Deep Learning-Based Snow Depth Retrieval Using Sentinel-1 Repeat-Pass InSAR

Nayan Yadav; Shadi Oveisgharan; Shirin Jalali

arxiv: 2604.17128 · v1 · submitted 2026-04-18 · 💻 cs.CE

Deep Learning-Based Snow Depth Retrieval Using Sentinel-1 Repeat-Pass InSAR

Nayan Yadav , Shadi Oveisgharan , Shirin Jalali This is my paper

Pith reviewed 2026-05-10 05:59 UTC · model grok-4.3

classification 💻 cs.CE

keywords snow depthInSARSentinel-1deep learningsnow retrievaltransferabilityremote sensinglidar validation

0 comments

The pith

A deep learning model maps Sentinel-1 repeat-pass InSAR observables directly to snow depth and transfers reliably to new years and regions.

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 model that learns the link between measured InSAR phase and coherence and actual snow depth. It trains the model at a single SnowEx site in Idaho and evaluates it on independent years at that site plus other geographic areas. The model reaches a Pearson correlation of 0.81 against lidar snow depth measurements. This outperforms the roughly 0.47 correlation reported for physics-based Sentinel-1 SWE retrievals at the same location. Accurate high-resolution snow depth data supports better modeling of seasonal water cycles and climate effects.

Core claim

A deep learning model trained on InSAR observables from one SnowEx Idaho site learns a direct mapping to snow depth that holds across independent years and geographically distinct regions, achieving a Pearson correlation of 0.81 with lidar ground truth compared with approximately 0.47 for existing physics-based Sentinel-1 SWE methods over the same site.

What carries the argument

The deep learning model that takes repeat-pass InSAR observables as input and directly outputs snow depth estimates, bypassing explicit physical modeling of snow properties.

If this is right

High-resolution snow depth maps become feasible from existing Sentinel-1 data without requiring detailed physics assumptions about snow density or microstructure.
Performance remains consistent for new acquisition years at the training location and for new geographic areas.
The approach offers a data-driven alternative that can exceed the accuracy of current physics-based Sentinel-1 SWE retrievals.
Operational snow monitoring can rely on a single trained model rather than repeated site-specific calibration.

Where Pith is reading between the lines

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

If the learned mapping proves stable across more radar frequencies or snow climates, similar models could be applied to other satellite InSAR datasets for broader coverage.
Integration with optical or passive microwave observations could address remaining gaps in forested or wet snow conditions.
Routine re-training on a small number of new lidar campaigns could extend the method to additional continents with minimal new field work.

Load-bearing premise

The statistical relationship between InSAR observables and snow depth learned at one site applies without major site-specific biases to independent years and other regions.

What would settle it

Apply the trained model to a new site with different snow types or terrain and measure whether its Pearson correlation with lidar snow depth falls substantially below 0.81.

Figures

Figures reproduced from arXiv: 2604.17128 by Nayan Yadav, Shadi Oveisgharan, Shirin Jalali.

**Figure 1.** Figure 1: Temporal transfer results for BS2020 → BS2021. Panels show (a) lidar snow depth reference, (b) Retrieved SWE using physics-based approach [14], and (c) MLP-predicted snow depth. (a) (b) (c) [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗

**Figure 2.** Figure 2: Spatial transfer results for BS2020 → MC2020. Panels show (a) lidar snow depth reference, (b) Retrieved SWE using physics-based approach [14], and (c) MLP-predicted snow depth. (a) (b) (c) [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗

**Figure 3.** Figure 3: Spatial transfer results for BS2020 → DC2020. Panels show (a) lidar snow depth reference, (b) Retrieved SWE using physics-based approach [14], and (c) MLP-predicted snow depth. ASF’s On-Demand Processing system, Hybrid Pluggable Processing Pipeline (HyP3), is used to generate 6-day interferometric products. Reference snow depth is obtained from NASA SnowEx airborne QSI lidar products, which provide high-re… view at source ↗

**Figure 4.** Figure 4: 2D residual error histogram InSAR predictors include 12-day repeat Sentinel-1 unwrapped interferometric phase, temporal coherence, and radar backscatter amplitude time series. For each pixel, these quantities are provided to the model as temporal stacks spanning 12 acquisitions, preserving time-dependent variability. Interferometric coherence is summarized using its temporal mean and standard deviation to… view at source ↗

