pith. sign in

arxiv: 2606.24364 · v1 · pith:MDH4TQTTnew · submitted 2026-06-23 · 📡 eess.IV

High Resolution Sediment-Specific Surface Soil Moisture Retrieval Using Sentinel-1 Time Series and Auxiliary Data

Alireza Hamedianfar , Oleg Antropov , Matthieu Molinier , Ulla Salmela , Hanna Kukkula , Lauri Seitsonen , Pauliina Liwata-Kentt\"al\"a , Maarit Middleton This is my paper

Pith reviewed 2026-06-25 22:27 UTC · model grok-4.3

classification 📡 eess.IV
keywords soil moisture retrievalSentinel-1SARmachine learningsediment-specificmining siteLightGBMtime series
0
0 comments X

The pith

Sediment-specific models using Sentinel-1 time series and auxiliary data retrieve surface soil moisture with RMSE of 0.037-0.050 m³/m³ and R² up to 0.90.

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

The paper tests whether models tailored to individual sediments at a limestone quarry can improve surface soil moisture estimates from Sentinel-1 radar data under varying weather. It combines SAR backscatter and time-series indices with Sentinel-2 optical data, topography and temperature, then trains machine learning algorithms on in-situ capacitance sensor readings. Tree-based ensembles reach the lowest errors and highest correlations when the full feature set is used. The work aims to support high-resolution monitoring where soil conditions differ by material type. Accuracy proves highest for clay and organic soils and lower for sand and gravel.

Core claim

The authors establish that sediment-specific well-calibrated machine learning models, using the most comprehensive feature set of Sentinel-1 backscatter and time-series soil moisture indices along with Sentinel-2 optical, topographic and temperature predictors, produce spatially explicit high-resolution soil moisture estimates. In the best configurations, RMSE reaches 0.037-0.050 m³ m⁻³ with R² up to 0.90, and tree-based ensembles like LightGBM, random forest and XGBoost give the most accurate and stable results. Adding sediment type information improves basic Sentinel-1 retrievals by more than 2 volumetric percent but adds little when richer features are already included. Performance varies

What carries the argument

Sediment-specific machine learning regression models trained on multi-source remote sensing features and in-situ capacitance sensor data.

If this is right

  • Tree-based ensemble methods yield the most accurate and stable soil moisture predictions across conditions.
  • Comprehensive feature sets that include time-series indices and auxiliary data outperform Sentinel-1 backscatter alone.
  • Sediment type information provides notable gains mainly for simpler Sentinel-1-only retrievals.
  • Retrieval accuracy differs across sediment types, remaining lowest for clay and organic soils.

Where Pith is reading between the lines

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

  • The method could be tested at other mining or construction sites that share similar sediment variability, provided local calibration data exist.
  • High-resolution maps produced this way could support real-time decisions on dust control or drainage at active quarries.
  • Extending the temporal coverage or adding further sensor inputs might reduce errors further for the harder-to-predict sediments such as gravel.

Load-bearing premise

The in-situ reference observations from capacitance sensors accurately represent the true soil moisture for each sediment type under varying weather conditions at the study site.

What would settle it

Independent validation measurements at the same site or a similar mining location that produce RMSE values consistently above 0.06 m³/m³ for the same feature sets and methods would challenge the reported accuracy.

Figures

Figures reproduced from arXiv: 2606.24364 by Alireza Hamedianfar, Hanna Kukkula, Lauri Seitsonen, Maarit Middleton, Matthieu Molinier, Oleg Antropov, Pauliina Liwata-Kentt\"al\"a, Ulla Salmela.

