Modeling soil organic matter (SOM) from satellite data using VISNIR-SWIR spectroscopy and PLS regression with step-down variable selection algorithm: case study of Campos Amazonicos National Park savanna enclave, Brazil

Rosero‐Vlasova, Olga A.; Alves, Daniel Borini; Vlassova, Lidia; Pérez‐Cabello, Fernando; Llovería, Raquel Montorio

doi:10.1117/12.2278701

Cited by 4 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The S2A data (R = 0.68, RMSE = 0.26%) showed significantly better results in terms of SOC prediction 2 than L8 (R = 0.65, RMSE = 0.28%). These results are consistent with the studies of Castaldi et al (2019) and Rosero-Vlasova et al (2017). Moreover, the generated SOC maps were validated using similar reference field observations (Leave-one-out).…”

Section: Soc Prediction Models -Performancesupporting

confidence: 89%

Estimation of soil organic carbon in agricultural fields: A remote sensing approach

Madugundu¹,

Al‐Gaadi²,

Tola³

et al. 2022

JEB

View full text Add to dashboard Cite

Aim: In view of the importance of Soil Organic Carbon (SOC) in agricultural management, a study was conducted to develop a digital SOC map using remotely sensed spectral indices. The present study was conducted on the Tawdeehiya Farms, located in the central region of Saudi Arabia between Al-Kharj and Haradh cities. Methodology: Landsat-8 (L8) and Sentinel-2 (S2A) satellite images were used for the characterization of SOC stocks in the topsoil layer (0-10 cm) of the experimental fields. Soil samples were randomly collected from six (50 ha each) agricultural fields and analyzed in the laboratory for SOC (SOCA) following Walkley and Black method. While, vegetation indices (VI), such as the Normalized Difference Vegetation Index (NDVI), NDVIRedEdge, Enhanced Vegetation Index (EVI), Bare Soil Index (BSI), and Reduced Simple Ratio (RSR) were computed and subsequently used for the development of SOC prediction models. Results: Univariate linear regression technique was employed for the recognition of a suitable band/VI for SOC (SOCP) mapping. The SWIR-1 band of both L8 (R2 = 0.86) and S2A (R2 = 0.77) data was promising for predicting SOC with 16% (S2A) and 18% (L8) of BIAS. Interpretation: The NDVI and BSI (for L8 data) and BSI and RSR (for S2A data) were found most suitable VI in the prediction of SOC. The R2 values of linear regression models were 0.68 (BSI) and 0.78 (RSR), indicating that nearly 68% and 78% of the SOC could be predicted through L8 and S2A datasets, respectively.

show abstract

Section: Soc Prediction Models -Performancesupporting

confidence: 89%

Estimation of soil organic carbon in agricultural fields: A remote sensing approach

Madugundu¹,

Al‐Gaadi²,

Tola³

et al. 2022

JEB

View full text Add to dashboard Cite

show abstract

“…On the whole, validation results were similar for all the methods. They compare well to the best achievements in modelling of the same soil characteristics reported in previous research (Conforti et al, ; Demattê et al, ; Mouazen et al, ; Rosero‐Vlasova et al, ). However, the important difference lies in the structure of the models created by different algorithms evident in the number of predictors in models developed using the three compared methods.…”

Section: Resultsmentioning

confidence: 99%

“…Modelling of SOM content and texture fractions is based on 70 preselected spectral bands (11 bands in VIS, 18 bands in NIR, and 48 bands in SWIR spectral regions). The importance of this set of wavelengths for soil property detection was previously reported in multiple studies (Ben‐Dor, Heller, & Chudnovsky, ; Demattê et al, ; Demattê & da Silva Terra, ; Melendez‐Pastor, Navarro‐Pedreño, Gómez, & Koch, ; Rosero‐Vlasova, Borini Alves, Vlassova, Perez‐Cabello, & Montorio Lloveria, ).…”

Section: Methodsmentioning

confidence: 99%

Soil organic matter and texture estimation from visible–near infrared–shortwave infrared spectra in areas of land cover changes using correlated component regression

et al. 2019

Self Cite

View full text Add to dashboard Cite

Land use changes due to natural and human‐related factors, which include wildfires and crop abandonment, are among the most important drivers of soil degradation and demand regular monitoring. Proximal soil sensing in visible–near infrared–shortwave infrared spectral regions could offer a solution. However, to become operational, optimal combination of data and technique has to be defined. Thus, the purpose of this study was (a) to predict the soil organic matter (SOM) content and soil texture in areas of wildfire burns and crop abandonment in Aragón Province, Northern Spain, from their laboratory reflectance spectra using novel correlated components regression with a step‐down variable selection algorithm (CCR‐SD) and (b) to compare the CCR‐SD and the partial least squares regression (PLSR) methods. The results obtained by the tested methods were similar. CCR‐SD models showed high predictive capacity with coefficients of determination (R2) in the range of 0.80–0.86 and 0.70–0.87 for calibration and validation data sets, respectively, and the highest R2 value was attained in the SOM estimation. Moreover, the CCR‐SD models stand out for the superior accuracy–parsimony relationship: the number of predictors varied from 16 (silt models) to 49 (SOM models). On average, the CCR‐SD calibrations needed less than a half of the predictors employed in PLSR models. This research confirmed that CCR‐SD can be used for monitoring SOM content and texture of soils from visible–near infrared–shortwave infrared spectra in the study area and, probably, in other areas of land use/land cover change and that CCR‐SD can create highly parsimonious models that achieve results comparable with the commonly used PLSR method.

show abstract

Sentinel-2 Satellite Imagery for Retrieving and Mapping Soil Properties Using Machine Learning

Amin,

Abdelfattah,

Mohamed

et al. 2023

Springer Proceedings in Earth and Environmental Sciences

View full text Add to dashboard Cite

Modeling soil organic matter (SOM) from satellite data using VISNIR-SWIR spectroscopy and PLS regression with step-down variable selection algorithm: case study of Campos Amazonicos National Park savanna enclave, Brazil

Cited by 4 publications

References 13 publications

Estimation of soil organic carbon in agricultural fields: A remote sensing approach

Estimation of soil organic carbon in agricultural fields: A remote sensing approach

Soil organic matter and texture estimation from visible–near infrared–shortwave infrared spectra in areas of land cover changes using correlated component regression

Sentinel-2 Satellite Imagery for Retrieving and Mapping Soil Properties Using Machine Learning

Contact Info

Product

Resources

About