pith. sign in

arxiv: 2606.05368 · v2 · pith:UDKSN3HQnew · submitted 2026-06-03 · 💻 cs.CV

Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin

Sayan Mandal , Rocco Sedona , Simon Besnard , Mikhail Urbazaev , Morris Riedel , Ehsan Zandi , Gabriele Cavallaro This is my paper

Pith reviewed 2026-06-28 06:00 UTC · model grok-4.3

classification 💻 cs.CV
keywords Biomazon datasetGEDI RH profilesAGBDAmazon Basinmultimodal remote sensingforest structure modelingmachine learning benchmarkbiomass prediction
0
0 comments X

The pith

Biomazon supplies a 20 m multimodal benchmark that pairs full GEDI RH profiles and AGBD with multi-sensor inputs for joint forest-structure modeling in the Amazon.

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

The paper creates Biomazon, a benchmark dataset over the Amazon at 20 m resolution that combines GEDI measurements of forest height profiles and biomass with data from multiple sensors. It provides standardized spatial splits to support training and evaluation of machine learning models that predict the full vertical structure jointly with biomass rather than separate scalars. Baseline experiments with a shared encoder-decoder model explore how different backbones, modalities, and embeddings affect performance in single and joint prediction tasks. Comparisons to existing gridded products place the results in context for tropical forest applications.

Core claim

Biomazon is a 20 m multimodal benchmark dataset over the Amazon Basin that pairs GEDI RH and AGBD targets with multi-sensor predictors including Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, and AlphaEarth embeddings, under standardized spatial splits and evaluation protocols, enabling joint prediction of the entire RH profile with AGBD.

What carries the argument

The Biomazon dataset with its GEDI targets and multi-sensor inputs under fixed splits, used as the central benchmark for evaluating joint RH-profile and AGBD prediction methods.

If this is right

  • Allows comprehensive ablation of model scale, modality contributions, and auxiliary embeddings in standalone and fusion settings.
  • Reports single-target and joint-target results under a unified training protocol to quantify tradeoffs.
  • Provides regionally aligned comparisons against existing GEDI L4D RH10-RH98 and AGBD products at matching temporal scale.
  • Establishes a reference benchmark for future work on structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.

Where Pith is reading between the lines

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

  • Joint modeling of the full profile may reduce biomass estimation errors by enforcing physically consistent ordering across RH percentiles.
  • The dataset could support extensions to other tropical regions once similar GEDI pairings become available.
  • Standardized protocols may allow direct comparison of new methods against the reported baselines without re-implementing splits.

Load-bearing premise

The chosen multi-sensor predictors and standardized spatial splits produce an ML-ready benchmark without leakage or regional bias.

What would settle it

A demonstration that models trained on Biomazon show large performance drops on held-out regions or no gain over models trained on prior datasets without the full multimodal stack would falsify its value as a robust benchmark.

Figures

Figures reproduced from arXiv: 2606.05368 by Ehsan Zandi, Gabriele Cavallaro, Mikhail Urbazaev, Morris Riedel, Rocco Sedona, Sayan Mandal, Simon Besnard.

Figure 1
Figure 1. Figure 1: Spatial coverage of Biomazon dataset in the Amazon Basin visualized using the Dynamic World V1 LULC [11] modality (01/04/2019–30/03/2023), spanning 80.10°W–44.91°W and 16.37°S–6.33°N; gray indicates areas outside the coverage region. GEDI’s footprint Above-Ground Biomass Density (AGBD) es￾timates explicitly depend on vertical-structure (relative height (RH)) metrics rather than a single canopy-height proxy… view at source ↗
Figure 2
Figure 2. Figure 2: Extent of spatial coverage of the acquisitions of the input modalities across the study area. We can see (a), (b), (c) and (d) have full coverage. (g) [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Radar signal interaction with forest canopy across major SAR [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Train-Val-Test split of Biomazon. Splitting is done at tile-level after removal of tile-overlap. Light green: train, dark-green: train tiles lying in cross-zone showing uneven overlapping, dark-blue: val tiles, red: test tiles. valid pixels are present in either the RH or AGBD band of the GEDI raster, ensuring a minimum amount of lidar supervision per patch. Because the target distributions are skewed, ext… view at source ↗
Figure 5
Figure 5. Figure 5: GEDI target distributions in the Biomazon dataset. Expanded tail views are shown for RH98 and AGBD, the predominant scalar targets in existing forest-structure and biomass datasets. List 1 Tile-level splitting procedure. 1) Tile trimming: Because adjacent HLS-MGRS tiles share an overlap strip of ≈4.9 km per side, we first trim each tile to its midline-partitioned footprint so that no ground location appear… view at source ↗
Figure 6
Figure 6. Figure 6: Proposed architecture with AEX fusion (Config 8). The decoder heads are detailed in Fig.8. [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Proposed AlphaEarth embeddings fusion architecture in Config 8. [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Proposed AlphaEarth embeddings Base architecture (Config 0). [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Bin-wise relative RMSE difference % of Config 1-8 vs Config 0, using Prithvi-100M encoder. Config 0 AEX-Base is used as reference point. For [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Bin-wise RMSE of models under different training setups. Prithvi setups used Config 8 while AEXB setups used Config 0. Left column shows RH98 [PITH_FULL_IMAGE:figures/full_fig_p016_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Comparison of our baselines vs available products across different RH percentiles. [PITH_FULL_IMAGE:figures/full_fig_p018_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Visual comparison of our baselines vs GEDI L4D on RH10. [PITH_FULL_IMAGE:figures/full_fig_p018_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Visual comparison of our baselines vs GEDI L4D on RH50. [PITH_FULL_IMAGE:figures/full_fig_p019_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Visual comparison of our baselines vs GEDI L4D, Wagner et al., Potapov et al. and Tolan et al. on RH95. [PITH_FULL_IMAGE:figures/full_fig_p020_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Visual comparison of our baselines vs GEDI L4D and Lang et al. on RH98. [PITH_FULL_IMAGE:figures/full_fig_p021_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Visual comparison of our baselines vs GEDI L4D and ESA Biomass CCI on AGBD. [PITH_FULL_IMAGE:figures/full_fig_p021_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Scatterplot comparison of RH10 between GEDI L4D and our baselines. [PITH_FULL_IMAGE:figures/full_fig_p022_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Scatterplot comparison of RH50 between GEDI L4D and our baselines. [PITH_FULL_IMAGE:figures/full_fig_p022_18.png] view at source ↗
Figure 19
Figure 19. Figure 19: Scatterplot comparison of RH95 between GEDI L4D, Wagner et al., Potapov et al., Tolan et al. and our baselines. [PITH_FULL_IMAGE:figures/full_fig_p023_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Scatterplot comparison of RH98 between GEDI L4D, Lang et al. and our baselines. [PITH_FULL_IMAGE:figures/full_fig_p023_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: Scatterplot comparison of AGBD between GEDI L4D, ESA Biomass CCI and our baselines. [PITH_FULL_IMAGE:figures/full_fig_p024_21.png] view at source ↗
read the original abstract