Figure 1
Figure 1. Figure 1: Location and overview of study site with IoT soil moisture sensors. R [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Studied sediment classes with varying vegetation cover: a) Organic [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Meteorological characterization of the study site during observa [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Reference volumetric water content monitoring data for measured [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Flowchart illustrating overall approach for model development for operational soil moisture prediction over a mineral extraction site T [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Example of produced spatially explicit SSM map for a) northern and [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: RMSE% heatmaps illustrating SSM retrieval performance across feature sets and regression methods at sensor level and sediment-area level. RMSE values are reported in volumetric percentage points 3.3. Influence of feature set composition in SSM retrieval The progressive evaluation of the feature sets showed a clear improvement in SSM retrieval accuracy as additional predictor groups were introduced. Figures… view at source ↗
Figure 8
Figure 8. Figure 8: Selected scatterplots illustrating prediction performance on sensor and sediment-area levels with XGBoost and LightGBM methods AU [PITH_FULL_IMAGE:figures/full_fig_p011_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Distribution of RMSE% values across feature sets (sensor-plot level) based on 144 experiments with sediment labels included as a predictor variable [PITH_FULL_IMAGE:figures/full_fig_p012_9.png] view at source ↗
Figure 12
Figure 12. Figure 12: RMSE distribution across Sentinel-1 orbits and regression models RE [PITH_FULL_IMAGE:figures/full_fig_p012_12.png] view at source ↗
Figure 11
Figure 11. Figure 11: Performance summary on sensor and sediment-area level across dif [PITH_FULL_IMAGE:figures/full_fig_p012_11.png] view at source ↗
Figure 13
Figure 13. Figure 13: Sediment specific performance across various SSM retrieval models, [PITH_FULL_IMAGE:figures/full_fig_p013_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: E PR [PITH_FULL_IMAGE:figures/full_fig_p013_14.png] view at source ↗
read the original abstract

In this study, we examine the potential of continuous ground moisture monitoring over a mining site using a combination of in-situ soil moisture sensors and multi-sensor SAR images. We focus on assessing and improving methodologies for retrieval of surface soil moisture, i.e. ground moisture, from SAR measurements focusing on detailed in situ reference observations for several key geomaterials, i.e. sediments, typical in the study site. The mining site represents a limestone quarry locate in the southeastern Finland. Our hypothesis is that sediment-specific well-calibrated models can be instrumental in improving soil moisture retrieval under different weather conditions to produce spatially explicit soil moisture estimates at high resolution compared to baseline approaches. Studied SAR data are represented by Copernicus Sentinel-1 C-band images, while auxiliary datasets include optical Sentinel-2 data. Reference data were collected using IoT enabled capacitance sensors. The examined machine learning methods include Xgboost, LightGBM, RFs, linear regression and k-nearest neighbors regression. The best performance was achieved with the most comprehensive feature set which combines Sentinel-1 backscatter, time-series based soil moisture indices, Sentinel-2 optical, topographic, and temperature predictors. In the best sediment-area-level configurations, RMSE decreased to 0.037-0.050 m^3 m^(-3) (3.7-5.0 volumetric % points), with R^2 values reaching 0.90. Tree-based ensemble methods, especially LightGBM, RF, and XGBoost, provided the most accurate and stable predictions. Accuracy varied by sediment texture, with the lowest errors for clay and organic soil and higher errors for flotation sand and gravel. Adding sediment information improved Sentinel-1-only retrievals by more than 2 vol-%, but provided little additional benefit when richer multi-source feature sets were used.

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

2 major / 2 minor

Summary. The manuscript claims that sediment-specific machine learning models trained on Sentinel-1 C-band SAR time series, augmented with Sentinel-2 optical indices, topographic, and temperature predictors, can retrieve surface soil moisture at high resolution over a Finnish limestone quarry. Using IoT capacitance sensors as reference, it reports that tree-based ensembles (LightGBM, RF, XGBoost) achieve RMSE of 0.037-0.050 m³ m⁻³ and R² up to 0.90 in the best sediment-area configurations, with sediment information improving Sentinel-1-only retrievals by >2 vol-% and accuracy varying by texture (lowest errors on clay/organic, higher on sand/gravel).

