [PITH_FULL_IMAGE:figures/full_fig_p018_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Coherence regression results obtained under a large-baseline interferometric configu [PITH_FULL_IMAGE:figures/full_fig_p018_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Coherence regression results obtained on an ALOS L-band HH-polarized interfer [PITH_FULL_IMAGE:figures/full_fig_p019_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Temporal coherence predictions obtained on geocoded Sentinel-1 GRD data over [PITH_FULL_IMAGE:figures/full_fig_p020_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Temporal coherence predictions obtained on geocoded Sentinel-1 GRD data over [PITH_FULL_IMAGE:figures/full_fig_p020_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Temporal coherence predictions obtained on geocoded Sentinel-1 GRD data over [PITH_FULL_IMAGE:figures/full_fig_p021_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Local-scale analysis over a developed urban region (Crop I). The figure reports [PITH_FULL_IMAGE:figures/full_fig_p021_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Local-scale analysis over a cultivated region affected by temporal decorrelation [PITH_FULL_IMAGE:figures/full_fig_p022_19.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

38 extracted references · 2 canonical work pages · 1 internal anchor

  1. [1]

    Aiazzi, L

    B. Aiazzi, L. Alparone, S. Baronti, and A. Garzelli. Coherence estimation from multilook incoherent SAR imagery.IEEE Transactions on Geoscience and Remote Sensing, 41(11): 2531–2539, 2003

    2003

  2. [2]

    Chen and H.A

    C.W. Chen and H.A. Zebker. Phase unwrapping for large SAR interferograms: statistical segmentation and generalized network models.IEEE Transactions on Geoscience and Remote Sensing, 40(8):1709–1719, 2002

    2002

  3. [3]

    S. R. Cloude and E. Pottier. A review of target decomposition theorems in radar polarimetry. IEEE Transactions on Geoscience and Remote Sensing, 34(2):498–518, 1997

    1997

  4. [4]

    R.J. Dekker. Texture analysis and classification of ERS SAR images for map updating of urban areas in The Netherlands.IEEE Transactions on Geoscience and Remote Sensing, 41(9):1950–1958, 2003

    1950

  5. [5]

    P. C. Dubois, J. van Zyl, and E. T. Engman. A model for the estimation of soil moisture from radar backscatter.IEEE Transactions on Geoscience and Remote Sensing, 33(4): 915–926, 1995

    1995

  6. [6]

    Engdahl and J.M

    M.E. Engdahl and J.M. Hyyppa. Land-cover classification using multitemporal ERS-1/2 InSAR data.IEEE Transactions on Geoscience and Remote Sensing, 41(7):1620–1628, 2003

    2003

  7. [7]

    E. T. Engman and J. T. Wang. Evaluation of Three Radar Backscatter Roughness Models Using Soil Moisture Data Collected by the Space Shuttle Flight 41G SIR-B SAR.IEEE Transactions on Geoscience and Remote Sensing, 25(5):709–715, 1987

    1987

  8. [8]

    ESA, Frascati, Italy, version 3.9 edition, 2020

    European Space Agency (ESA).Sentinel-1 Product Specification Document. ESA, Frascati, Italy, version 3.9 edition, 2020. URL https://sentinels.copernicus.eu/documents/ 247904/1877131/Sentinel-1-Product-Specification. Accessed: 2025-09-12

    2020

  9. [9]

    The copernicus pod service.Advances in Space Research, 74(6):2615–2648, 2024

    Jaime Fernández, Heike Peter, Carlos Fernández, Javier Berzosa, Marc Fernández, Luning Bao, Miguel Ángel Muñoz, Sonia Lara, Eva Terradillos, Pierre Féménias, and Carolina Nogueira. The copernicus pod service.Advances in Space Research, 74(6):2615–2648, 2024

    2024

  10. [10]

    [Online]

    Google.Google Earth Engine (GEE). [Online]. Available:https://earthengine.google. com/,

  11. [11]

    [Online]

    Google.GEE: Sentinel-1 GRD dataset. [Online]. Available: https://developers.google. com/earth-engine/datasets/catalog/COPERNICUS_S1_GRD,

  12. [12]

    [Online]

    Google.GEE: Sentinel-1 GRD preprocessing. [Online]. Available:https://developers. google.com/earth-engine/guides/sentinel1#sentinel-1-preprocessing, . 25

  13. [13]

    M. T. Hallikainen, F. T. Ulaby, M. C. Dobson, M. A. El-Rayes, and L. Wu. Microwave dielectric behavior of wet soil—Part 1: Empirical models and experimental observations. IEEE Transactions on Geoscience and Remote Sensing, 23(1):25–34, 1985

