Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2

Bousbih, Safa; Zribi, Mehrez; Pelletier, Charlotte; Gorrab, Azza; Lili-Chabaane, Zohra; Baghdadi, Nicolas; Aïssa, Nadhira Ben; Mougenot, Bernard

doi:10.3390/rs11131520

Cited by 85 publications

(43 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding the specific influence of soil surface roughness, these trends were highlighted from the synergy between S2 and S1, and particularly, S1-derived surface roughness that was previously assessed at several dates [41]. Bousbih et al [52] have also recently taken advantage of S2/S1 synergy for improving the prediction of soil clay texture, but in order to better target the clayey soils expected to slow drying, their strategy opted for the most humid periods between September and December; they, therefore, used S1-derived soil moisture instead of roughness.…”

Section: Optimal Dates For Predicting Soc From S2 Images and The Benementioning

confidence: 93%

The Impact of Acquisition Date on the Prediction Performance of Topsoil Organic Carbon from Sentinel-2 for Croplands

et al. 2019

Self Cite

View full text Add to dashboard Cite

The spatial assessment of soil organic carbon (SOC) is a major environmental challenge, notably for evaluating soil carbon stocks. Recent works have shown the capability of Sentinel-2 optical data to predict SOC content over temperate agroecosystems characterized by annual crops, using a single acquisition date. Considering a Sentinel-2 time series, this work intends to analyze the impact of acquisition date, and related weather and soil surface conditions on the prediction performance of topsoil SOC content (plough layer). A Sentinel-2 time-series was gathered, comprised of the dates corresponding to both the maximum of bare soil coverage and minimum of cloud coverage. Cross-validated partial least squares regression (PLSR) models were constructed between soil reflectance image spectra, and SOC content analyzed from 329 top soil samples collected over the study area. Cross-validation R2 ranged from 0.005 to 0.58, root mean square error from 5.86 to 3.02 g·kg−1 and residual prediction deviation values from 1.0 to 1.5 (without unit), according to date. The main factors influencing these differences were soil roughness, in conjunction with soil moisture, and the cloud and cloud shadow cover of the entire tile. The best performing dates were spring dates characterized by both lowest soil surface roughness and moisture content. Normalized difference vegetation index (NDVI) values below 0.35 did not influence prediction performance. This consolidates the previous results obtained during single date acquisitions and offers wider perspectives for the further use of Sentinel-2 into multidate mosaics for digital soil mapping.

show abstract

Section: Optimal Dates For Predicting Soc From S2 Images and The Benementioning

confidence: 93%

The Impact of Acquisition Date on the Prediction Performance of Topsoil Organic Carbon from Sentinel-2 for Croplands

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, the clay index was moderately relevant for predicting all PSFs, while NDVI was moderately relevant for predicting the clay and silt fractions (Table 4). With respect to the clay index of Sentinel-2, there was a negative relationship with soil clay content [77]. The soil texture mapping using Sentinel-2 data performance had a good discrimination for extremely different soil texture classes (e.g., sandy loam versus clay), whereas neighboring soil texture classes (e.g., sandy clay loam and clay class) had high uncertainty [75].…”

Section: Environmental Covariatesmentioning

confidence: 95%

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

et al. 2021

View full text Add to dashboard Cite

Soil texture and particle size fractions (PSFs) are a critical characteristic of soil that influences most physical, chemical, and biological properties of soil; furthermore, reliable spatial predictions of PSFs are crucial for agro-ecological modeling. Here, series of hybridized artificial neural network (ANN) models with bio-inspired metaheuristic optimization algorithms such as a genetic algorithm (GA-ANN), particle swarm optimization (PSO-ANN), bat (BAT-ANN), and monarch butterfly optimization (MBO-ANN) algorithms, were built for predicting PSFs for the Mazandaran Province of northern Iran. In total, 1595 composite surficial soil samples were collected, and 64 environmental covariates derived from terrain, climatic, remotely sensed, and categorical datasets were used as predictors. Models were tested using a repeated 10-fold nested cross-validation approach. The results indicate that the hybridized ANN methods were far superior to the reference approach using ANN with a backpropagation training algorithm (BP-ANN). Furthermore, the MBO-ANN approach was consistently determined to be the best approach and yielded the lowest error and uncertainty. The MBO-ANN model improved the predictions in terms of RMSE by 20% for clay, 10% for silt, and 24% for sand when compared to BP-ANN. The physiographical units, soil types, geology maps, rainfall, and temperature were the most important predictors of PSFs, followed by the terrain and remotely sensed data. This study demonstrates the effectiveness of bio-inspired algorithms for improving ANN models. The outputs of this study will support and inform sustainable soil management practices, agro-ecological modeling, and hydrological modeling for the Mazandaran Province of Iran.