**Figure 5.** Figure 5: Spatial distribution of snow depth estimates for the DC2020 dataset. (a) LiDAR-derived snow depth and (b) model-predicted snow depth. The red [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗

read the original abstract

Snow depth plays a central role in seasonal snowpack characterization and the terrestrial water cycle, yet remains challenging to estimate at high spatial resolution. Recent studies have shown that repeat-pass interferometric synthetic aperture radar (InSAR) measurements combined with physics-based models can enable effective snow water equivalent (SWE) retrieval. However, the performance of these methods depends strongly on measurement accuracy and modeling assumptions. Building on the success of InSAR-based approaches, we develop a robust learning-based model that directly learns the relationship between measured InSAR observables and snow depth. The model is trained on a single SnowEx Idaho site and evaluated across independent years and geographically distinct regions. Results demonstrate strong temporal and spatial transferability. In temporal transfer experiments, the proposed approach achieves a Pearson correlation of 0.81 with lidar snow depth, compared to a correlation of approximately 0.47 reported for physics-based Sentinel-1 SWE retrievals over the same site.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper trains a DL model on one SnowEx Idaho site to pull snow depth from Sentinel-1 InSAR and reports decent transfer to other years and regions with r=0.81, beating the physics baseline of 0.47, but the generalization claim rests on thin evidence.

read the letter

The main takeaway is that a supervised deep learning model trained on repeat-pass InSAR phase and coherence from a single Idaho SnowEx site can retrieve snow depth and hold up across independent years and other regions at a Pearson correlation of 0.81 against lidar, compared with roughly 0.47 for the physics-based Sentinel-1 SWE method they cite. That numerical edge is the clearest result they show. What is actually new is the direct regression from InSAR observables to depth without an intermediate physics model for SWE, plus the explicit temporal and spatial transfer tests. The paper does a straightforward job of documenting those splits and the improvement over the baseline they reference. The soft spots are more noticeable. The abstract gives no architecture, loss, optimizer, or training schedule, and the full text would need to supply those plus any ablation on input features or uncertainty estimates to make the numbers interpretable. More importantly, the transfer claim assumes the learned mapping is invariant to site-specific factors like topography, vegetation, incidence angle, and snow microstructure. Without quantitative comparison of how dissimilar the test regions actually are or controls for those variables, it is hard to rule out that the model is exploiting correlations that happen to be similar across the chosen sites rather than learning general physics. That is the load-bearing assumption, and the current description does not close it. This work is for remote-sensing and hydrology groups that already use Sentinel-1 and want to test data-driven alternatives to physics retrievals. A reader who needs high-resolution snow depth maps for water-resource or climate applications could extract the performance numbers and try the approach, provided the methods section is expanded. It deserves a serious referee because the core application is practical, the baseline comparison is clear, and the transfer experiments are a reasonable first step even if they require more scrutiny on generalization and reproducibility. I would send it to review rather than desk reject, with the expectation that the authors add the missing implementation details and site-dissimilarity checks.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes a deep learning model to retrieve snow depth directly from Sentinel-1 repeat-pass InSAR observables (phase and coherence). The model is trained on lidar-labeled data from a single SnowEx Idaho site and evaluated on independent years at the same site (temporal transfer) as well as on geographically distinct regions (spatial transfer), reporting a Pearson correlation of 0.81 with lidar snow depth in the temporal experiments—substantially higher than the ~0.47 correlation cited for physics-based Sentinel-1 SWE retrievals over the same site.

Significance. If the transferability results are reproducible and the model truly learns site-invariant relationships rather than site-specific correlations, the work would represent a meaningful advance over physics-based InSAR approaches for high-resolution snow depth mapping. It could improve operational snowpack monitoring in hydrology and water-resource applications, particularly where physics-based assumptions break down.

major comments (2)

[Abstract] Abstract: The abstract reports concrete performance numbers (Pearson r = 0.81) and a transferability claim but supplies no model architecture, loss function, optimizer, training/validation splits, input feature preprocessing, or uncertainty quantification. These omissions are load-bearing for the central claim because the reported correlations cannot be verified or reproduced without them.
[Results] Results / Methods (transfer experiments): The claim that a model trained on one SnowEx Idaho site generalizes to independent years and geographically distinct regions rests on the untested assumption that InSAR observables map to snow depth invariantly across differences in topography, vegetation structure, incidence angle, and snow microstructure. No quantitative site-dissimilarity metrics, ablation on input features, or cross-site bias analysis are described, so it is impossible to rule out that the 0.81 correlation reflects residual site-specific correlations rather than learned physics.

