WorldView-2 Bands Research Articles

Species-based aboveground mangrove carbon stock estimation using WorldView-2 image data

The carbon stocks of a mangrove ecosystem depend to some extent on the diversity of its constituent species, which have different biophysical characteristics. The high-resolution remote sensing imagery from WorldView-2 (2 m pixel size) provides a data source for estimating aboveground mangrove carbon (mangrove AGC) stocks across species. This study was designed to (i) map mangrove species by applying the GEOBIA method, (ii) calculate mangrove AGC using species-specific allometric equations, and (iii) map the spatial distribution of mangrove AGC at the species level. It combined the species map from GEOBIA with carbon stock estimation by generating a model based on the vegetation index (spectral transformation of several WorldView-2 bands) over the Clungup Mangrove Conservation (CMC) area in Malang, East Java, Indonesia. GEOBIA was used to classify mangrove species based on the homogeneous segments of each species depicted in the image, while the carbon stocks in the field were calculated using species-specific allometric equations. A regression function between the carbon stocks and the vegetation index value stored in each pixel was applied to the derived mangrove species map. The GEOBIA species mapping using the nearest neighbor algorithm identified six dominant species in the CMC area, namely Bruguiera gymnorrhiza, Ceriops tagal, Rhizophora apiculata, Rhizophora mucronata, Sonneratia alba, and Nypa fruticans, with an 84% overall accuracy. Based on the regression analysis results, the vegetation index values varied across species. The mangrove AGC estimation and mapping at the species level produced favorable results, with a maximum accuracy of 54.94% for B. gymnorrhiza, 55.55% for C. tagal, 41.43% for R. apiculata, 51.38% for R. mucronata, and 54.87% for S. alba. Also, the range of the estimated carbon stocks differed for each species. This research contributes an innovative development by combining methods of mangrove species mapping with mangrove AGC estimation at the species level.

Classification of urban tree species using LiDAR data and WorldView-2 satellite imagery in a heterogeneous environment

Feature complexity and heterogeneity of urban areas pose a challenge for tree species classification. This study examined the effectiveness of the integrated Worldview-2 (WV-2) bands, vegetation indices and normalized Digital Surface Model (nDSM) dataset in mapping common urban tree species and other land use and land cover (LULC) types using Random Forest (RF) and Support Vector Machine (SVM) algorithms. The study also ranked the importance of nDSM, WV-2 bands and vegetation indices. The results indicate that the integrated dataset was effective as shown by high classification accuracies of 97% for the RF and 94% for SVM classifiers. The nDSM was the top-ranked variable with high Mean Decrease in Accuracy (MDA) and Mean Decrease in Gini (MDG) scores of 0.98 and 0.61, respectively. This research provides information to municipalities on the methods and data that can be used for the sustainable management of urban tree species.

Combining WV-2 images and tree physiological factors to detect damage stages of Populus gansuensis by Asian longhorned beetle (Anoplophora glabripennis) at the tree level

BackgroundAnoplophora glabripennis (Motschulsky), commonly known as Asian longhorned beetle (ALB), is a wood-boring insect that can cause lethal infestation to multiple borer leaf trees. In Gansu Province, northwest China, ALB has caused a large number of deaths of a local tree species Populus gansuensis. The damaged area belongs to Gobi desert where every single tree is artificially planted and is extremely difficult to cultivate. Therefore, the monitoring of the ALB infestation at the individual tree level in the landscape is necessary. Moreover, the determination of an abnormal phenotype that can be obtained directly from remote-sensing images to predict the damage degree can greatly reduce the cost of field investigation and management.MethodsMultispectral WorldView-2 (WV-2) images and 5 tree physiological factors were collected as experimental materials. One-way ANOVA of the tree’s physiological factors helped in determining the phenotype to predict damage degrees. The original bands of WV-2 and derived vegetation indices were used as reference data to construct the dataset of a prediction model. Variance inflation factor and stepwise regression analyses were used to eliminate collinearity and redundancy. Finally, three machine learning algorithms, i.e., Random Forest (RF), Support Vector Machine (SVM), Classification And Regression Tree (CART), were applied and compared to find the best classifier for predicting the damage stage of individual P. gansuensis.ResultsThe confusion matrix of RF achieved the highest overall classification accuracy (86.2%) and the highest Kappa index value (0.804), indicating the potential of using WV-2 imaging to accurately detect damage stages of individual trees. In addition, the canopy color was found to be positively correlated with P. gansuensis’ damage stages.ConclusionsA novel method was developed by combining WV-2 and tree physiological index for semi-automatic classification of three damage stages of P. gansuensis infested with ALB. The canopy color was determined as an abnormal phenotype that could be directly assessed using remote-sensing images at the tree level to predict the damage degree. These tools are highly applicable for driving quick and effective measures to reduce damage to pure poplar forests in Gansu Province, China.