Significance. If the reference observations are reliable, the work offers a practical demonstration of how multi-source features and sediment stratification can enhance SAR-based soil moisture retrieval in heterogeneous mining environments. The empirical comparison across five ML methods and multiple feature sets, plus the reported gains from time-series indices, would be a useful contribution to operational monitoring applications.

major comments (2)
  1. [Abstract and §3] Abstract and §3 (Methods/Validation): All reported metrics (RMSE 0.037-0.050 m³ m⁻³, R²=0.90) are computed directly against the IoT capacitance sensor readings used as ground truth, yet the text supplies no per-sediment calibration curves, laboratory dielectric measurements, gravimetric cross-checks, or independent validation of the sensors across clay, organic, sand, and gravel materials. Capacitance probes are known to require texture-specific calibration because of sensitivity to bulk density, salinity, and organic content; without this, the sediment-specific improvement claim and headline accuracy figures rest on an untested assumption that the sensors faithfully track true volumetric moisture.
  2. [§4] §4 (Results): The claim that 'adding sediment information improved Sentinel-1-only retrievals by more than 2 vol-%' is presented without error bars, statistical significance tests, or cross-validation details that would confirm the improvement is not an artifact of post-hoc model selection or data leakage between training and test periods.
minor comments (2)
  1. [Abstract and §2] The abstract and methods section should explicitly state the number of sensors per sediment class, the temporal overlap between SAR acquisitions and sensor readings, and any temporal filtering applied to the time series.
  2. [Abstract] Notation for volumetric moisture (m³ m⁻³) is used inconsistently with the parenthetical 'volumetric % points'; standardize throughout.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major point below and indicate where revisions will be made to improve clarity and rigor.

read point-by-point responses

  1. Referee: [Abstract and §3] Abstract and §3 (Methods/Validation): All reported metrics (RMSE 0.037-0.050 m³ m⁻³, R²=0.90) are computed directly against the IoT capacitance sensor readings used as ground truth, yet the text supplies no per-sediment calibration curves, laboratory dielectric measurements, gravimetric cross-checks, or independent validation of the sensors across clay, organic, sand, and gravel materials. Capacitance probes are known to require texture-specific calibration because of sensitivity to bulk density, salinity, and organic content; without this, the sediment-specific improvement claim and headline accuracy figures rest on an untested assumption that the sensors faithfully track true volumetric moisture.

    Authors: We agree that the manuscript does not present per-sediment laboratory calibrations or gravimetric cross-checks for the capacitance sensors. The sensors were installed and operated according to manufacturer guidelines for volumetric moisture estimation in typical mineral soils, and our analysis treats the readings as the reference for evaluating relative model performance across sediment types. The sediment-specific models are intended to capture texture-related variations in the SAR-auxiliary feature space rather than to correct absolute sensor bias. In revision we will expand §3 to include a dedicated paragraph on sensor limitations, citing the known sensitivity of capacitance probes to texture, bulk density and organic matter, and we will qualify the reported RMSE/R² values as relative to the deployed IoT readings. revision: yes

  2. Referee: [§4] §4 (Results): The claim that 'adding sediment information improved Sentinel-1-only retrievals by more than 2 vol-%' is presented without error bars, statistical significance tests, or cross-validation details that would confirm the improvement is not an artifact of post-hoc model selection or data leakage between training and test periods.

    Authors: The >2 vol-% improvement was obtained by comparing otherwise identical model configurations (same feature sets, same temporal splits) with and without the sediment class as an additional categorical predictor; the comparison was repeated across the five ML algorithms and multiple random seeds. In the revised manuscript we will (i) report standard deviations across the cross-validation folds, (ii) add paired statistical tests (Wilcoxon signed-rank on per-fold RMSE) to quantify significance of the sediment-information gain, and (iii) provide an explicit description of the temporal blocking used in cross-validation to exclude leakage. These additions will appear in §4 and the supplementary material. revision: yes

Circularity Check

0 steps flagged

Empirical ML regression on in-situ targets exhibits no circularity

full rationale

The paper trains standard regressors (LightGBM, RF, XGBoost, etc.) on Sentinel-1 backscatter, time-series indices, Sentinel-2 optical, topographic and temperature features, with IoT capacitance sensor readings serving as the explicit target variable. Reported RMSE and R² values are ordinary cross-validation or hold-out errors against those same sensor observations; no equation, ansatz or uniqueness claim reduces the output to the input by construction. No self-citation chains, fitted-parameter renamings or self-definitional steps appear in the described methodology. The derivation is therefore a conventional supervised-learning pipeline whose central performance claims remain independent of the inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on empirical ML fitting to site-specific in-situ data; no explicit free parameters or invented entities are stated in the abstract beyond standard domain assumptions about SAR-moisture relationships.