minor comments (1)

[Abstract] The abstract should explicitly state the number of test years, number of spatial test sites, and the geographic/elevation/land-cover differences between training and test regions to allow readers to gauge the strength of the transferability evidence.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed comments on our manuscript. We address each major comment below and have prepared revisions to improve clarity and strengthen the supporting analyses.

read point-by-point responses

Referee: [Abstract] Abstract: The abstract reports concrete performance numbers (Pearson r = 0.81) and a transferability claim but supplies no model architecture, loss function, optimizer, training/validation splits, input feature preprocessing, or uncertainty quantification. These omissions are load-bearing for the central claim because the reported correlations cannot be verified or reproduced without them.

Authors: We agree that the abstract, being a concise summary, did not include these technical specifications. The full Methods section of the manuscript describes the convolutional neural network architecture, Adam optimizer, mean squared error loss, 70/30 training/validation split on the primary SnowEx site, normalization of phase and coherence inputs, and uncertainty estimation via ensemble runs with varied initializations. To directly address the concern, we will revise the abstract to incorporate the model type, primary training parameters, and data split information while remaining within length constraints. This change will facilitate verification without altering the reported results. revision: yes
Referee: [Results] Results / Methods (transfer experiments): The claim that a model trained on one SnowEx Idaho site generalizes to independent years and geographically distinct regions rests on the untested assumption that InSAR observables map to snow depth invariantly across differences in topography, vegetation structure, incidence angle, and snow microstructure. No quantitative site-dissimilarity metrics, ablation on input features, or cross-site bias analysis are described, so it is impossible to rule out that the 0.81 correlation reflects residual site-specific correlations rather than learned physics.

Authors: The transfer experiments in the manuscript already demonstrate consistent performance across independent years at the training site and on geographically separate regions. However, we acknowledge that explicit quantitative comparisons of site dissimilarity and feature importance were not included. In the revised version, we will add a dedicated analysis subsection that computes site-dissimilarity metrics (e.g., differences in elevation range, vegetation indices from auxiliary datasets, and incidence angle distributions) between training and transfer locations. We will also incorporate an ablation study on input features (phase versus coherence) and provide cross-site bias plots together with error distributions. These additions will more rigorously support the interpretation that the model has learned generalizable relationships. revision: yes

Circularity Check

0 steps flagged

No circularity; standard supervised regression with held-out temporal/spatial evaluation

full rationale

The paper trains a deep learning model on InSAR observables (phase, coherence) paired with lidar snow depth labels from a single SnowEx Idaho site, then evaluates Pearson correlation on independent years and geographically distinct regions. This is a conventional supervised regression pipeline with explicit held-out splits; no derivation step reduces to its own inputs by construction, no fitted parameter is relabeled as a prediction, and no load-bearing claim rests on self-citation or an imported uniqueness theorem. The reported 0.81 correlation is an empirical test outcome, not an algebraic identity with the training data. The comparison to the 0.47 physics-based baseline is external and does not create circularity within the present work.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies no information on model hyperparameters, loss terms, or physical assumptions, so no free parameters, axioms, or invented entities can be identified.

pith-pipeline@v0.9.0 · 5465 in / 1127 out tokens · 53510 ms · 2026-05-10T05:59:55.698636+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

17 extracted references · 17 canonical work pages

[1]

Potential impacts of a warming climate on water availability in snow-dominated regions,

T. P. Barnett, J. C. Adam, and D. P. Lettenmaier, “Potential impacts of a warming climate on water availability in snow-dominated regions,”Nature, vol. 438, no. 7066, pp. 303–309, 2005

work page 2005
[2]

How much runoff originates as snow in the western united states, and how will that change in the future?