Accurate, spatially explicit characterization of tropical forest structure is essential for carbon accounting and ecosystem monitoring, yet most ML pipelines predict canopy-top height proxies (e.g., RH95/RH98) or AGBD as separate scalar targets, rather than learning the forest vertical structure as an ordered profile. The community lacks a ML-ready multimodal benchmark for predicting the entire GEDI RH profile jointly with AGBD, or for evaluating methods that enforce physically consistent ordering across RH percentiles. We address this with Biomazon, a 20 m multimodal benchmark dataset over the Amazon Basin that pairs GEDI RH and AGBD targets with multi-sensor predictors (Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, and AlphaEarth embeddings) under standardized spatial splits and evaluation protocols. Using a shared encoder-decoder with task-specific heads as a baseline framework, we conduct a comprehensive ablation study of (i) backbone/model scale, (ii) modality contributions, and (iii) the use of auxiliary embeddings under standalone and fusion settings, and we report both single-target and joint-target results to quantify tradeoffs under a unified training protocol. Finally, we contextualize baseline performance through regionally aligned comparisons against existing gridded products, including GEDI L4D RH10-RH98 and AGBD, at matching temporal scale. Biomazon, together with the accompanying protocols and baseline results, establishes a reference benchmark for future work on structurally consistent RH-profile prediction and structure-biomass modeling in tropical forests.

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.

Referee Report

1 major / 0 minor

Summary. The manuscript introduces Biomazon, a 20 m resolution multimodal dataset over the Amazon Basin that pairs GEDI RH profiles and AGBD targets with multi-sensor predictors (Sentinel-1/2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World LULC, AlphaEarth embeddings). It supplies standardized spatial splits and evaluation protocols, together with baseline encoder-decoder experiments that ablate backbone scale, modality contributions, auxiliary embeddings, and single- versus joint-target training, plus comparisons to existing gridded GEDI L4D products.

Significance. If the spatial splits demonstrably eliminate leakage, Biomazon would supply a needed public benchmark for methods that predict ordered RH profiles jointly with AGBD while enforcing physical consistency, moving the field beyond separate scalar height or biomass regressions.

major comments (1)
  1. [Methods] Methods (spatial split description): the manuscript states that standardized spatial splits are provided but supplies no block size, minimum separation distance, or stratification method. In the Amazon, where forest structure and Sentinel/ALOS signatures exhibit autocorrelation lengths of several km, splits that are merely “spatial” rather than explicitly block-cross-validated at scales exceeding predictor correlation length leave the central claim of an ML-ready, leakage-free benchmark unsubstantiated.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback emphasizing the need for explicit details on spatial splitting to substantiate the leakage-free benchmark claim. We agree this aspect requires clarification and will revise the manuscript to address it directly.

read point-by-point responses

  1. Referee: [Methods] Methods (spatial split description): the manuscript states that standardized spatial splits are provided but supplies no block size, minimum separation distance, or stratification method. In the Amazon, where forest structure and Sentinel/ALOS signatures exhibit autocorrelation lengths of several km, splits that are merely “spatial” rather than explicitly block-cross-validated at scales exceeding predictor correlation length leave the central claim of an ML-ready, leakage-free benchmark unsubstantiated.

    Authors: We acknowledge that the manuscript currently lacks explicit details on block size, minimum separation distance, and stratification method for the spatial splits. This omission weakens the substantiation of the leakage-free claim, particularly given the autocorrelation scales of several km for forest structure and multi-sensor predictors in the Amazon. In the revised manuscript, we will expand the Methods section (and associated data documentation) to specify: (i) the block size selected to exceed typical predictor correlation lengths, (ii) the minimum separation distance enforced between training and test blocks, and (iii) the stratification approach (e.g., by ecoregion or canopy cover). We will also release the exact splitting code and metadata to enable independent verification. These additions will directly support the central claim of an ML-ready benchmark. revision: yes

Circularity Check

0 steps flagged

Dataset release with baselines; no derivation chain present

full rationale

The paper releases a multimodal dataset (Biomazon) pairing GEDI targets with predictors under spatial splits and reports baseline ML experiments. No equations, fitted parameters, or first-principles derivations are claimed or present in the provided text. The central contribution is data curation and empirical benchmarking rather than any prediction that reduces to its inputs by construction. Self-citations, if any, are not load-bearing for a derivation. This matches the default non-circular case for dataset papers.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no technical sections available to audit free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5837 in / 1105 out tokens · 47377 ms · 2026-06-28T06:00:46.927335+00:00 · methodology

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

100 extracted references · 26 canonical work pages

  1. [1]

    3d-abc: A foundation model for global terrestrial 3d above and below ground carbon stock mapping,

    G. Grosse, J. Hashemi, L. van Delden, T. L ¨ubker, I. Nitze, J. Strauss, S. Kruse, U. Herzschuh, P. Ghamisi, P. Steinbach, G. Joshi, W. Yu, A. Rizaldy, R. Gloaguen, G. Cavallaro, E. Zandi, R. Sedona, S. Hashim, S. Mandal, M. Herold, Q. Song, S. Besnard, M. Urbazaev, M. Sips, A. Huth, I. Hajnsek, and M. Pardini, “3d-abc: A foundation model for global terre...