axioms (1)
  • domain assumption SAR backscatter, time-series indices, and auxiliary optical/topographic data relate to surface soil moisture in a way that ML models can learn across sediment types
    The retrieval methodology and performance claims depend on this relationship holding for the studied geomaterials and weather conditions.

pith-pipeline@v0.9.1-grok · 5906 in / 1276 out tokens · 43235 ms · 2026-06-25T22:27:56.260245+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

68 extracted references · 16 canonical work pages

  1. [1]

    Hydrology and Earth System Sciences , volume=

    Controls on spatial and temporal variability of soil moisture across a heterogeneous boreal forest landscape , author=. Hydrology and Earth System Sciences , volume=. 2025 , publisher=

    2025

  2. [2]

    2018 , issn =

    Performance assessment of factory and field calibrations for electromagnetic sensors in a loam soil , journal =. 2018 , issn =. doi:https://doi.org/10.1016/j.agwat.2017.10.020 , author =

    work page doi:10.1016/j.agwat.2017.10.020 2018

  3. [3]

    2017 , issn =

    Hydrologic behavior of model slopes with synthetic water repellent soils , journal =. 2017 , issn =. doi:https://doi.org/10.1016/j.jhydrol.2017.09.013 , author =

    work page doi:10.1016/j.jhydrol.2017.09.013 2017

  4. [4]

    2013 , issn =

    Advances in soil moisture retrieval from synthetic aperture radar and hydrological applications , journal =. 2013 , issn =. doi:https://doi.org/10.1016/j.jhydrol.2012.10.044 , author =

    work page doi:10.1016/j.jhydrol.2012.10.044 2013

  5. [5]

    and Bazzi, H

    Baghdadi, N. and Bazzi, H. and El Hajj, M. and Zribi, M. , TITLE =. Remote Sens. , VOLUME =. 2018 , NUMBER =

    2018

  6. [6]

    1999 , issn =

    A Method for Estimating Soil Moisture from ERS Scatterometer and Soil Data , journal =. 1999 , issn =. doi:https://doi.org/10.1016/S0034-4257(99)00036-X , author =

    work page doi:10.1016/s0034-4257(99)00036-x 1999

  7. [7]

    2020 , issn =

    ALOS-2 and Sentinel-1 SAR data sensitivity analysis to surface soil moisture over bare and vegetated agricultural fields , journal =. 2020 , issn =. doi:https://doi.org/10.1016/j.compag.2020.105303 , author =

    work page doi:10.1016/j.compag.2020.105303 2020

  8. [8]

    2021 , issn =

    Sentinel-1 soil moisture at 1 km resolution: a validation study , journal =. 2021 , issn =. doi:https://doi.org/10.1016/j.rse.2021.112554 , author =

    work page doi:10.1016/j.rse.2021.112554 2021

  9. [9]

    , journal=

    Small, D. , journal=. Flattening Gamma: Radiometric Terrain Correction for SAR Imagery , year=

  10. [10]

    Remote Sens

    1-km soil moisture retrieval using multi-temporal dual-channel. Remote Sens. Env. , volume =. 2023 , issn =. doi:https://doi.org/10.1016/j.rse.2022.113334 , author =

    work page doi:10.1016/j.rse.2022.113334 2023

  11. [11]

    and Jagdhuber, T

    Hajnsek, I. and Jagdhuber, T. and Schon, H. and Papathanassiou, K.P. , journal=. Potential of Estimating Soil Moisture Under Vegetation Cover by Means of PolSAR , year=

  12. [12]

    Geological Survey of Finland , title =

  13. [13]

    and Dwyer, Edward and Whelan, Pádraig , TITLE =

    Barrett, Brian W. and Dwyer, Edward and Whelan, Pádraig , TITLE =. Remote Sens. , VOLUME =. 2009 , NUMBER =

