Soil Moisture in the Biebrza Wetlands Retrieved from Sentinel-1 Imagery

Dąbrowska-Zielińska, K.; Musiał, Jan; Malińska, Alicja; Budzynska, Maria; Gurdak, Radosław; Kiryla, Wojciech; Bartold, Maciej; Grzybowski, Patryk

doi:10.3390/rs10121979

Cited by 57 publications

(44 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, an increase in moisture content of approximately 5% generates an increase in σ • vv of approximately 1.15 dB and only 0.55 dB in σ • vh . Overall, the results obtained over the experimental period, including all soil moisture data measured, are consistent with the radar sensitivity over bare soils pointed out by several previous studies in the case of data acquired in C-band [70,71,[73][74][75][76], and confirm that the VV polarization is more suitable for quantifying the soil contribution. By contrast, the VH has been shown to be more related to the vegetation contribution to the radar backscatter since VH is more sensitive to the vegetation volume scattering mechanism, due to the depolarization effect by vegetation-volume-scattering, which mainly depends on the vegetation characteristics [73,[77][78][79].…”

Section: Relation Between Radar Backscattering Coefficient and Soil Msupporting

confidence: 90%

Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data

et al. 2019

View full text Add to dashboard Cite

The main objective of this work was to retrieve surface soil moisture (SSM) by using scattering models and a support vector machine (SVM) technique driven by backscattering coefficients obtained from Sentinel-1 satellite images acquired over bare agricultural soil in the Tensfit basin of Morocco. Two backscattering models were selected in this study due to their wide use in inversion procedures: the theoretical integral equation model (IEM) and the semi-empirical model (Oh). To this end, the sensitivity of the SAR backscattering coefficients at V V ( σ v v ∘ ) and V H ( σ v h ∘ ) polarizations to in situ soil moisture data were analyzed first. As expected, the results showed that over bare soil the σ v v ∘ was well correlated with SSM compared to the σ v h ∘ , which showed more dispersion with correlation coefficients values (r) of about 0.84 and 0.61 for the V V and V H polarizations, respectively. Afterwards, these values of σ v v ∘ were compared to those simulated by the backscatter models. It was found that IEM driven by the measured length correlation L slightly underestimated SAR backscatter coefficients compared to the Oh model with a bias of about − 0.7 dB and − 1.2 dB and a root mean square (RMSE) of about 1.1 dB and 1.5 dB for Oh and IEM models, respectively. However, the use of an optimal value of L significantly improved the bias of IEM, which became near to zero, and the RMSE decreased to 0.9 dB. Then, a classical inversion approach of σ v v ∘ observations based on backscattering model is compared to a data driven retrieval technic (SVM). By comparing the retrieved soil moisture against ground truth measurements, it was found that results of SVM were very encouraging and were close to those obtained by IEM model. The bias and RMSE were about 0.28 vol.% and 2.77 vol.% and − 0.13 vol.% and 2.71 vol.% for SVM and IEM, respectively. However, by taking into account the difficultly of obtaining roughness parameter at large scale, it was concluded that SVM is still a useful tool to retrieve soil moisture, and therefore, can be fairly used to generate maps at such scales.

show abstract

Section: Relation Between Radar Backscattering Coefficient and Soil Msupporting

confidence: 90%

Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Considering inference complexity of the network, T FP mul = 4 × 20 × 25 × 25 × 9 = 450K, T FP add1 = 4 × 20 × 25 × 25 = 50K, and T FP add2 = 4 × 20 × 25 × 25 × 8 = 400K based on Equations (4)- (6). Consequently, the total number of operations would equal to 900K which requires only 0.0009 GFlops computing sources and shows the suitability of such compact networks for real-time applications.…”

Section: Of 29mentioning

confidence: 99%

Dual and Single Polarized SAR Image Classification Using Compact Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