    2025

  2. [2]

    JUWELS Cluster and Booster: Exascale Pathfinder with Modular Supercomputing Architecture at Juelich Supercomputing Centre,

    J ¨ulich Supercomputing Centre, “JUWELS Cluster and Booster: Exascale Pathfinder with Modular Supercomputing Architecture at Juelich Supercomputing Centre,”Journal of large-scale research facilities, vol. 7, no. A183, 2021. [Online]. Available: http://dx.doi.org/ 10.17815/jlsrf-7-183

    work page doi:10.17815/jlsrf-7-183 2021

  3. [3]

    A large and persistent carbon sink in the world’s forests,

    Y . Pan, R. A. Birdsey, J. Fang, R. Houghton, P. E. Kauppi, W. A. Kurz, O. L. Phillips, A. Shvidenko, S. L. Lewis, J. G. Canadell, P. Ciais, R. B. Jackson, S. W. Pacala, A. D. McGuire, S. Piao, A. Rautiainen, S. Sitch, and D. Hayes, “A large and persistent carbon sink in the world’s forests,”Science, vol. 333, no. 6045, pp. 988–993, 2011. [Online]. Availa...

    work page doi:10.1126/science.1201609 2011

  4. [4]

    Tropical forests are home to over half of the world’s vertebrate species,

    R. Pillay, M. Venter, J. Aragon-Osejo, P. Gonz ´alez-del Pliego, A. J. Hansen, J. E. Watson, and O. Venter, “Tropical forests are home to over half of the world’s vertebrate species,”Frontiers in Ecology and the Environment, vol. 20, no. 1, pp. 10–15, 2022. [Online]. Available: https://esajournals.onlinelibrary.wiley.com/doi/abs/10.1002/fee.2420

    work page doi:10.1002/fee.2420 2022

  5. [5]

    Characterizing the structural complexity of the earth’s forests with spaceborne lidar,

    T. de Conto, R. Dubayah, and J. Armston, “Characterizing the structural complexity of the earth’s forests with spaceborne lidar,” May 2024. [Online]. Available: http://dx.doi.org/10.21203/rs.3.rs-4445870/v1 27

    work page doi:10.21203/rs.3.rs-4445870/v1 2024

  6. [6]

    Aboveground biomass density models for nasa’s global ecosystem dynamics investigation (gedi) lidar mission,

    L. Duncanson, J. R. Kellner, J. Armston, R. Dubayah, D. M. Minor, S. Hancock, S. P. Healey, P. L. Patterson, S. Saarela, S. Marselis, C. E. Silva, J. Bruening, S. J. Goetz, H. Tang, M. Hofton, B. Blair, S. Luthcke, L. Fatoyinbo, K. Abernethy, A. Alonso, H.-E. Andersen, P. Aplin, T. R. Baker, N. Barbier, J. F. Bastin, P. Biber, P. Boeckx, J. Bogaert, L. Bo...

    2022

  7. [7]

    Algorithm theoretical basis document for gedi footprint aboveground biomass density,

    J. R. Kellner, J. Armston, and L. Duncanson, “Algorithm theoretical basis document for gedi footprint aboveground biomass density,” Earth and Space Science, vol. 10, no. 4, p. e2022EA002516, 2023, e2022EA002516 2022EA002516. [Online]. Available: https: //agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2022EA002516

    work page doi:10.1029/2022ea002516 2023

  8. [8]

    The global ecosystem dynamics investigation: High-resolution laser ranging of the earth’s forests and topography,

    R. Dubayah, J. B. Blair, S. Goetz, L. Fatoyinbo, M. Hansen, S. Healey, M. Hofton, G. Hurtt, J. Kellner, S. Luthcke, J. Armston, H. Tang, L. Duncanson, S. Hancock, P. Jantz, S. Marselis, P. L. Patterson, W. Qi, and C. Silva, “The global ecosystem dynamics investigation: High-resolution laser ranging of the earth’s forests and topography,” Science of Remote...

    2020

  9. [9]

    A high- resolution canopy height model of the earth,

    N. Lang, W. Jetz, K. Schindler, and J. D. Wegner, “A high- resolution canopy height model of the earth,”Nature Ecology & Evolution, vol. 7, no. 11, p. 1778–1789, 2023. [Online]. Available: http://dx.doi.org/10.1038/s41559-023-02206-6

    work page doi:10.1038/s41559-023-02206-6 2023

  10. [10]

    Mapping global forest canopy height through integration of gedi and landsat data,

    P. Potapov, X. Li, A. Hernandez-Serna, A. Tyukavina, M. C. Hansen, A. Kommareddy, A. Pickens, S. Turubanova, H. Tang, C. E. Silva, J. Armston, R. Dubayah, J. B. Blair, and M. Hofton, “Mapping global forest canopy height through integration of gedi and landsat data,”Remote Sensing of Environment, vol. 253, p. 112165, 2021. [Online]. Available: https://www....