    2009

  14. [14]

    2021 , issn =

    Soil moisture retrieval over agricultural fields from L-band multi-incidence and multitemporal PolSAR observations using polarimetric decomposition techniques , journal =. 2021 , issn =. doi:https://doi.org/10.1016/j.rse.2021.112485 , author =

    work page doi:10.1016/j.rse.2021.112485 2021

  15. [15]

    and Parizzi, A

    De Zan, F. and Parizzi, A. and Prats-Iraola, P. and López-Dekker, P. , journal=. A. 2014 , volume=

    2014

  16. [16]

    and Hajnsek, I

    Jagdhuber, T. and Hajnsek, I. and Papathanassiou, K. P. , journal=. An Iterative Generalized Hybrid Decomposition for Soil Moisture Retrieval Under Vegetation Cover Using Fully Polarimetric. 2015 , volume=

    2015

  17. [17]

    Das and Dara Entekhabi and Rowena Lohman and Andreas Colliander and Dharmendra Kumar Pandey and R.K

    Preet Lal and Gurjeet Singh and Narendra N. Das and Dara Entekhabi and Rowena Lohman and Andreas Colliander and Dharmendra Kumar Pandey and R.K. Setia , keywords =. A multi-scale algorithm for the NISAR mission high-resolution soil moisture product , journal =. 2023 , issn =

    2023

  18. [18]

    Baldwin and S

    D. Baldwin and S. Manfreda and K. Keller and E.A.H. Smithwick , keywords =. Predicting root zone soil moisture with soil properties and satellite near-surface moisture data across the conterminous United States , journal =. 2017 , issn =

    2017

  19. [19]

    Hydrology Research , volume=

    Operational readiness of microwave remote sensing of soil moisture for hydrologic applications , author=. Hydrology Research , volume=. 2007 , publisher=

    2007

  20. [20]

    and Batlivala, Percy P

    Ulaby, Fawwaz T. and Batlivala, Percy P. and Dobson, Myron C. , journal=. Microwave Backscatter Dependence on Surface Roughness, Soil Moisture, and Soil Texture: Part I-Bare Soil , year=

  21. [21]

    Machine learning , volume=

    Random forests , author=. Machine learning , volume=. 2001 , publisher=

    2001

  22. [22]

    Science of Remote Sensing , volume=

    Surface soil moisture prediction using multimodal remote sensing data fusion and machine learning algorithms in semi-arid agricultural region , author=. Science of Remote Sensing , volume=. 2025 , publisher=

    2025

  23. [23]

    Sensors , volume=

    Synergetic use of Sentinel-1 and Sentinel-2 data for soil moisture mapping at 100 m resolution , author=. Sensors , volume=. 2017 , publisher=

    2017

  24. [24]

    Advances in Space Research , volume=

    Comparison of three machine learning algorithms for retrieving soil moisture information from Sentinel-1A SAR data in northwest Shandong plain, China , author=. Advances in Space Research , volume=. 2024 , publisher=

    2024

  25. [25]

    Statistics and Computing , year=

    A tutorial on support vector regression , author=. Statistics and Computing , year=

  26. [26]

    Gleason and Jungho Im , keywords =

    Colin J. Gleason and Jungho Im , keywords =. Forest biomass estimation from airborne LiDAR data using machine learning approaches , journal =. 2012 , issn =. doi:https://doi.org/10.1016/j.rse.2012.07.006 , url =

    work page doi:10.1016/j.rse.2012.07.006 2012

  27. [27]

    Tibshirani ,\ 10.1111/j.2517-6161.1996.tb02080.x journal journal J

    Tibshirani, Robert , title =. Journal of the Royal Statistical Society: Series B (Methodological) , volume =. 2018 , month =. doi:10.1111/j.2517-6161.1996.tb02080.x , url =

    work page doi:10.1111/j.2517-6161.1996.tb02080.x 2018

  28. [28]