    1985

  14. [14]

    Deep Residual Learning for Image Recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep Residual Learning for Image Recognition, 2015. URLhttps://arxiv.org/abs/1512.03385

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  15. [15]

    Collin Homer, Jon Dewitz, Limin Yang, Suming Jin, Patrick Danielson, George Xian, John Coulston, Nathaniel Herold, James Wickham, and Kevin Megown. Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information.Photogrammetric Engineering & Remote Sensing, 81 (5):345–354, 2015

    2011

  16. [16]

    Jacob, Fernando Vicente-Guijalba, Carlos Lopez-Martinez, Juan M

    Alexander W. Jacob, Fernando Vicente-Guijalba, Carlos Lopez-Martinez, Juan M. Lopez- Sanchez, Marius Litzinger, Harald Kristen, Alejandro Mestre-Quereda, Dariusz Ziółkowski, Marco Lavalle, Claudia Notarnicola, Gopika Suresh, Oleg Antropov, Shaojia Ge, Jaan Praks, Yifang Ban, Eric Pottier, Jordi Joan Mallorquí Franquet, Javier Duro, and Marcus E. Engdahl. ...

    2020

  17. [17]

    TanDEM-X: A Satellite Formation for High-Resolution SAR Interferometry.IEEE Transactions on Geoscience and Remote Sensing, 45(11):3317–3341, 2007

    Gerhard Krieger, Alberto Moreira, Hauke Fiedler, Irena Hajnsek, Marian Werner, Marwan Younis, and Manfred Zink. TanDEM-X: A Satellite Formation for High-Resolution SAR Interferometry.IEEE Transactions on Geoscience and Remote Sensing, 45(11):3317–3341, 2007

    2007

  18. [18]

    Kuplich, P.J

    T.M. Kuplich, P.J. Curran, and P.M. Atkinson. Relating SAR image texture and backscatter to tropical forest biomass. InIGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477), volume 4, pages 2872–2874, 2003

    2003

  19. [19]

    TanDEM-X Forest Mapping Using Convolutional Neural Networks.Remote Sensing, 11(24):2980, 2019

    Antonio Mazza, Francescopaolo Sica, Paola Rizzoli, and Giuseppe Scarpa. TanDEM-X Forest Mapping Using Convolutional Neural Networks.Remote Sensing, 11(24):2980, 2019

    2019

  20. [20]

    Quick and dirty

    A. V. Monti-Guarnieri and C. Prati. SAR interferometry: a "Quick and dirty" coherence estimator for data browsing.IEEE Transactions on Geoscience and Remote Sensing, 35(3): 660–669, 1997

    1997

  21. [21]

    Coherent change detection for multipass sar.IEEE Transactions on Geoscience and Remote Sensing, 56(11):6811–6822, 2018

    Andrea Monti-Guarnieri, Maria Antonia Brovelli, Marco Manzoni, Mauro Mari- otti d’Alessandro, Monia Elisa Molinari, and Daniele Oxoli. Coherent change detection for multipass sar.IEEE Transactions on Geoscience and Remote Sensing, 56(11):6811–6822, 2018

    2018

  22. [22]

    Nisar sample data product suite, 2025

    NASA. Nisar sample data product suite, 2025. URLhttps://science.nasa.gov/mission/ nisar/sample-data/. Accessed: 2026-04-15

    2025

  23. [23]

    Pinheiro

    M. Pinheiro. Increase of sentinel-1a orbital tube: Impact on interferometry. Technical report, Technical Note ESA-EOPG-EOPGMQ-TN-2024-12, 2024

    2024

  24. [24]

    Multi-Temporal Sentinel-1 Backscatter and Coherence for Rainforest Mapping

    Andrea Pulella, Rodrigo Aragao Santos, Francescopaolo Sica, Philipp Posovszky, and Paola Rizzoli. Multi-Temporal Sentinel-1 Backscatter and Coherence for Rainforest Mapping. Remote Sensing, 12(5):847, 2020

    2020

  25. [25]

    Raney, T

    R.K. Raney, T. Freeman, R.W. Hawkins, and R. Bamler. A plea for radar brightness. In Proceedings of IGARSS ’94 - 1994 IEEE International Geoscience and Remote Sensing Symposium, volume 2, pages 1090–1092, 1994. 26

    1994

  26. [26]

    The SAR2Height framework for urban height map reconstruction from single SAR intensity images.ISPRS Journal of Photogrammetry and Remote Sensing, 211:104–120, 2024