    2021

  11. [11]

    Dynamic world, near real-time global 10 m land use land cover mapping,

    C. F. Brown, S. P. Brumby, B. Guzder-Williams, T. Birch, S. B. Hyde, J. Mazzariello, W. Czerwinski, V . J. Pasquarella, R. Haertel, S. Ilyushchenko, K. Schwehr, M. Weisse, F. Stolle, C. Hanson, O. Guinan, R. Moore, and A. M. Tait, “Dynamic world, near real-time global 10 m land use land cover mapping,” Scientific Data, vol. 9, no. 1, 2022. [Online]. Avail...

    work page doi:10.1038/s41597-022-01307-4 2022

  12. [12]

    Species level mapping of forest canopy height in nepal using gedi with sentinel-1 and sentinel-2,

    A. Nazir, N. P. Hanan, H. Gilani, and H. L. Shrestha, “Species level mapping of forest canopy height in nepal using gedi with sentinel-1 and sentinel-2,”Frontiers in Remote Sensing, vol. V olume 7 - 2026, 2026. [Online]. Available: https://www.frontiersin.org/journals/ remote-sensing/articles/10.3389/frsen.2026.1725509

    work page doi:10.3389/frsen.2026.1725509 2026

  13. [13]

    Canopy height mapping in the western himalayas, pakistan: A deep learning approach using gedi and sentinel-2 fusion,

    A. Ahmad, S. Sastry, A. Dhakal, S. Khanal, A. Levering, H. Gilani, and N. Jacobs, “Canopy height mapping in the western himalayas, pakistan: A deep learning approach using gedi and sentinel-2 fusion,”International Journal of Applied Earth Observation and Geoinformation, vol. 146, p. 105030, 2026. [Online]. Available: https://www.sciencedirect.com/science/...

    2026

  14. [14]

    Satellite-based mapping of annual canopy height and aboveground biomass in african dense forests,

    L. Wan, P. Ciais, A. de Truchis, E. Sean, F. J. Fischer, D. Purnell, G. Belouze, I. Fayad, M. Schwartz, Y . Xu, Y . Su, M. R ´ejou-M´echain, N. Barbier, P. Tresson, J.-F. Bastin, J. Bogaert, A. Vander Linden, A. Plumacker, B. Angoboy Ilondea, D.-M. Assumani, T. de Haulleville, L. B. Sagang, L. Durieux, Y . Ryu, T. Yang, C. V . Obame, T. Bossy, F. Frappart...

    work page doi:10.3389/frsen.2025.1724950 2025

  15. [15]

    Mapping vegetation height and identifying the northern forest limit across canada using icesat-2, landsat time series and topographic data,

    H. Travers-Smith, N. Coops, C. Mulverhill, M. Wulder, D. Ignace, and T. Lantz, “Mapping vegetation height and identifying the northern forest limit across canada using icesat-2, landsat time series and topographic data,”Remote Sensing of Environment, vol. 305, p. 114097, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S003442...

    2024

  16. [16]

    Very high resolution canopy height maps from rgb imagery using self-supervised vision transformer and convolutional decoder trained on aerial lidar,

    J. Tolan, H.-I. Yang, B. Nosarzewski, G. Couairon, H. V . V o, J. Brandt, J. Spore, S. Majumdar, D. Haziza, J. Vamaraju, T. Moutakanni, P. Bojanowski, T. Johns, B. White, T. Tiecke, and C. Couprie, “Very high resolution canopy height maps from rgb imagery using self-supervised vision transformer and convolutional decoder trained on aerial lidar,”Remote Se...

    2024

  17. [17]

    Wall-to-wall amazon forest height mapping with planet nicfi, aerial lidar, and a u-net regression model,

    F. H. Wagner, R. Dalagnol, G. Carter, M. C. M. Hirye, S. Gill, L. B. S. Takougoum, S. Favrichon, M. Keller, J. P. H. B. Ometto, L. Alves, C. Creze, S. P. George-Chacon, S. Li, Z. Liu, A. Mullissa, Y . Yang, E. G. Santos, S. R. Worden, M. Brandt, P. Ciais, S. C. Hagen, and S. Saatchi, “Wall-to-wall amazon forest height mapping with planet nicfi, aerial lid...

    work page doi:10.1002/rse2.70041

  18. [18]

    Gedi l2a elevation and height metrics data global footprint level v002,

    R. Dubayah, M. Hofton, J. Blair, J. Armston, H. Tang, and S. Luthcke, “Gedi l2a elevation and height metrics data global footprint level v002,” 2021. [Online]. Available: https://www.earthdata.nasa.gov/data/ catalog/lpcloud-gedi02-a-002

    2021

  19. [19]

    Alphaearth foundations: An embedding field model for accurate and efficient global mapping from sparse label data,

    C. F. Brown, M. R. Kazmierski, V . J. Pasquarella, W. J. Rucklidge, M. Samsikova, C. Zhang, E. Shelhamer, E. Lahera, O. Wiles, S. Ilyushchenko, N. Gorelick, L. L. Zhang, S. Alj, E. Schechter, S. Askay, O. Guinan, R. Moore, A. Boukouvalas, and P. Kohli, “Alphaearth foundations: An embedding field model for accurate and efficient global mapping from sparse ...

    Pith/arXiv arXiv 2025

  20. [20]

    Tessera: Temporal embeddings of surface spectra for earth representation and analysis,

    Z. Feng, C. Atzberger, S. Jaffer, J. Knezevic, S. Sormunen, R. Young, M. C. Lisaius, M. Immitzer, T. Jackson, J. Ball, D. A. Coomes, A. Madhavapeddy, A. Blake, and S. Keshav, “Tessera: Temporal embeddings of surface spectra for earth representation and analysis,”

  21. [21]

    Available: https://arxiv.org/abs/2506.20380

    [Online]. Available: https://arxiv.org/abs/2506.20380

    Pith/arXiv arXiv

  22. [22]

    Spectral indices outperform alphaearth foundation embeddings for aboveground biomass estimation in a regenerating tropical andean forest,

    J. Rojas-Lucero, Y . Solano-Correa, N. Kolarik, J. Brandt, and T. Caughlin, “Spectral indices outperform alphaearth foundation embeddings for aboveground biomass estimation in a regenerating tropical andean forest,”Remote Sensing Applications: Society and Environment, vol. 42, p. 102113, 2026. [Online]. Available: https: //www.sciencedirect.com/science/ar...

