Hierarchical clustering of Sentinel-1 SAR data for soil moisture estimation at the field scale
Bibliographic record
Abstract
Superficial soil moisture is a key hydrological variable playing a main role in the fluxes of water and heat between land and atmosphere. Its spatial and temporal variations are indeed crucial for applications such as environmental modelling and agricultural management. Soil moisture direct measurements lack spatial representativeness, while soil moisture spatialized information could be derived from satellite data acquired by active microwave sensors. In recent years, missions such as ESA’s (European Space Agency) Sentinel-1 SAR (Synthetic Aperture Radar) mission has provided open data at high resolution (up to 20 m) and temporal frequency (6 days at the equator latitudes before December 2021).In the proposed work, high resolution data of Sentinel-1 are analyzed on an agricultural area at a resolution of 20 m over a 4 year period. In particular, it is proposed a hierarchical approach for detecting time and space domains where coherently apply a Change Detection method for retrieving soil moisture from the co-polarized band of Sentinel-1 data. The study is conducted at the field scale. Given the agricultural land use of the study area, the total SAR backscattered signal is modelled as the sum of vegetation and attenuated soil contributions.At first, a classification for masking out the sub-areas dominated by a volumetric response due to vegetation is performed. For doing this, the adaptive thresholding method proposed by Satalino et al., 2014 [1] is performed on proper SAR parameters, such as the VH band, the RVI (Radar Vegetation Index) adapted to Sentinel-1 data [2], and the cross-polarized Interferometric Coherence. The resulting classifications derived from the different parameters are then compared. When working on an agricultural area at the resolution of 20 m, the effects of the soil roughness changes on the backscattering coefficient could not be neglected. For considering them, since no soil roughness data are available on the study area, a time series analysis for detecting steep changes in the co-polarized band is performed. By doing this, it is expected to detect temporal clusters in which no soil roughness variations occur, and thus where a CD method can be applied. The results of the latter classification may be compared with an optical roughness index.REFERENCES[1] G. Satalino, A. Balenzano, F. Mattia and M. W. J. Davidson, "C-Band SAR Data for Mapping Crops Dominated by Surface or Volume Scattering," in IEEE Geoscience and Remote Sensing Letters, vol. 11, no. 2, pp. 384-388, Feb. 2014, doi: 10.1109/LGRS.2013.2263034.[2] M. Trudel, F. Charbonneau, R. Leconte, “Using RADARSAT-2 polarimetric and ENVISAT-ASAR dual-polarization data for estimating soil moisture over agricultural fields”. Canadian Journal of Remote Sensing 2012, 38, 514–527.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".