D. Li, M. L. Wrzesien, M. Durand, J. Adam, and D. P. Lettenmaier, “How much runoff originates as snow in the western united states, and how will that change in the future?”Geophysical Research Letters, vol. 44, no. 12, pp. 6163–6172, 2017

work page 2017
[3]

Tracking flowpaths in a complex karst system through tracer test and hydrogeochemical monitoring: Implications for groundwater protection (gran sasso, italy),

V . Lorenzi, F. Banzato, M. Barberio, N. Goeppert, N. Goldscheider, F. Gori, A. Lacchini, M. Manetta, G. Medici, S. Rusiet al., “Tracking flowpaths in a complex karst system through tracer test and hydrogeochemical monitoring: Implications for groundwater protection (gran sasso, italy),”Heliyon, vol. 10, no. 2, 2024

work page 2024
[4]

Extent of the rain-snow transition zone in the western us under historic and projected climate,

P. Z. Klos, T. E. Link, and J. T. Abatzoglou, “Extent of the rain-snow transition zone in the western us under historic and projected climate,”Geophysical Research Letters, vol. 41, no. 13, pp. 4560–4568, 2014

work page 2014
[5]

New climate models reveal faster and larger increases in arctic precipitation than previously projected,

M. R. McCrystall, J. Stroeve, M. Serreze, B. C. Forbes, and J. A. Screen, “New climate models reveal faster and larger increases in arctic precipitation than previously projected,”Nature communications, vol. 12, no. 1, p. 6765, 2021

work page 2021
[6]

A low-to-no snow future and its impacts on water resources in the western united states,

E. R. Siirila-Woodburn, A. M. Rhoades, B. J. Hatchett, L. S. Huning, J. Szinai, C. Tague, P. S. Nico, D. R. Feldman, A. D. Jones, W. D. Collinset al., “A low-to-no snow future and its impacts on water resources in the western united states,”Nature Reviews Earth & Environment, vol. 2, no. 11, pp. 800–819, 2021

work page 2021
[7]

Estimating the spatial distribution of snow water equivalent in the world’s mountains,

J. Dozier, E. H. Bair, and R. E. Davis, “Estimating the spatial distribution of snow water equivalent in the world’s mountains,”Wiley Interdisciplinary Reviews: Water, vol. 3, no. 3, pp. 461–474, 2016

work page 2016
[8]

The airborne snow observatory: Fusion of scanning lidar, imaging spectrometer, and physically-based modeling for mapping snow water equivalent and snow albedo,

T. H. Painter, D. F. Berisford, J. W. Boardman, K. J. Bormann, J. S. Deems, F. Gehrke, A. Hedrick, M. Joyce, R. Laidlaw, D. Markset al., “The airborne snow observatory: Fusion of scanning lidar, imaging spectrometer, and physically-based modeling for mapping snow water equivalent and snow albedo,” Remote Sensing of Environment, vol. 184, pp. 139–152, 2016

work page 2016
[9]

Snow depth variability in the northern hemisphere mountains observed from space,

H. Lievens, M. Demuzere, H.-P. Marshall, R. H. Reichle, L. Brucker, I. Brangers, P. de Rosnay, M. Dumont, M. Girotto, W. W. Immerzeelet al., “Snow depth variability in the northern hemisphere mountains observed from space,”Nature communications, vol. 10, no. 1, p. 4629, 2019

work page 2019
[10]

Sentinel-1 snow depth retrieval at sub-kilometer resolution over the european alps,

H. Lievens, I. Brangers, H.-P. Marshall, T. Jonas, M. Olefs, and G. De Lannoy, “Sentinel-1 snow depth retrieval at sub-kilometer resolution over the european alps,”The Cryosphere, vol. 16, no. 1, pp. 159–177, 2022

work page 2022
[11]

Insar for estimation of changes in snow water equivalent of dry snow,

T. Guneriussen, K. A. Hogda, H. Johnsen, and I. Lauknes, “Insar for estimation of changes in snow water equivalent of dry snow,”IEEE Transactions on Geoscience and Remote Sensing, vol. 39, no. 10, pp. 2101–2108, 2002

work page 2002
[12]

Snow water equivalent of dry snow measured by differential interferometry,

S. Leinss, A. Wiesmann, J. Lemmetyinen, and I. Hajnsek, “Snow water equivalent of dry snow measured by differential interferometry,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 8, no. 8, pp. 3773–3790, 2015

work page 2015
[13]

Snow water equivalent change mapping from slope-correlated synthetic aperture radar interferometry (insar) phase variations,