Accurate land use/land cover classification of synthetic aperture radar (SAR) images plays an important role in environmental, economic, and nature related research areas and applications. When fully polarimetric SAR data is not available, single-or dual-polarization SAR data can also be used whilst posing certain difficulties. For instance, traditional Machine Learning (ML) methods generally focus on finding more discriminative features to overcome the lack of information due to single-or dual-polarimetry. Beside conventional ML approaches, studies proposing deep convolutional neural networks (CNNs) come with limitations and drawbacks such as requirements of massive amounts of data for training and special hardware for implementing complex deep networks. In this study, we propose a systematic approach based on sliding-window classification with compact and adaptive CNNs that can overcome such drawbacks whilst achieving state-of-the-art performance levels for land use/land cover classification. The proposed approach voids the need for feature extraction and selection processes entirely, and perform classification directly over SAR intensity data. Furthermore, unlike deep CNNs, the proposed approach requires neither a dedicated hardware nor a large amount of data with ground-truth labels. The proposed systematic approach is designed to achieve maximum classification accuracy on single and dual-polarized intensity data with minimum human interaction. Moreover, due to its compact configuration, the proposed approach can process such small patches which is not possible with deep learning solutions. This ability significantly improves the details in segmentation masks. An extensive set of experiments over two benchmark SAR datasets confirms the superior classification performance and efficient computational complexity of the proposed approach compared to the competing methods.retrieval with Sentinel-1 [6], TerraSAR-X, and COSMO-Skymed [7]. A comprehensive list of fields and applications of SAR is available in [8].Ecological and socioeconomic applications greatly benefit from LU/LC classification, making SAR image classification the primary task. For example, forest biomass analysis investigated in [9] provides vegetation ecosystem analysis in Mediterranean areas. Further studies [10,11] focus on the relation between vegetation type and urban climate by questioning how vegetation types affect the temperature. Moreover, Mennis [12] analyzes the relationship between socioeconomic status and vegetation intensity and reveals that higher vegetation intensity is associated with socioeconomic advantage. However, accurate LU/LC classification is a challenging task especially for conventional machine learning methods due to several reasons: (1) existing speckle noise in SAR data, (2) requirement of pre-processing, i.e., feature extraction is especially needed for single-and dual-polarimetric cases to compensate for the lack of full polarization information, and finally, (3) the large-scale nature of SAR data.Nevertheless, there...

show abstract

“…Sensors operating in the optical and infrared spectrum are capable of detecting spectral changes in Sphagnum mosses, which are caused by different moisture states and water levels [22][23][24]. In SAR applications, soil moisture has been estimated from σ 0 [15,17,[25][26][27][28] or polarimetry [27], while coherence data has been used to derive surface water levels [28]. In particular, previous studies have shown promising correlations between σ 0 and WTD in peatlands, but they have either focussed on forested peatlands with limited in situ data for WTD [28] or on large-scale applications, which did not allow conclusions to be drawn on the effect of soil properties and vegetation [29].…”

Section: Introductionmentioning

confidence: 99%

“…They carry a SAR which uses C-band radar with a frequency of 5.4 GHz in dual polarization [30]. Sentinel-1 data has been recently applied for soil moisture estimation in mineral soils [18] as well as in organic soils [25]. The high spatial resolution (posted raster cell size ~10 m) enables new approaches to distinguish even small and narrow parcels of land, as is typical for cultivated peatlands [31].…”

Section: Introductionmentioning

confidence: 99%

On the Potential of Sentinel-1 for High Resolution Monitoring of Water Table Dynamics in Grasslands on Organic Soils

Asmuß¹,

Bechtold

Tiemeyer³

2019

Remote Sensing

View full text Add to dashboard Cite

For soils with shallow groundwater and high organic carbon content, water table depth (WTD) is a key parameter to describe their hydrologic state and to estimate greenhouse gas emissions (GHG). Since the microwave backscatter coefficient (σ0) is sensitive to soil moisture, the application of Sentinel-1 satellite data might support the monitoring of these climate-relevant soils at high spatial resolution (~100 m) by detecting spatial and temporal changes in local field and water management. Despite the low penetration depth of the C-band, σ0 is influenced by shallow WTD fluctuations via the soil hydraulic connection between the water table and surface soil. Here, we analyzed σ0 at 60 monitoring wells in a drained temperate peatland with degraded organic soils used as extensive grassland. We evaluated temporal Spearman correlation coefficients between σ0 and WTD considering the soil and vegetation information. To account for the effects of seasonal vegetation changes, we used the cross-over (incidence) angle method. Climatologies of the slope of the incidence angle dependency derived from two years of Sentinel-1 data and their application to the cross-over angle method did improve correlations, though the effect was minor. Overall, averaged over all sites, a temporal Spearman correlation coefficient of 0.45 (±0.17) was obtained. The loss of correlation during summer (higher vegetation, deeper WTD) and the effects of cuts and grazing are discussed. The site-specific general wetness level, described by the mean WTD of each site was shown to be a major factor controlling the strength of the correlation. Mean WTD deeper than about −0.60 m lowered the correlations across sites, which might indicate an important limit of the application.

show abstract

Soil Moisture in the Biebrza Wetlands Retrieved from Sentinel-1 Imagery

Cited by 57 publications

References 30 publications

Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data

Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data

Dual and Single Polarized SAR Image Classification Using Compact Convolutional Neural Networks

On the Potential of Sentinel-1 for High Resolution Monitoring of Water Table Dynamics in Grasslands on Organic Soils

Contact Info

Product

Resources

About