    2026

  23. [23]

    Open-canopy: Towards very high resolution forest monitor- ing,

    F. Fogel, Y . Perron, N. Besic, L. Saint-Andr ´e, A. Pellissier-Tanon, M. Schwartz, T. Boudras, I. Fayad, A. d’Aspremont, L. Landrieu, and P. Ciais, “Open-canopy: Towards very high resolution forest monitor- ing,” in2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 1395–1406

    2025

  24. [24]

    Preditree: A multi-temporal sub-meter dataset of multi-spectral imagery aligned with canopy height maps,

    H. Debary, M. Fiaz, and L. Klein, “Preditree: A multi-temporal sub-meter dataset of multi-spectral imagery aligned with canopy height maps,” 2025. [Online]. Available: https://arxiv.org/abs/2509.01202

    arXiv 2025

  25. [25]

    Biomassters: A benchmark dataset for forest biomass estimation using multi-modal satellite time-series,

    A. Nascetti, R. Yadav, K. Brodt, Q. Qu, H. Fan, Y . Shendryk, I. Shah, and C. Chung, “Biomassters: A benchmark dataset for forest biomass estimation using multi-modal satellite time-series,” inAdvances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, Eds., vol. 36. Curran Associates, Inc., 2023...

    2023

  26. [26]

    Agbd: A global-scale biomass dataset,

    G. Sialelli, T. Peters, J. D. Wegner, and K. Schindler, “Agbd: A global-scale biomass dataset,”ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. X-G-2025, pp. 829–838, 2025. [Online]. Available: https://isprs-annals.copernicus.org/ articles/X-G-2025/829/2025/

    2025

  27. [27]

    Gedi l4d imputed waveforms, version 2,

    E. Seo, S. Healey, Z. Yang, R. Dubayah, T. De Conto, and J. Armston, “Gedi l4d imputed waveforms, version 2,” 2025, accessed: 2026-02-19. [Online]. Available: https://www.earthdata.nasa.gov/data/ catalog/ornl-cloud-gedi-l4d-imputed-waveforms-2455-2

    2025

  28. [28]

    Santoro and O

    M. Santoro and O. Cartus, “Esa biomass climate change initiative (biomass cci): Global datasets of forest above-ground biomass for the years 2007, 2010, 2015, 2016, 2017, 2018, 2019, 2020, 2021 and 2022, v6.0,” 2025. [Online]. Available: https://catalogue.ceda.ac. uk/uuid/95913ffb6467447ca72c4e9d8cf30501 28

    2007

  29. [29]

    Super-resolved canopy height mapping from sentinel-2 time series using lidar hd reference data across metropolitan france,

    K. Ekaterina, H. Florian, M. St ´ephane, M. Florian, and P. Milena, “Super-resolved canopy height mapping from sentinel-2 time series using lidar hd reference data across metropolitan france,” 2025. [Online]. Available: http://dx.doi.org/10.2139/ssrn.5917615

    work page doi:10.2139/ssrn.5917615 2025

  30. [30]

    Sera-h: Beyond native sentinel spatial limits for high-resolution canopy height mapping,

    T. Boudras, M. Schwartz, R. Fensholt, M. Brandt, I. Fayad, J.-P. Wigneron, G. Belouze, F. Fogel, and P. Ciais, “Sera-h: Beyond native sentinel spatial limits for high-resolution canopy height mapping,”

  31. [31]

    Available: https://arxiv.org/abs/2512.18128

    [Online]. Available: https://arxiv.org/abs/2512.18128

    arXiv

  32. [32]

    Assessment and improvement of gedi canopy height estimation in tropical and temperate forests,

    M.-S. Cho, D. P. Roy, H. B. Kashongwe, L. Yan, and M. Shen, “Assessment and improvement of gedi canopy height estimation in tropical and temperate forests,”Science of Remote Sensing, vol. 11, p. 100221, 2025. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S2666017225000276

    2025

  33. [33]

    Forest aboveground biomass estimation using gedi and earth observation data through attention-based deep learning,

    W. Dong, E. T. A. Mitchard, H. Yu, S. Hancock, and C. M. Ryan, “Forest aboveground biomass estimation using gedi and earth observation data through attention-based deep learning,” 2023. [Online]. Available: https://arxiv.org/abs/2311.03067

    arXiv 2023

  34. [34]

    Interpolation of gedi biomass estimates with calibrated uncertainty quantification,

    R. Young and S. Keshav, “Interpolation of gedi biomass estimates with calibrated uncertainty quantification,” 2026. [Online]. Available: https://arxiv.org/abs/2601.16834

    arXiv 2026

  35. [35]

    Remotely sensed l-band sar data for tropical forest biomass estimation,

    H. Omar, H. Khali, and A. R. Kassim, “Remotely sensed l-band sar data for tropical forest biomass estimation,”Journal of Tropical Forest Science, vol. 23, pp. 318–327, 07 2011

    2011

  36. [36]

    The use of alos/palsar backscatter to estimate above-ground forest biomass: A case study in western siberia,

    A. Peregon and Y . Yamagata, “The use of alos/palsar backscatter to estimate above-ground forest biomass: A case study in western siberia,”Remote Sensing of Environment, vol. 137, pp. 139–146, 2013. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S0034425713002058

    2013

  37. [37]

    Estimating and mapping aboveground biomass of vegetation in typical lake flooding wetland based on modis and landsat images fusion,

    X. Li, Y . Lin, Z. Lv, Y . Song, and X. Huang, “Estimating and mapping aboveground biomass of vegetation in typical lake flooding wetland based on modis and landsat images fusion,” Remote Sensing, vol. 17, no. 22, 2025. [Online]. Available: https: //www.mdpi.com/2072-4292/17/22/3754

    2025

  38. [38]

    A 30 m canopy height map in china created by fusion of multiple relative height metrics,

    Y . Xiao, Q. Wang, H. Xi, and X. Tong, “A 30 m canopy height map in china created by fusion of multiple relative height metrics,”IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1–16, 2025

    2025

  39. [39]

    Application of lidar for critical endangered bird species conservation on the island of kauai, hawaii,

    G. A. Fricker, L. H. Crampton, E. M. Gallerani, J. M. Hite, R. Inman, and T. W. Gillespie, “Application of lidar for critical endangered bird species conservation on the island of kauai, hawaii,” Ecosphere, vol. 12, no. 6, p. e03554, 2021. [Online]. Available: https://esajournals.onlinelibrary.wiley.com/doi/abs/10.1002/ecs2.3554

    work page doi:10.1002/ecs2.3554 2021

  40. [40]