    ESA Living Planet Symposium , year = 2010, editor =

    Terrain-Corrected Gamma: Improved Thematic Land-Cover Retrieval for SAR with Robust Radiometric Terrain Correction. ESA Living Planet Symposium , year = 2010, editor =

    2010

  29. [29]

    Machine Learning , year=

    Support-Vector Networks , author=. Machine Learning , year=

  30. [30]

    and Smola, Alex , title =

    Vapnik, Vladimir and Golowich, Steven E. and Smola, Alex , title =. Proceedings of the 10th International Conference on Neural Information Processing Systems , pages =. 1996 , publisher =

    1996

  31. [31]

    The Support Vector Method of Function Estimation

    Vapnik, Vladimir. The Support Vector Method of Function Estimation. Nonlinear Modeling: Advanced Black-Box Techniques. 1998. doi:10.1007/978-1-4615-5703-6_3

    work page doi:10.1007/978-1-4615-5703-6_3 1998

  32. [32]

    Steve R. Gunn. Support Vector Machines for Classification and Regression. 1998

    1998

  33. [33]

    and Ulander, Lars M

    Neumann, Maxim and Saatchi, Sassan S. and Ulander, Lars M. H. and Fransson, Johan E. S. , journal=. Assessing Performance of L- and P-Band Polarimetric Interferometric SAR Data in Estimating Boreal Forest Above-Ground Biomass , year=

  34. [34]

    Modeling Aboveground Biomass in Tropical Forests Using Multi-Frequency SAR Data—A Comparison of Methods , year=

    Englhart, Sandra and Keuck, Vanessa and Siegert, Florian , journal=. Modeling Aboveground Biomass in Tropical Forests Using Multi-Frequency SAR Data—A Comparison of Methods , year=

  35. [35]

    European Journal of Remote Sensing , volume =

    Ayoob Karami and Nicolas Baghdadi and Henri Bazzi and Yasser Nasrallah and Mehrez Zribi and Sami Najem and Jean-Pierre Wigneron , title =. European Journal of Remote Sensing , volume =. 2026 , publisher =

    2026

  36. [36]

    , TITLE =

    Lamichhane, Manoj and Mehan, Sushant and Mankin, Kyle R. , TITLE =. Remote Sensing , VOLUME =. 2025 , NUMBER =

    2025

  37. [37]

    and Kumar, Vipin , title =

    Li, Xiang and Nieber, John L. and Kumar, Vipin , title =. Vadose Zone Journal , volume =. doi:https://doi.org/10.1002/vzj2.20361 , year =

    work page doi:10.1002/vzj2.20361

  38. [38]

    Model-based Tensor Decompositions for Geophysical Parameter Retrieval from Multidimensional SAR Data , year=

    Basargin, Nikita and Alonso-González, Alberto and Hajnsek, Irena , journal=. Model-based Tensor Decompositions for Geophysical Parameter Retrieval from Multidimensional SAR Data , year=

  39. [39]

    , journal=

    Zhu, Liujun and Dai, Junjie and Jin, Junliang and Yuan, Shanshui and Xiong, Ziwei and Walker, Jeffrey P. , journal=. Are the Current Expectations for SAR Remote Sensing of Soil Moisture Using Machine Learning Overoptimistic? , year=

  40. [40]

    Sensors , volume=

    Retrieval of surface soil moisture at field scale using Sentinel-1 SAR data , author=. Sensors , volume=. 2025 , publisher=

    2025

  41. [41]

    IGARSS 2025-2025 IEEE International Geoscience and Remote Sensing Symposium , pages=

    Field-scale soil moisture estimated from Sentinel-1 SAR data using a knowledge-guided deep learning approach , author=. IGARSS 2025-2025 IEEE International Geoscience and Remote Sensing Symposium , pages=. 2025 , organization=

    2025

  42. [42]

    Vadose Zone Journal , volume=

    From point to pixel scale: An upscaling approach for in situ soil moisture measurements , author=. Vadose Zone Journal , volume=. 2016 , publisher=

    2016

  43. [43]