show abstract

“…Sentinel-2 collects multispectral optical imagery across the VNIR and SWIR range at moderate spatial resolution (10 to 20 m) and high temporal resolution (2 to 5 days). Sentinel-2 has been used with other remote sensing data (e.g., Sentinel-1, MODIS, Landsat) for predicting soil texture (Bousbih et al, 2019;Loiseau et al, 2019) and other properties (bulk density, pH, carbon and soil depth) (Poggio & Gimona, 2017). Vaudour, Gomez, Fouad, and Lagacherie (2019) investigated the use of Sentinel-2 data to predict multiple soil properties, including texture, organic carbon, iron, pH, calcium carbonate and cation exchange capacity.…”

Section: Comparison Of Dem Sentinel-1 and 2 And Hyperspectral Data For Soil Mappingmentioning

confidence: 99%

Synergistic use of hyperspectral imagery, Sentinel‐1 and LiDAR improves mapping of soil physical and geochemical properties at the farm‐scale

Zhang

Hartemink

Huang

et al. 2021

European J Soil Science

View full text Add to dashboard Cite

Airborne imaging spectroscopy data provide soil and vegetation information over relatively large areas at high spatial resolutions (<5 m). We combined airborne hyperspectral data with space-borne data to map soil properties and investigate the contributions of the different sensor data to the mapping accuracy. The study was conducted on a 330-ha farm in south-central Wisconsin, USA, where soils are relatively young and soil variation is high. Seventy-three soil samples (0-10 cm depth) were taken from cropped fields before planting. The soil data were used with remote sensing data for mapping clay, silt, sand, total carbon (TC), Mg, Al, Si, Fe, Ca, Ti, Mn and Zr. Three types of variables were compared: (a) DEM + Sentinel-1 & 2, as these are easy-to-obtain, (b) hyperspectral data with high-spatial resolution, and (c) hyperspectral data + DEM + Sentinel-1, to evaluate if the prediction can be improved by combining hyperspectral data with DEM + Sentinel-1, and if combining DEM + Sentinel-1 with hyperspectral data had higher prediction accuracy than combination with Sentinel-2 data. The partial least square regression (PLSR) model was used for establishing relationships between soil and remote sensing data. It was found that airborne hyperspectral imaging can accurately map the spatial distributions of soil clay content, Si and Fe concentrations. Combining hyperspectral data with DEM and Sentinel-1 improved the performance of models for mapping a range of soil properties (e.g., clay, silt, sand, Al, Ti, Mn and Zr). Total C, Mg and Ca concentrations cannot be predicted from the combination of hyperspectral data, Sentinel-1 and terrain attributes. In a highly heterogeneous landscape, surface soil properties can be accurately mapped combining LiDAR DEM, Sentinel-1 and hyperspectral data. Highlights• Airborne imaging spectroscopy, DEM and Sentinel-1 were used to map surface soil properties.• Hyperspectral data can accurately map clay, Si and Fe.• Combining hyperspectral data with DEM, Sentinel-1 improved prediction accuracy of several soil properties.

show abstract

Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2

Cited by 85 publications

References 56 publications

The Impact of Acquisition Date on the Prediction Performance of Topsoil Organic Carbon from Sentinel-2 for Croplands

The Impact of Acquisition Date on the Prediction Performance of Topsoil Organic Carbon from Sentinel-2 for Croplands

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

Synergistic use of hyperspectral imagery, Sentinel‐1 and LiDAR improves mapping of soil physical and geochemical properties at the farm‐scale

Contact Info

Product

Resources

About