J. Eppler, B. Rabus, and P. Morse, “Snow water equivalent change mapping from slope-correlated synthetic aperture radar interferometry (insar) phase variations,”The Cryosphere, vol. 16, no. 4, pp. 1497–1521, 2022

work page 2022
[14]

Snow water equivalent retrieval over idaho–part 1: Using sentinel-1 repeat-pass interferometry,

S. Oveisgharan, R. Zinke, Z. Hoppinen, and H. P. Marshall, “Snow water equivalent retrieval over idaho–part 1: Using sentinel-1 repeat-pass interferometry,”The Cryosphere, vol. 18, no. 2, pp. 559–574, 2024

work page 2024
[15]

Decorrelation in interferometric radar echoes,

H. A. Zebker and J. Villasenor, “Decorrelation in interferometric radar echoes,”IEEE Transactions on geoscience and remote sensing, vol. 30, no. 5, pp. 950–959, 1992

work page 1992
[16]

Advancing terrestrial snow depth monitoring with machine learning and l-band insar data: a case study using nasa’s snowex 2017 data,

I. O. Alabi, H.-P. Marshall, J. Mead, and E. Trujillo, “Advancing terrestrial snow depth monitoring with machine learning and l-band insar data: a case study using nasa’s snowex 2017 data,”Frontiers in Remote Sensing, vol. 5, p. 1481848, 2025

work page 2017
[17]

Using lidar and snotel data for evaluating the performance of snow water equivalent retrieval using sentinel-1 repeat-pass interferometry,

S. Oveisgharan, E. Havazli, R. Zinke, and Z. Hoppinen, “Using lidar and snotel data for evaluating the performance of snow water equivalent retrieval using sentinel-1 repeat-pass interferometry,”EGUsphere, 2026, under r‘eview

work page 2026

[1] [1]

Potential impacts of a warming climate on water availability in snow-dominated regions,

T. P. Barnett, J. C. Adam, and D. P. Lettenmaier, “Potential impacts of a warming climate on water availability in snow-dominated regions,”Nature, vol. 438, no. 7066, pp. 303–309, 2005

work page 2005

[2] [2]

How much runoff originates as snow in the western united states, and how will that change in the future?

D. Li, M. L. Wrzesien, M. Durand, J. Adam, and D. P. Lettenmaier, “How much runoff originates as snow in the western united states, and how will that change in the future?”Geophysical Research Letters, vol. 44, no. 12, pp. 6163–6172, 2017

work page 2017

[3] [3]

Tracking flowpaths in a complex karst system through tracer test and hydrogeochemical monitoring: Implications for groundwater protection (gran sasso, italy),

V . Lorenzi, F. Banzato, M. Barberio, N. Goeppert, N. Goldscheider, F. Gori, A. Lacchini, M. Manetta, G. Medici, S. Rusiet al., “Tracking flowpaths in a complex karst system through tracer test and hydrogeochemical monitoring: Implications for groundwater protection (gran sasso, italy),”Heliyon, vol. 10, no. 2, 2024

work page 2024

[4] [4]

Extent of the rain-snow transition zone in the western us under historic and projected climate,

P. Z. Klos, T. E. Link, and J. T. Abatzoglou, “Extent of the rain-snow transition zone in the western us under historic and projected climate,”Geophysical Research Letters, vol. 41, no. 13, pp. 4560–4568, 2014

work page 2014

[5] [5]

New climate models reveal faster and larger increases in arctic precipitation than previously projected,

M. R. McCrystall, J. Stroeve, M. Serreze, B. C. Forbes, and J. A. Screen, “New climate models reveal faster and larger increases in arctic precipitation than previously projected,”Nature communications, vol. 12, no. 1, p. 6765, 2021

work page 2021

[6] [6]

A low-to-no snow future and its impacts on water resources in the western united states,

E. R. Siirila-Woodburn, A. M. Rhoades, B. J. Hatchett, L. S. Huning, J. Szinai, C. Tague, P. S. Nico, D. R. Feldman, A. D. Jones, W. D. Collinset al., “A low-to-no snow future and its impacts on water resources in the western united states,”Nature Reviews Earth & Environment, vol. 2, no. 11, pp. 800–819, 2021

work page 2021

[7] [7]

Estimating the spatial distribution of snow water equivalent in the world’s mountains,

