Copernicus Sentinel-2 Calibration and Validation

Szantoi, Zoltan; Strobl, Peter

doi:10.1080/22797254.2019.1582840

Cited by 38 publications

(28 citation statements)

References 8 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sentinel-2B level-2A product provides geometric and radiometrically corrected images. The data is delivered as Bottom-Of-Atmosphere (BOA) reflectance images converted from the level-1C Top-Of-Atmosphere (TOA) reflectance (Szantoi and Strobl 2019). Its application was tested by Vuolo et al (2016) and used by different studies (e.g., Arogoundade et al 2020;Ng et al 2018) in the areas of invasive species distribution.…”

Section: Satellite Image Processing and Selection Of Variablesmentioning

confidence: 99%

Species Distribution Modelling performance and its implication for Sentinel-2-based prediction of invasive Prosopis juliflora in lower Awash River basin, Ethiopia

2021

View full text Add to dashboard Cite

Background Species Distribution Modelling (SDM) coupled with freely available multispectral imagery from Sentinel-2 (S2) satellite provides an immense contribution in monitoring invasive species. However, attempts to evaluate the performances of SDMs using S2 spectral bands and S2 Radiometric Indices (S2-RIs) and biophysical variables, in particular, were limited. Hence, this study aimed at evaluating the performance of six commonly used SDMs and one ensemble model for S2-based variables in modelling the current distribution of Prosopis juliflora in the lower Awash River basin, Ethiopia. Thirty-five variables were computed from Sentinel-2B level-2A, and out of the variables, twelve significant variables were selected using Variable Inflation Factor (VIF). A total of 680 presence and absence data were collected to train and validate variables using the tenfold bootstrap replication approach in the R software “sdm” package. The performance of the models was evaluated using sensitivity, specificity, True Skill Statistics (TSS), kappa coefficient, area under the curve (AUC), and correlation. Results Our findings demonstrated that except bioclim all machine learning and regression models provided successful prediction. Among the tested models, Random Forest (RF) performed better with 93% TSS and 99% AUC followed by Boosted Regression Trees (BRT), ensemble, Generalized Additive Model (GAM), Support Vector Machine (SVM), and Generalized Linear Model (GLM) in decreasing order. The relative influence of vegetation indices was the highest followed by soil indices, biophysical variables, and water indices in decreasing order. According to RF prediction, 16.14% (1553.5 km2) of the study area was invaded by the alien species. Conclusions Our results highlighted that S2-RIs and biophysical variables combined with machine learning and regression models have a higher capacity to model invasive species distribution. Besides, the use of machine learning algorithms such as RF algorithm is highly essential for remote sensing-based invasive SDM.

show abstract

Section: Satellite Image Processing and Selection Of Variablesmentioning

confidence: 99%

Species Distribution Modelling performance and its implication for Sentinel-2-based prediction of invasive Prosopis juliflora in lower Awash River basin, Ethiopia

2021

View full text Add to dashboard Cite

show abstract

“…Satellite remote sensing (RS) helps in the mapping of current crop status and the assessment of biophysical parameters. Currently, RS data are publicly accessible due to the availability of an unprecedented amount of Free Sentinel data from the Copernicus Program, established by the European Space Agency [1]. Constellations of the Sentinel-2 satellites (2A and 2B) can be also used for precision farming applications [2].…”

Section: Introductionmentioning

confidence: 99%

Within-Field Relationships between Satellite-Derived Vegetation Indices, Grain Yield and Spike Number of Winter Wheat and Triticale

et al. 2020

View full text Add to dashboard Cite

The aims of this study were to: (i) evaluate the relationships between vegetation indices (VIs) derived from Sentinel-2 imagery and grain yield (GY) and the number of spikes per square meter (SN) of winter wheat and triticale; (ii) determine the dates and plant growth stages when the above relationships were the strongest at individual field scale, thus allowing for accurate yield prediction. Observations of GY and SN were performed at harvest on six fields (three locations in two seasons: 2017 and 2018) in three regions of Poland, i.e., northeastern (A—Brożówka), central (B—Zdziechów) and southeastern Poland (C—Kryłów). Vegetation indices (Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), modified SAVI (mSAVI), modified SAVI 2 (mSAVI2), Infrared Percentage Vegetation Index (IPVI), Global Environmental Monitoring Index (GEMI), and Ratio Vegetation Index (RVI)) calculated for sampling points from mid-March until mid-July, covering within-field soil and topographical variability, were included in the analysis. Depending on the location, the highest correlation coefficients (of about 0.6–0.9) for most of VIs with GY and SN were obtained about 4–6 weeks before harvest (from the beginning of shooting to milk maturity). Therefore, satellite-derived VIs are useful for the prediction of within-field cereal GY as well as SN variability. Information on GY, predicted together with the results for soil nutrient availability, is the basis for the formulation of variable fertilize rates in precision agriculture. All examined VIs were similarly correlated with GY and SN via the commonly used NDVI. The increase in NDVI by 0.1 unit was related to an average increase in GY by about 2 t ha−1.

show abstract

“…The Sentinels currently produce about 25 TByte of observation data each day, disseminated through ESA’s primary distribution channels (i.e., the Sentinel Data Hub) [ https://scihub.copernicus.eu/dhus/ ]. For Sentinel-2AB, which likely has the highest relevance for LC mapping applications, routine production of global surface reflectance (L2A) data began in early 2019 ( Szantoi and Strobl, 2019 ). The global Landsat archive holds more than 6 M unique scenes that provide more than 40 years of data, and higher-level science products such as surface reflectance are available through on-demand interfaces ( Wulder et al, 2019 ).…”

Section: The Current State Of Eo Data Repositories Platforms and Resmentioning

confidence: 99%

Addressing the need for improved land cover map products for policy support

Szantoi

Geller

Tsendbazar

et al. 2020

Environmental Science & Policy

Self Cite

View full text Add to dashboard Cite

Highlights Despite the widespread importance of land cover products, current production approaches leave many end users unsatisfied. Frequent, global coverage of satellite imagery is now available, enabling new approaches for land cover product generation. New approaches and land cover products can better serve end user needs. A dynamic, automated land cover mapping system is proposed, with challenges outlined and their solutions proposed. Realization of the concept will require additional government support.

show abstract

Copernicus Sentinel-2 Calibration and Validation

Cited by 38 publications

References 8 publications

Species Distribution Modelling performance and its implication for Sentinel-2-based prediction of invasive Prosopis juliflora in lower Awash River basin, Ethiopia

Species Distribution Modelling performance and its implication for Sentinel-2-based prediction of invasive Prosopis juliflora in lower Awash River basin, Ethiopia

Within-Field Relationships between Satellite-Derived Vegetation Indices, Grain Yield and Spike Number of Winter Wheat and Triticale

Addressing the need for improved land cover map products for policy support

Contact Info

Product

Resources

About