    Multitemporal sentinel and gedi data integration for overstory and understory fuel type classification,

    P. Mohammadpour, D. X. Viegas, A. Pereira, and E. Chuvieco, “Multitemporal sentinel and gedi data integration for overstory and understory fuel type classification,”International Journal of Applied Earth Observation and Geoinformation, vol. 139, p. 104455, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S1569843225001025

    2025

  41. [41]

    DUNIA: Pixel- sized embeddings via cross-modal alignment for earth observation applications,

    I. Fayad, M. Zimmer, M. Schwartz, F. Gieseke, P. CIAIS, G. Belouze, S. Brood, A. de Truchis, and A. d’Aspremont, “DUNIA: Pixel- sized embeddings via cross-modal alignment for earth observation applications,” inForty-second International Conference on Machine Learning, 2025. [Online]. Available: https://openreview.net/forum?id= JXCiQteuOv

    2025

  42. [42]

    Pangaea: Assessing geospatial foundation models capabilities through a global and inclusive benchmark,

    V . Marsocci, Y . Jia, G. L. Bellier, D. Kerekes, L. Zeng, S. Hafner, S. Gerard, E. Brune, R. Yadav, A. Shibli, H. Fang, Y . Ban, M. Vergauwen, N. Audebert, and A. Nascetti, “Pangaea: Assessing geospatial foundation models capabilities through a global and inclusive benchmark,”IEEE Geoscience and Remote Sensing Magazine, vol. 14, no. 1, p. 245–285, Feb. 2...

    work page doi:10.1109/mgrs.2025.3628194 2026

  43. [43]

    Geo-bench: Toward foundation models for earth monitoring,

    A. Lacoste, N. Lehmann, P. Rodriguez, E. Sherwin, H. Kerner, B. L ¨utjens, J. Irvin, D. Dao, H. Alemohammad, A. Drouin, M. Gunturkun, G. Huang, D. Vazquez, D. Newman, Y . Bengio, S. Ermon, and X. Zhu, “Geo-bench: Toward foundation models for earth monitoring,” inAdvances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko,...

    2023

  44. [44]

    Unified deep learning model for global prediction of aboveground biomass, canopy height, and cover from high-resolution, multi-sensor satellite imagery,

    M. Weber, C. Beneke, and C. Wheeler, “Unified deep learning model for global prediction of aboveground biomass, canopy height, and cover from high-resolution, multi-sensor satellite imagery,” Remote Sensing, vol. 17, no. 9, 2025. [Online]. Available: https: //www.mdpi.com/2072-4292/17/9/1594

    2025

  45. [45]

    Monotonic networks,

    J. Sill, “Monotonic networks,” inAdvances in Neural Information Pro- cessing Systems, M. Jordan, M. Kearns, and S. Solla, Eds., vol. 10. MIT Press, 1997. [Online]. Available: https://proceedings.neurips.cc/paper files/paper/1997/file/83adc9225e4deb67d7ce42d58fe5157c-Paper.pdf

    1997

  46. [46]

    Non-crossing quantile regression for deep reinforcement learning,

    F. Zhou, J. Wang, and X. Feng, “Non-crossing quantile regression for deep reinforcement learning,” inProceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS ’20. Red Hook, NY , USA: Curran Associates Inc., 2020

    2020

  47. [47]

    Non-decreasing quantile function network with efficient exploration for distributional reinforcement learning,

    F. Zhou, Z. Zhu, Q. Kuang, and L. Zhang, “Non-decreasing quantile function network with efficient exploration for distributional reinforcement learning,” inProceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, Z.-H. Zhou, Ed. International Joint Conferences on Artificial Intelligence Organization, 8 2021, pp. 34...

    work page doi:10.24963/ijcai.2021/476 2021

  48. [48]

    Distributional reinforcement learning with monotonic splines,

    Y . Luo, G. Liu, H. Duan, O. Schulte, and P. Poupart, “Distributional reinforcement learning with monotonic splines,” inInternational Conference on Learning Representations, 2022. [Online]. Available: https://openreview.net/forum?id=C8Ltz08PtBp

    2022

  49. [49]

    Impact of amazonian deforestation on precipitation reverses between seasons,

    Y . Qin, D. Wang, A. D. Ziegler, B. Fu, and Z. Zeng, “Impact of amazonian deforestation on precipitation reverses between seasons,” Nature, vol. 639, no. 8053, p. 102–108, Mar. 2025. [Online]. Available: http://dx.doi.org/10.1038/s41586-024-08570-y

    work page doi:10.1038/s41586-024-08570-y 2025

  50. [50]

    His- torical deforestation drives strong rainfall decline across the southern amazon basin,

    J. Cui, S. Piao, C. Huntingford, T. Wang, and D. V . Spracklen, “His- torical deforestation drives strong rainfall decline across the southern amazon basin,”Nature Communications, vol. 17, no. 1, Jan. 2026. [Online]. Available: http://dx.doi.org/10.1038/s41467-026-68361-z

    work page doi:10.1038/s41467-026-68361-z 2026

  51. [51]

    The drivers and impacts of amazon forest degradation,

    D. M. Lapola, P. Pinho, J. Barlow, L. E. O. C. Arag ˜ao, E. Berenguer, R. Carmenta, H. M. Liddy, H. Seixas, C. V . J. Silva, C. H. L. Silva- Junior, A. A. C. Alencar, L. O. Anderson, D. Armenteras, V . Brovkin, K. Calders, J. Chambers, L. Chini, M. H. Costa, B. L. Faria, P. M. Fearnside, J. Ferreira, L. Gatti, V . H. Gutierrez-Velez, Z. Han, K. Hibbard, C...

    work page doi:10.1126/science.abp8622 2023

  52. [52]