    2026 , doi =

    Lems, Johanna and Dorigo, Wouter and Gruber, Alexander , title =. 2026 , doi =

    2026

  44. [44]

    Remote Sensing , volume=

    High spatial and temporal soil moisture retrieval in agricultural areas using multi-orbit and vegetation adapted Sentinel-1 SAR time series , author=. Remote Sensing , volume=. 2023 , publisher=

    2023

  45. [45]

    IEEE Transactions on Geoscience and Remote Sensing , volume=

    Sentinel-1 sensitivity to soil moisture at high incidence angle and the impact on retrieval over seasonal crops , author=. IEEE Transactions on Geoscience and Remote Sensing , volume=. 2020 , publisher=

    2020

  46. [46]

    Advances in neural information processing systems , volume=

    Lightgbm: A highly efficient gradient boosting decision tree , author=. Advances in neural information processing systems , volume=

  47. [47]

    Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining , pages=

    Xgboost: A scalable tree boosting system , author=. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining , pages=

  48. [48]

    Journal of the Indian Society of Remote Sensing , volume=

    Estimation of surface moisture content using Sentinel-1 C-band SAR data through machine learning models , author=. Journal of the Indian Society of Remote Sensing , volume=. 2021 , publisher=

    2021

  49. [49]

    Land , volume=

    Comparative analysis of machine-learning models for soil moisture estimation using high-resolution remote-sensing data , author=. Land , volume=. 2024 , publisher=

    2024

  50. [50]

    the Journal of machine Learning research , volume=

    Scikit-learn: Machine learning in Python , author=. the Journal of machine Learning research , volume=. 2011 , publisher=

    2011

  51. [51]

    Remote Sensing , volume=

    The Influence of Texture on Soil Moisture Modeling for Soils of Diverse Roughness Using Backscattering Coefficient and Polarimetric Decompositions Derived from Sentinel-1 Data , author=. Remote Sensing , volume=. 2025 , publisher=

    2025

  52. [52]

    Remote Sensing , volume=

    Soil texture, soil moisture, and Sentinel-1 backscattering: Towards the retrieval of field-scale soil hydrological properties , author=. Remote Sensing , volume=. 2025 , publisher=

    2025

  53. [53]

    Sentinel-1 Next Generation: Enhanced C-band Data Continuity , year=

    Torres, Ramon and Geudtner, Dirk and Davidson, Malcolm and Bibby, David and Navas-Traver, Ignacio and Garcia Hernandez, Ana Isabel and Laduree, Gregory and Poupaert, Jelle and Cossu, Mario and Touveneau, Marie and Graham, Stefan , booktitle=. Sentinel-1 Next Generation: Enhanced C-band Data Continuity , year=

  54. [54]

    2012 , note =

    GMES Sentinel-1 mission , journal =. 2012 , note =. doi:https://doi.org/10.1016/j.rse.2011.05.028 , author =

    work page doi:10.1016/j.rse.2011.05.028 2012

  55. [55]

    and Bawden, Gerald W

    Rosen, Paul A. and Bawden, Gerald W. and Barela, Phil and Chapman, Bruce and Fattahi, Heresh and Jones, Cathleen E. and Joughin, Ian R. and Lavalle, Marco and Lohman, Rowena B. and Simons, Mark and Siqueira, Paul and Das, Anup and Desai, Nilesh M. and Kumar, Raj and Putrevu, Deepak and Sharma, Rashmi and Shrikant, CV , journal=. The NASA-ISRO SAR Mission:...

  56. [56]

    2021 , issn =

    Soil moisture retrieval from remote sensing measurements: Current knowledge and directions for the future , journal =. 2021 , issn =. doi:https://doi.org/10.1016/j.earscirev.2021.103673 , author =

    work page doi:10.1016/j.earscirev.2021.103673 2021

  57. [57]

    Walker , keywords =

    Mohammad Amin Shahriari and Hossein Aghighi and Mohsen Azadbakht and Davoud Ashourloo and Ali Akbar Matkan and Foad Brakhasi and Jeffrey P. Walker , keywords =. Soil moisture estimation using combined SAR and optical imagery: Application of seasonal machine learning algorithms , journal =. 2025 , issn =. doi:https://doi.org/10.1016/j.asr.2025.01.064 , url =

    work page doi:10.1016/j.asr.2025.01.064 2025

  58. [58]