J. Dozier, E. H. Bair, and R. E. Davis, “Estimating the spatial distribution of snow water equivalent in the world’s mountains,”Wiley Interdisciplinary Reviews: Water, vol. 3, no. 3, pp. 461–474, 2016

work page 2016

[8] [8]

The airborne snow observatory: Fusion of scanning lidar, imaging spectrometer, and physically-based modeling for mapping snow water equivalent and snow albedo,

T. H. Painter, D. F. Berisford, J. W. Boardman, K. J. Bormann, J. S. Deems, F. Gehrke, A. Hedrick, M. Joyce, R. Laidlaw, D. Markset al., “The airborne snow observatory: Fusion of scanning lidar, imaging spectrometer, and physically-based modeling for mapping snow water equivalent and snow albedo,” Remote Sensing of Environment, vol. 184, pp. 139–152, 2016

work page 2016

[9] [9]

Snow depth variability in the northern hemisphere mountains observed from space,

H. Lievens, M. Demuzere, H.-P. Marshall, R. H. Reichle, L. Brucker, I. Brangers, P. de Rosnay, M. Dumont, M. Girotto, W. W. Immerzeelet al., “Snow depth variability in the northern hemisphere mountains observed from space,”Nature communications, vol. 10, no. 1, p. 4629, 2019

work page 2019

[10] [10]

Sentinel-1 snow depth retrieval at sub-kilometer resolution over the european alps,

H. Lievens, I. Brangers, H.-P. Marshall, T. Jonas, M. Olefs, and G. De Lannoy, “Sentinel-1 snow depth retrieval at sub-kilometer resolution over the european alps,”The Cryosphere, vol. 16, no. 1, pp. 159–177, 2022

work page 2022

[11] [11]

Insar for estimation of changes in snow water equivalent of dry snow,

T. Guneriussen, K. A. Hogda, H. Johnsen, and I. Lauknes, “Insar for estimation of changes in snow water equivalent of dry snow,”IEEE Transactions on Geoscience and Remote Sensing, vol. 39, no. 10, pp. 2101–2108, 2002

work page 2002

[12] [12]

Snow water equivalent of dry snow measured by differential interferometry,

S. Leinss, A. Wiesmann, J. Lemmetyinen, and I. Hajnsek, “Snow water equivalent of dry snow measured by differential interferometry,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 8, no. 8, pp. 3773–3790, 2015

work page 2015

[13] [13]

Snow water equivalent change mapping from slope-correlated synthetic aperture radar interferometry (insar) phase variations,

J. Eppler, B. Rabus, and P. Morse, “Snow water equivalent change mapping from slope-correlated synthetic aperture radar interferometry (insar) phase variations,”The Cryosphere, vol. 16, no. 4, pp. 1497–1521, 2022

work page 2022

[14] [14]

Snow water equivalent retrieval over idaho–part 1: Using sentinel-1 repeat-pass interferometry,

S. Oveisgharan, R. Zinke, Z. Hoppinen, and H. P. Marshall, “Snow water equivalent retrieval over idaho–part 1: Using sentinel-1 repeat-pass interferometry,”The Cryosphere, vol. 18, no. 2, pp. 559–574, 2024

work page 2024

[15] [15]

Decorrelation in interferometric radar echoes,

H. A. Zebker and J. Villasenor, “Decorrelation in interferometric radar echoes,”IEEE Transactions on geoscience and remote sensing, vol. 30, no. 5, pp. 950–959, 1992

work page 1992

[16] [16]

Advancing terrestrial snow depth monitoring with machine learning and l-band insar data: a case study using nasa’s snowex 2017 data,

I. O. Alabi, H.-P. Marshall, J. Mead, and E. Trujillo, “Advancing terrestrial snow depth monitoring with machine learning and l-band insar data: a case study using nasa’s snowex 2017 data,”Frontiers in Remote Sensing, vol. 5, p. 1481848, 2025

work page 2017

[17] [17]

Using lidar and snotel data for evaluating the performance of snow water equivalent retrieval using sentinel-1 repeat-pass interferometry,

S. Oveisgharan, E. Havazli, R. Zinke, and Z. Hoppinen, “Using lidar and snotel data for evaluating the performance of snow water equivalent retrieval using sentinel-1 repeat-pass interferometry,”EGUsphere, 2026, under r‘eview

work page 2026