    Critical transitions in the amazon forest system,

    B. M. Flores, E. Montoya, B. Sakschewski, N. Nascimento, A. Staal, R. A. Betts, C. Levis, D. M. Lapola, A. Esqu ´ıvel-Muelbert, C. Jakovac, C. A. Nobre, R. S. Oliveira, L. S. Borma, D. Nian, N. Boers, S. B. Hecht, H. ter Steege, J. Arieira, I. L. Lucas, E. Berenguer, J. A. Marengo, L. V . Gatti, C. R. C. Mattos, and M. Hirota, “Critical transitions in the...

    work page doi:10.1038/s41586-023-06970-0 2024

  53. [53]

    Google earth engine: Planetary-scale geospatial analysis for everyone,

    N. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, “Google earth engine: Planetary-scale geospatial analysis for everyone,”Remote Sensing of Environment, vol. 202, pp. 18–27, 2017, big Remotely Sensed Data: tools, applications and experiences. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S0034425717302900

    2017

  54. [54]

    gedidb: A toolbox for processing and providing global ecosystem dynamics investigation (gedi) l2a-b and l4a-c data,

    S. Besnard, F. Dombrowski, and A. Holcomb, “gedidb: A toolbox for processing and providing global ecosystem dynamics investigation (gedi) l2a-b and l4a-c data,”Journal of Open Source Software, vol. 10, no. 113, p. 8593, 2025. [Online]. Available: https://doi.org/10.21105/joss.08593

    work page doi:10.21105/joss.08593 2025

  55. [55]

    Copernicus Sentinel-2 (processed by ESA), 2021, MSI Level-2A BOA Reflectance Product. Collection 1,

    European Space Agency, “Copernicus Sentinel-2 (processed by ESA), 2021, MSI Level-2A BOA Reflectance Product. Collection 1,” 2021. [Online]. Available: https://doi.org/10.5270/S2 -znk9xsj

    work page doi:10.5270/s2 2021

  56. [56]

    Comparison between top and bottom of atmosphere sentinel-2 image for mangrove mapping in balikpapan bay, east kalimantan,

    D. Ginting, K. Setiawan, N. Anggraini, A. Suardana, M. Nandika, A. Ulfa, K. Aziz, and R. Dewanti, “Comparison between top and bottom of atmosphere sentinel-2 image for mangrove mapping in balikpapan bay, east kalimantan,”BIO Web of Conferences, vol. 89, p. 07003, 2024. [Online]. Available: http://dx.doi.org/10.1051/bioconf/20248907003

    work page doi:10.1051/bioconf/20248907003 2024

  57. [57]

    Comparison of sentinel-2 and landsat 8 imagery for forest variable prediction in boreal region,

    H. Astola, T. H ¨ame, L. Sirro, M. Molinier, and J. Kilpi, “Comparison of sentinel-2 and landsat 8 imagery for forest variable prediction in boreal region,”Remote Sensing of Environment, vol. 223, pp. 257–273, 2019. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S0034425719300252

    2019

  58. [58]

    Comparison of sentinel-2 and landsat 8 in the estimation of boreal forest canopy cover and leaf area index,

    L. Korhonen, Hadi, P. Packalen, and M. Rautiainen, “Comparison of sentinel-2 and landsat 8 in the estimation of boreal forest canopy cover and leaf area index,”Remote Sensing of Environment, vol. 195, pp. 259–274, 2017. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S0034425717301256

    2017

  59. [59]

    Evaluating the capabilities of sentinel-2 for quantitative estimation of biophysical variables in vegetation,

    W. J. Frampton, J. Dash, G. Watmough, and E. J. Milton, “Evaluating the capabilities of sentinel-2 for quantitative estimation of biophysical variables in vegetation,”ISPRS Journal of Photogrammetry and 29 Remote Sensing, vol. 82, pp. 83–92, 2013. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S092427161300107X

    2013

  60. [60]

    Evaluation of sentinel-2 red-edge bands for empirical estimation of green lai and chlorophyll content,

    J. Delegido, J. Verrelst, L. Alonso, and J. Moreno, “Evaluation of sentinel-2 red-edge bands for empirical estimation of green lai and chlorophyll content,”Sensors, vol. 11, no. 7, pp. 7063–7081, 2011. [Online]. Available: https://www.mdpi.com/1424-8220/11/7/7063

    2011

  61. [61]

    Multi-model estimation of forest canopy closure by using red edge bands based on sentinel-2 images,

    Y . Hua and X. Zhao, “Multi-model estimation of forest canopy closure by using red edge bands based on sentinel-2 images,”Forests, vol. 12, no. 12, 2021. [Online]. Available: https://www.mdpi.com/1999-4907/ 12/12/1768

    2021

  62. [62]

    State-wide forest canopy height and aboveground biomass map for new york with 10 m resolution, integrating gedi, sentinel-1, and sentinel-2 data,

    H. Tamiminia, B. Salehi, M. Mahdianpari, and T. Goulden, “State-wide forest canopy height and aboveground biomass map for new york with 10 m resolution, integrating gedi, sentinel-1, and sentinel-2 data,” Ecological Informatics, vol. 79, p. 102404, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1574954123004338

    2024

  63. [63]

    Harmonized Sentinel-2 MSI: Mul- tiSpectral Instrument, Level-2A (SR),

    Google Earth Engine Data Catalog, “Harmonized Sentinel-2 MSI: Mul- tiSpectral Instrument, Level-2A (SR),” https://developers.google.com/ earth-engine/datasets/catalog/COPERNICUS S2 SR HARMONIZED, [Accessed 20-10-2025]

    2025

  64. [64]

    Cloud Score+ S2 HARMONIZED V1,

    Google Earth Engine Data Catalog, “Cloud Score+ S2 HARMONIZED V1,” https://developers.google.com/earth-engine/datasets/catalog/ GOOGLE CLOUD SCORE PLUS V1 S2 HARMONIZED, [Accessed 20-10-2025]

    2025

  65. [65]

    Comprehensive quality assessment of optical satellite imagery using weakly supervised video learning,