    The Extractive Industries and Society , volume=

    The role of earth observation technologies in enhancing social acceptance of mining operations , author=. The Extractive Industries and Society , volume=. 2025 , publisher=

    2025

  59. [59]

    Remote Sensing of Environment , volume =

    Soil moisture retrieval from Sentinel-1: Lessons learned after more than a decade in orbit , author =. Remote Sensing of Environment , volume =. 2026 , doi =

    2026

  60. [60]

    and Dasgupta, Antara and Rahmati, Mehdi and Jagdhuber, Thomas , journal =

    Montzka, Carsten and Brocca, Luca and Chen, Hao and Das, Narendra N. and Dasgupta, Antara and Rahmati, Mehdi and Jagdhuber, Thomas , journal =. 2026 , doi =

    2026

  61. [61]

    Intercomparison of very high-resolution surface soil moisture products over

    Ouaadi, Nadia and Jarlan, Lionel and Le Page, Michel and Zribi, Mehrez and Paolini, Giovani and Ait Hssaine, Bouchra and Escorihuela, Maria Jose and Fanise, Pascal and Merlin, Olivier and Baghdadi, Nicolas and Boone, Aaron , journal =. Intercomparison of very high-resolution surface soil moisture products over. 2024 , doi =

    2024

  62. [62]

    International Journal of Applied Earth Observation and Geoinformation , volume =

    High-resolution surface soil moisture retrieval: A hybrid machine learning framework integrating change detection and downscaling for precision water management , author =. International Journal of Applied Earth Observation and Geoinformation , volume =. 2025 , doi =

    2025

  63. [63]

    CATENA , volume =

    Comparison of bagging, boosting and stacking algorithms for surface soil moisture mapping using optical-thermal-microwave remote sensing synergies , author =. CATENA , volume =. 2022 , doi =

    2022

  64. [64]

    and Gupta, Dileep Kumar and Kumar, Pradeep and Prasad, Rajendra and Pandey, Dharmendra Kumar and Das, Anup Kumar and Gupta, Manika , journal =

    Chaudhary, Sumit Kumar and Srivastava, Prashant K. and Gupta, Dileep Kumar and Kumar, Pradeep and Prasad, Rajendra and Pandey, Dharmendra Kumar and Das, Anup Kumar and Gupta, Manika , journal =. Machine learning algorithms for soil moisture estimation using. 2022 , doi =

    2022

  65. [65]

    Very High Spatial Resolution Soil Moisture Observation of Heterogeneous Subarctic Catchment Using Nonlocal Averaging and Multitemporal

    Manninen, Terhikki and J. Very High Spatial Resolution Soil Moisture Observation of Heterogeneous Subarctic Catchment Using Nonlocal Averaging and Multitemporal. IEEE Transactions on Geoscience and Remote Sensing , volume =. 2022 , doi =

    2022

  66. [66]

    Scientific Reports , volume =

    Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images , author =. Scientific Reports , volume =. 2023 , doi =

    2023

  67. [67]

    and Notarnicola, C

    Pasolli, L. and Notarnicola, C. and Bruzzone, L. and Bertoldi, G. and Della Chiesa, S. and Hell, V. and Niedrist, G. and Tappeiner, U. and Zebisch, M. and Del Frate, F. and Vaglio Laurin, G. , title =. Applied and Environmental Soil Science , volume =. doi:https://doi.org/10.1155/2011/175473 , url =. https://onlinelibrary.wiley.com/doi/pdf/10.1155/2011/17...

    work page doi:10.1155/2011/175473 2011

  68. [68]

    Remote Sensing , VOLUME =

    El Hajj, Mohammad and Baghdadi, Nicolas and Zribi, Mehrez and Bazzi, Hassan , TITLE =. Remote Sensing , VOLUME =. 2017 , NUMBER =

    2017