Sentinel-2 is intended to improve vegetation assessment at local to global scales. Today, estimation of leaf nitrogen (N) as an indicator of rangeland quality is possible using hyperspectral systems. However, few studies based on commercial imageries have shown a potential of the red-edge band to accurately predict leaf N at the broad landscape scale. We intend to investigate the utility of Sentinel-2 for estimating leaf N concentration in the African savanna. Grass canopy reflectance was measured using the analytical spectral device (ASD) in concert with leaf sample collections for leaf N chemical analysis. ASD reflectance data were resampled to the spectral bands of Sentinel-2 using published spectral response functions. Random forest (RF), partial least square regression (PLSR), and stepwise multiple linear regression (SMLR) were used to predict leaf N using all 13 bands. Using leave-one-out cross validation, the RF model explained 90% of leaf N variation, with a root mean square error of 0.04 (6% of the mean), which is higher than that of PLSR and SMLR. Using RF, spectral bands centered at 705 nm (red edge) and two shortwave infrared bands centered at 2190 and 1610 nm were found to be the most important bands in predicting leaf N.
The European Space Agency (ESA) has embarked on the development of the Sentinel constellation. Sentinel-2 is intended to improve vegetation assessment at local to global scale. Rangeland quality assessment is crucial for planning and management of grazing areas. Well managed and improved grazing areas lead to higher livestock production, which is a pillar of the rural economy and livelihoods, especially in many parts of the African continent. Leaf nitrogen (N) is an indicator of rangeland quality, and is crucial for understanding ecosystem function and services. Today, estimation of leaf N is possible using field and imaging spectroscopy. However, a few studies based on commercially available multispectral imageries such as WorldView-2 and RapidEye have shown the potential of a red-edge band for accurately predicting and mapping leaf N at the broad landscape scale. Sentinel-2 has two red edge bands. The objective of this study was to investigate the utility of the spectral configuration of Sentinel-2 for estimating leaf N concentration in rangelands and savannas of Southern Africa. Grass canopy reflectance was measured using the FieldSpec 3, Analytical Spectral Device (ASD) in concert with leaf sample collections for leaf N chemical analysis. ASD reflectances were resampled to the spectral bands of Sentinel-2 using published spectral response functions. Random Forest (RF) technique was used to predict leaf N using all thirteen bands. Using leave-one-out cross validation, the RF model explained 90% of leaf N variation, with the root mean square error (RMSE) of 0.04 (6% of the mean). Interestingly, spectral bands centred at 705 nm (red edge) and two shortwave infrared centred at 2190 and 1610 nm were found to be the most important bands in predicting leaf N. These findings concur with previous studies based on spectroscopy, airborne hyperspectral or multispectral imagery, e.g. RapidEye, on the importance of shortwave infrared and red-edge reflectance in the estimation of leaf N. In that sense, the ESA’s Sentinel-2 sampling in both spectral regions has a unique spectral configuration, and a high potential to estimate leaf N which is crucial for informing decision makers on rangeland condition monitoring.
Classification of different tree species in semiarid areas can be challenging as a result of the change in leaf structure and orientation due to soil moisture constraints. Tree species mapping is, however, a key parameter for forest management in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples.We performed classification using random forest (RF) and support vector machines (SVM) based on EnMap box. The overall accuracies for classifying the five tree species was 88.75 and 85% for both SVM and RF, respectively. We also demonstrated that the new red-edge band in the RapidEye sensor has the potential for classifying tree species in semiarid environments when integrated with other standard bands. Similarly, we observed that where there are limited training samples, SVM is preferred over RF. Finally, we demonstrated that the two accuracy measures of quantity and allocation disagreement are simpler and more helpful for the vast majority of remote sensing classification process than the kappa coefficient. Overall, high species classification can be achieved using strategically located RapidEye bands integrated with advanced processing algorithms.
Hyperspectral remote-sensing approaches are suitable for detection of the differences in 3-carbon (C 3 ) and four carbon (C 4 ) grass species phenology and composition. However, the application of hyperspectral sensors to vegetation has been hampered by high-dimensionality, spectral redundancy, and multicollinearity problems. In this experiment, resampling of hyperspectral data to wider wavelength intervals, around a few band-centers, sensitive to the biophysical and biochemical properties of C 3 or C 4 grass species is proposed. The approach accounts for an inherent property of vegetation spectral response: the asymmetrical nature of the inter-band correlations between a waveband and its shorter- and longer-wavelength neighbors. It involves constructing a curve of weighting threshold of correlation (Pearson's r ) between a chosen band-center and its neighbors, as a function of wavelength. In addition, data were resampled to some multispectral sensors-ASTER, GeoEye-1, IKONOS, QuickBird, RapidEye, SPOT 5, and WorldView-2 satellites-for comparative purposes, with the proposed method. The resulting datasets were analyzed, using the random forest algorithm. The proposed resampling method achieved improved classification accuracy (κ=0.82 ), compared to the resampled multispectral datasets (κ=0.78 , 0.65, 0.62, 0.59, 0.65, 0.62, 0.76, respectively). Overall, results from this study demonstrated that spectral resolutions for C 3 and C 4 grasses can be optimized and controlled for high dimensionality and multicollinearity problems, yet yielding high classification accuracies. The findings also provide a sound basis for programming wavebands for future sensors.
Remote sensing of grass/herb quantity is essential for rangeland management of livestock and wildlife. Spectral indices such as NDVI, determined from red and near infrared bands are affected by variable soil and atmospheric conditions and saturate in dense vegetation. Alternatively, the wavelength of maximum slope in the red-NIR transition, termed the red edge position (REP) has potential to mitigate these effects. But the utility of the REP using air- and space-borne imagery is determined by the availability of narrow bands in the region of the red edge and the simplicity of the extraction method. Very recently, we proposed a simple technique for extracting the REP called the linear extrapolation method [Cho and Skidmore, Remote Sens. Environ., 101(2006)118.]. The purpose of this study was to evaluate the potential of the linear extrapolation method for estimating fresh grass/herb biomass and compare its performance with the four-point linear interpolation and three-point Lagrangian interpolation methods. The REPs were derived from atmospherically corrected HYMAP images collected over Majella National Park, Italy in July 2004. The predictive capabilities of various REP linear regression models were evaluated using leave-one-out cross validation and test set validation methods. For both validation methods, the linear extrapolation REP models produced higher correlations with grass/herb biomass and lower prediction errors compared with the linear interpolation and Lagrangian REP models. This study demonstrates the potential of REPs extracted by the linear extrapolation method using HYMAP data for estimating fresh grass/herb biomass.