    V . J. Pasquarella, C. F. Brown, W. Czerwinski, and W. J. Rucklidge, “Comprehensive quality assessment of optical satellite imagery using weakly supervised video learning,” in2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, pp. 2125–2135

    2023

  66. [66]

    Sentinel-1 SAR GRD: C- band Synthetic Aperture Radar Ground Range Detected, log scaling,

    Google Earth Engine Data Catalog, “Sentinel-1 SAR GRD: C- band Synthetic Aperture Radar Ground Range Detected, log scaling,” https://developers.google.com/earth-engine/datasets/catalog/ COPERNICUS S1 GRD, [Accessed 07-10-2025]

    2025

  67. [67]

    Sentinel-1 Algorithms,

    Google Earth Engine Data Catalog, “Sentinel-1 Algorithms,” https:// developers.google.com/earth-engine/guides/sentinel1, [Accessed 07-10- 2025]

    2025

  68. [68]

    Review of remote sensing-based methods for forest aboveground biomass estimation: Progress, challenges, and prospects,

    L. Tian, X. Wu, Y . Tao, M. Li, C. Qian, L. Liao, and W. Fu, “Review of remote sensing-based methods for forest aboveground biomass estimation: Progress, challenges, and prospects,”Forests, vol. 14, no. 6,

  69. [69]

    Available: https://www.mdpi.com/1999-4907/14/6/1086

    [Online]. Available: https://www.mdpi.com/1999-4907/14/6/1086

    1999

  70. [70]

    Using long-term sar backscatter data to monitor post-fire vegetation recovery in tundra environment,

    Z. Zhou, L. Liu, L. Jiang, W. Feng, and S. V . Samsonov, “Using long-term sar backscatter data to monitor post-fire vegetation recovery in tundra environment,”Remote Sensing, vol. 11, no. 19, 2019. [Online]. Available: https://www.mdpi.com/2072-4292/11/19/2230

    2019

  71. [71]

    Improving forest above-ground biomass retrieval using multi-sensor l- and c- band sar data and multi-temporal spaceborne lidar data,

    M. Musthafa and G. Singh, “Improving forest above-ground biomass retrieval using multi-sensor l- and c- band sar data and multi-temporal spaceborne lidar data,”Frontiers in Forests and Global Change, vol. V olume 5 - 2022, 2022. [Online]. Available: https://www.frontiersin.org/ journals/forests-and-global-change/articles/10.3389/ffgc.2022.822704

    work page doi:10.3389/ffgc.2022.822704 2022

  72. [72]

    Assessment of forest above ground biomass estimation using multi-temporal c-band sentinel- 1 and polarimetric l-band palsar-2 data,

    X. Huang, B. Ziniti, N. Torbick, and M. J. Ducey, “Assessment of forest above ground biomass estimation using multi-temporal c-band sentinel- 1 and polarimetric l-band palsar-2 data,”Remote Sensing, vol. 10, no. 9,

  73. [73]

    Available: https://www.mdpi.com/2072-4292/10/9/1424

    [Online]. Available: https://www.mdpi.com/2072-4292/10/9/1424

    2072

  74. [74]

    Fusing sentinel-1 and -2 to model gedi-derived vegetation structure characteristics in gee for the paraguayan chaco,

    P. Kacic, A. Hirner, and E. Da Ponte, “Fusing sentinel-1 and -2 to model gedi-derived vegetation structure characteristics in gee for the paraguayan chaco,”Remote Sensing, vol. 13, no. 24, 2021. [Online]. Available: https://www.mdpi.com/2072-4292/13/24/5105

    2021

  75. [75]

    High- resolution canopy height map in the landes forest (france) based on gedi, sentinel-1, and sentinel-2 data with a deep learning approach,

    M. Schwartz, P. Ciais, C. Ottl ´e, A. De Truchis, C. Vega, I. Fayad, M. Brandt, R. Fensholt, N. Baghdadi, F. Morneau, D. Morin, D. Guyon, S. Dayau, and J.-P. Wigneron, “High- resolution canopy height map in the landes forest (france) based on gedi, sentinel-1, and sentinel-2 data with a deep learning approach,”International Journal of Applied Earth Observ...

    2024

  76. [76]

    PALSAR-2 ScanSAR Level 2.2,

    Google Earth Engine Data Catalog, “PALSAR-2 ScanSAR Level 2.2,” https://developers.google.com/earth-engine/datasets/catalog/JAXA ALOS PALSAR-2 Level2 2 ScanSAR, [Accessed 06-10-2025]

    2025

  77. [77]

    Quantifying the sensitivity of l-band sar to a decade of vegetation structure changes in savannas,

    K. Wessels, X. Li, A. Bouvet, R. Mathieu, R. Main, L. Naidoo, B. Erasmus, and G. P. Asner, “Quantifying the sensitivity of l-band sar to a decade of vegetation structure changes in savannas,”Remote Sensing of Environment, vol. 284, p. 113369, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0034425722004758

    2023

  78. [78]

    Copernicus DEM GLO-30: Global 30m Digital Elevation Model,

    Google Earth Engine Data Catalog, “Copernicus DEM GLO-30: Global 30m Digital Elevation Model,” https://developers.google.com/ earth-engine/datasets/catalog/COPERNICUS DEM GLO30, [Accessed 06-10-2025]

    2025

  79. [79]

    Dynamic World V1,

    Google Earth Engine Data Catalog, “Dynamic World V1,” https://developers.google.com/earth-engine/datasets/catalog/GOOGLE DYNAMICWORLD V1, [Accessed 04-10-2025]

    2025

  80. [80]

    Capabilities and limitations of landsat and land cover data for aboveground woody biomass estimation of uganda,

    V . Avitabile, A. Baccini, M. A. Friedl, and C. Schmullius, “Capabilities and limitations of landsat and land cover data for aboveground woody biomass estimation of uganda,”Remote Sensing of Environment, vol. 117, pp. 366–380, 2012, remote Sensing of Urban Environments. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S0034425711003609

    2012

Showing first 80 references.