    Michael Recla and Michael Schmitt. The SAR2Height framework for urban height map reconstruction from single SAR intensity images.ISPRS Journal of Photogrammetry and Remote Sensing, 211:104–120, 2024

    2024

  27. [27]

    Deep learning for InSAR processing

    Francescopaolo Sica. Deep learning for InSAR processing. In Michael Schmitt and Ronny Hänsch, editors,Deep Learning for Synthetic Aperture Radar Remote Sensing, chapter 7, pages 147–173. Elsevier, 2026

    2026

  28. [28]

    Repeat-pass SAR interferometry for land cover classification: a methodology using Sentinel-1 short-time-series.Remote Sensing of Environment, 232:111277, 2019

    Francescopaolo Sica, Andrea Pulella, Matteo Nannini, Muriel Pinheiro, and Paola Rizzoli. Repeat-pass SAR interferometry for land cover classification: a methodology using Sentinel-1 short-time-series.Remote Sensing of Environment, 232:111277, 2019

    2019

  29. [29]

    Insar decorrelation at x-band from the joint tandem-x/paz constellation.IEEE Geoscience and Remote Sensing Letters, 18(12):2107–2111, 2021

    Francescopaolo Sica, Sofie Bretzke, Andrea Pulella, José-Luis Bueso-Bello, Michele Martone, Pau Prats-Iraola, María-José González-Bonilla, Michael Schmitt, and Paola Rizzoli. Insar decorrelation at x-band from the joint tandem-x/paz constellation.IEEE Geoscience and Remote Sensing Letters, 18(12):2107–2111, 2021. doi: 10.1109/LGRS.2020.3014809

    work page doi:10.1109/lgrs.2020.3014809 2021

  30. [30]

    Francescopaolo Sica, Giorgia Gobbi, Paola Rizzoli, and Lorenzo Bruzzone.ϕ-Net: Deep Residual Learning for InSAR Parameters Estimation.IEEE Transactions on Geoscience and Remote Sensing, 59(5):3917–3941, 2021

    2021

  31. [31]

    D. Small. Flattening Gamma: Radiometric Terrain Correction for SAR Imagery.IEEE Transactions on Geoscience and Remote Sensing, 49(8):3081–3093, 2011

    2011

  32. [32]

    Stephenson, Tobias Köhne, Eric Zhan, Brent E

    Oliver L. Stephenson, Tobias Köhne, Eric Zhan, Brent E. Cahill, Sang-Ho Yun, Zachary E. Ross, and Mark Simons. Deep Learning-Based Damage Mapping With InSAR Coherence Time Series.IEEE Transactions on Geoscience and Remote Sensing, 60:1–17, 2022

    2022

  33. [33]

    Strozzi, P.B.G

    T. Strozzi, P.B.G. Dammert, U. Wegmuller, J.-M. Martinez, J.I.H. Askne, A. Beaudoin, and N.T. Hallikainen. Landuse mapping with ers sar interferometry.IEEE Transactions on Geoscience and Remote Sensing, 38(2):766–775, 2000

    2000

  34. [34]

    Touzi, A

    R. Touzi, A. Lopes, P. W. Vachon, and C. W. King. Coherence estimation for multilook polsar imagery.IEEE Transactions on Geoscience and Remote Sensing, 42(7):1386–1399, 2004

    2004

  35. [35]

    Minglong Xue, Jian Li, Zheng Zhao, and Qingli Luo. SAR2HEIGHT: Height Estimation from a Single SAR Image in Mountain Areas via Sparse Height and Proxyless Depth-Aware Penalty Neural Architecture Search for U-Net.Remote Sensing, 14(21):5392, 2022

    2022

  36. [36]

    Interferometric Processing of Sentinel-1 TOPS Data.IEEE Transactions on Geoscience and Remote Sensing, 54(4):2220–2234, 2016

    Néstor Yagüe-Martínez, Pau Prats-Iraola, Fernando Rodríguez González, Ramon Brcic, Robert Shau, Dirk Geudtner, Michael Eineder, and Richard Bamler. Interferometric Processing of Sentinel-1 TOPS Data.IEEE Transactions on Geoscience and Remote Sensing, 54(4):2220–2234, 2016

    2016

  37. [37]

    H. A. Zebker and R. M. Goldstein. Topographic Mapping from Interferometric SAR Observations.Journal of Geophysical Research, 97(B4):5037–5046, 1992

    1992

  38. [38]

    Zebker and J

    H.A. Zebker and J. Villasenor. Decorrelation in interferometric radar echoes.IEEE Transactions on Geoscience and Remote Sensing, 30(5):950–959, 1992. 27

    1992