Classification of tree species in a heterogeneous urban environment using object-based ensemble analysis and World View-2 satellite imagery

Urban trees are valuable in, inter alia, ameliorating air pollution and mitigating the effects associated with urban heat islands. The dearth of tree cover maps is a major challenge for urban planners in the management of urban trees. This work adopts remote sensing approaches to provide urban tree cover maps which can strengthen urban landscape management. Whereas traditional pixel-based classification approaches have been commonly used in image classification, they are not well-suited for urban tree mapping due to their failure to fully explore the image’s spatial and spectral characteristics. Object-based classification techniques produce improved accuracies using additional variables. This study depicts the capability of object-based image analysis (OBIA) in mapping common urban trees using very high-resolution (VHR) WorldView-2 (WV-2) imagery. The study tests the utility of WV-2 bands and other feature variables in the object-based mapping of common urban trees and other land cover classes. Furthermore, the study compares the utility of Support Vector Machine (SVM) and Random Forest (RF) in the object-based mapping of common urban trees and other land cover classes. The results show that the Normalized Difference Vegetation Index (NDVI), NIR 1 and NIR 2 bands were important in the classification of common urban trees and other land cover classes. The RF classifier performed better than SVM, with an overall accuracy of 91.9% as compared to 87.3% for SVM. The results of this study offer insight to urban authorities with knowledge on the segmentation parameters, classification methods and feature variables for mapping urban trees, valuable in urban tree management.

AUTOMATIC INDICES BASED CLASSIFICATION METHOD FOR MAP UPDATING USING VHR SATELLITE IMAGES

Urban land cover classification using Very High Resolution (VHR) satellite images is a very important source of information for map updating. Egyptian environment has more challenges in feature extraction. The main problem lies in the spectral similarity between different land cover classes. Also, great diversity in sizes, shapes, and materials of each class. The main aim of this work is to represent a new automatic indices-based classification method for map updating using VHR satellite images. The method uses a set of spectral indices with their thresholds in consecutive order, chosen based on WorldView-2 (WV-2) bands, to classify land cover in the Egyptian environment. For this study, WV-2 satellite images with eight spectral bands were used. The proposed method is compared with five traditional classification methods; Minimum distance, Spectral angle mapper, Mahalanobis distance, Spectral correlation mapper, and Maximum likelihood method, which included in ERDAS 2015 software, for validation purpose and checking its stability. The results show that the extracted features with the proposed method can contribute significantly to update Egyptian medium scale maps. The average overall accuracy achieved with the proposed approach (75.31%) is higher than those obtained using Minimum distance (54.0%), Spectral angle mapper (69.50%), and Mahalanobis distance (73.63%). Also, it is near to those obtained by the Spectral correlation mapper (76.50%), and Maximum likelihood method (78.25%).

