the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
AI-Driven TanDEM-X Penetration Bias Estimation in Antarctica Using ICESat-2 and ECMWF Data: Implications for the NASA Surface Topography and Vegetation Decadal Survey Incubation study
Abstract. TanDEM-X radar penetration into polar ice introduces significant uncertainties in digital elevation models (DEMs), consequently affecting the accuracy of glacial mass balance estimations. This limitation arises from the variable penetration depth of radar signals in snow and ice, which can cause the DEM surface to deviate from the true physical surface. X-band radars, operating in the 8–12 GHz range, interact with ice through absorption, reflection, and transmission. These interactions heavily depend on variables such as ice temperature, water content, snow density, and salinity, which directly influence microwave penetration depth and signal behaviour. Advancements in remote sensing have leveraged X-band synthetic aperture radar (SAR) to characterize snow and ice surfaces, facilitating applications such as sea ice classification and snow layer analysis. However, X-band SAR signals often exhibit biases in elevation measurements due to their partial penetration into snow and ice. This bias complicates efforts to integrate SAR-derived digital elevation models (DEMs) with laser altimetry data like ICESat-2, where penetration is negligible. Therefore, correcting X-band biases is critical for achieving high-accuracy surface elevation models and reliable glaciological assessments. Here we address these challenges by integrating neural network techniques with TanDEM-X (TDX) DEMs, Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) altimetry data, and environmental parameters from European Centre for Medium-Range Weather Forecasts (ECMWF). We leverage about 300,000 ICESat-2 pointwise measurements acquired within 30 days of TDX measurements spanning 2021–2024 in Antarctica. Additionally, we consider a diverse dataset of snow and atmospheric variables including temperature, snowfall, snow depth, and wind speed to model and predict X-band penetration biases across Antarctica. This approach advances existing methods by automating bias correction and enhancing the integration of SAR and altimetry datasets achieving mean bias correction of the order 1 cm with a Root Mean Square Error (RMSE) of about 1 m and maximum errors of the order of 10 m. Findings from this work provide actionable insights for improving elevation model accuracy in different ways. First, we offer the retrieved pointwise TanDEM-X, ICESat-2 and ECMWF dataset open access for future studies through a dedicated Zenodo page. Second, we provide both our trained network weights and our algorithms in the form of Jupyter Notebooks on Github for improved reproducibility. Most importantly, we discuss the broader efforts in the NASA Surface Topography Elevation (STV) decadal survey incubation study and polar ice monitoring by addressing penetration biases which is one of the most critical uncertainties in radar remote sensing of snow and ice.
- Preprint
(6453 KB) - Metadata XML
-
Supplement
(4824 KB) - BibTeX
- EndNote
Status: final response (author comments only)
-
CC1: 'Comment on egusphere-2025-1979', Georg Fischer, 23 Jun 2025
-
AC2: 'Reply on CC1', Ankita Vashishtha, 02 Oct 2025
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-1979/egusphere-2025-1979-AC2-supplement.pdf
-
AC2: 'Reply on CC1', Ankita Vashishtha, 02 Oct 2025
-
RC1: 'Comment on egusphere-2025-1979', Anonymous Referee #1, 29 Jun 2025
Please find the comments in the attachment.
-
AC3: 'Reply on RC1', Ankita Vashishtha, 02 Oct 2025
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-1979/egusphere-2025-1979-AC3-supplement.pdf
-
AC3: 'Reply on RC1', Ankita Vashishtha, 02 Oct 2025
-
RC2: 'Comment on egusphere-2025-1979', Anonymous Referee #2, 21 Aug 2025
Thank you to the authors for this contribution. The work is novel and will be impactful for developing multisensor fusion architectures under the Surface Topography and Vegetation mission. After looking closely at the previous review for this submission, I do not have any further comments; I agree with the previous reviewer in that I expect a more professional written presentation before initial manuscript submission. Please revise this manuscript following the suggestions given by the previous reviewer. This will allow me to provide a more focused scientific review for the next round of revisions.
Citation: https://doi.org/10.5194/egusphere-2025-1979-RC2 -
AC1: 'Reply on RC2', Ankita Vashishtha, 02 Oct 2025
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-1979/egusphere-2025-1979-AC1-supplement.pdf
-
AC1: 'Reply on RC2', Ankita Vashishtha, 02 Oct 2025
Data sets
(2021–2024) Dataset for : AI-Driven TanDEM-X Penetration Bias Estimation in Antarctica Using ICESat-2 and ECMWF Data Ankita Vashishtha, Pietro Milillo, Alexandre Becker Campos, Jose Luis Bueso Bello, Paola Rizzoli, and Johan Nilsson https://zenodo.org/records/15321465?preview=1&token=eyJhbGciOiJIUzUxMiIsImlhdCI6MTc0NjE2NTc3MCwiZXhwIjoxNzY5ODE3NTk5fQ.eyJpZCI6IjA5ODU2ZGEzLWNhNGUtNDI0Ny04OTVjLTM2YWNjMWQyYzdkYSIsImRhdGEiOnt9LCJyYW5kb20iOiJiZjVkMDNkZTJiOWQxOGZkNzczZGY2MzcxNWQ3MmY2YyJ9.wNoHk4a4BTu-dg0_K_hvQ_01Rc5dKtJ52JipmrxpCXUquUPCHoQiz3r_QU7WW7Lsx5MhYtvk3-_QkaYEIBQ7NA
Model code and software
https://github.com/Milillo-lab/TanDEM-X_ICESat-2_BiasEstimator Ankita Vashishtha, Pietro Milillo, Alexandre Becker Campos https://github.com/Milillo-lab/TanDEM-X_ICESat-2_BiasEstimator
Viewed
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
808 | 129 | 23 | 960 | 41 | 13 | 31 |
- HTML: 808
- PDF: 129
- XML: 23
- Total: 960
- Supplement: 41
- BibTeX: 13
- EndNote: 31
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
Dear authors,
very interesting approach! This is just one question/comment from selectively reading the preprint.
Whereas the relation between penetration bias and radar parameters (coherence, amplitude) is well know and understood (which makes it powerful for AI-based penetration bias corrections, such as yours), I find it a clever idea to include environmental parameters for an additional performance gain. As far as I understand, you use only current environmental parameters within 15 or 30 days of the TanDEM-X acquisition. This has a clear relevance, for instance about snow wetness, as you describe and discuss.
However, since the penetration is clearly related to the firn properties below the surface (e.g. stratigraphy, presence of refrozen melt layers, grain sizes, ...), I'm wondering if the environmental parameters of the recent few years might be actually more relevant than only the current ones within 30 days of the SAR acquisition. The environmental parameters of the past few years could be a good proxy for the subsurface firn structure/properties that determine signal penetration.
What's your take on this? Did you explore using environmental parameters from the previous years? An implementation of this probably triggers a couple of further questions, so I guess this might be something for future research. I still would be interested to hear a comment about this from you.
Best regards,
Georg Fischer