Urban Greening Tree Species Classification Based on HSV Colour Space of WorldView-2

Feature mining and effective combination of remote sensing data can effectively improve the accuracy of tree species classification; however, the application of some common features in tree species classification needs to be further analysed. In this study, we transformed WorldView-2 RGB bands to hue, saturation and value (HSV) colour space, constructed 56 HSV features, used maximum likelihood classification (MLC) and support vector machine (SVM) to classify tree species based on these data sets and feature combinations to explore which combinations can effectively improve the recognition accuracy. The results show that among the 56 HSV features, the highest classification accuracy (64.2893%) was generated by the HSV feature transformed by the 368 band combination (CBC368). A single HSV feature set could not improve the classification accuracy compared with the spectral band used which produced the HSV. Among the feature sets of all H, all S and all V, the highest classification accuracy (71.7063%) was generated by feature sets all S; it is close but not higher than the classification results obtained using eight bands. Among the combination of two feature sets, the highest classification accuracy (77.5384%) was generated by all S + all V, and the classification accuracy is much higher than that obtained using the eight bands of WorldView-2 (74.0713%, MLC based). When all H, S and V were combined, the classification accuracy reached 77.6251%. Comparative experiments showed that combining all HSV colour spaces transformed by the eight spectral bands of WorldView-2 can effectively improve tree species recognition accuracy.

Integration of WorldView-2 and airborne laser scanning data to classify defoliation levels in Quercus ilex L. Dehesas affected by root rot mortality: Management implications

The dehesa ecosystem is severely affected by root rot decline caused by the soilborne pathogenic oomycetes of the genus Phytophthora. Defoliation mapping is particularly challenging in low density ecosystems with high spectral variability due to environmental heterogeneity within relatively short distances. In this study, holm oak defoliation was assessed by classifying two different levels (low and high defoliation trees, with a 30% crown-defoliation threshold) using a combination of multispectral WorldView-2 (WV-2) and Airborne Laser Scanning (ALS) data in an automated Random Forest (RF) modeling approach. Besides the original remote sensing data, a set of vegetation indices (VI) and ALS-derived structural parameters were derived. Seven predictors of defoliation were selected from the ALS metrics, WV-2 bands, and indices datasets: the height percentile of the tree in which occurs the maximum number of returns, mean values in the tree crown of the Chlorophyll index green, Plant Senescence Reflectance Index, Red Edge Normalized Difference Vegetation Index, Double Peak Index, band 3 of the WV-2 image, and bincentil 70 values. The confusion matrix of the external evaluation achieved the highest overall classification accuracy (86.7%) and the highest Kappa index (0.73). Finally, we produced a predicted tree-defoliation map which was used to establish the relationship between Quercus ilex damage levels and soil variables and management practices. High defoliated trees were more abundant in zones of shallow and compacted soil, with lower silt proportion and Ca concentration. Our results offer to forest managers a tool for the rapid and effective assessment of large areas affected by root rot defoliation in their planning of control and restoration measures aimed at reducing the holm oak mortality of holm oaks in management units.

Semiautomated Detection and Mapping of Vegetation Distribution in the Antarctic Environment Using Spatial-Spectral Characteristics of WorldView-2 Imagery

Effective monitoring of changes in the geographic distribution of cryospheric vegetation requires high-resolution and accurate baseline maps. The rationale of the present study is to compare multiple feature extraction approaches to remotely mapping vegetation in Antarctica, assessing which give the greatest accuracy and reproducibility relative to those currently available. This study provides precise, high-resolution, and refined baseline information on vegetation distribution as is required to enable future spatiotemporal change analyses of the vegetation in Antarctica. We designed and implemented a semiautomated customized normalized difference vegetation index (NDVI) approach for extracting cryospheric vegetation by incorporating very high resolution (VHR) 8-band WorldView-2 (WV-2) satellite data. The viability of state-of-the-art target detection, spectral processing/matching, and pixel-wise supervised classification feature extraction techniques are compared with the customized NDVI approach devised in this study. An extensive quantitative and comparative assessment was made by evaluating four semiautomatic feature extraction approaches consisting of 16 feature extraction standalone methods (four customized NDVI plus 12 existing methods) for mapping vegetation on Fisher Island and Stornes Peninsula in the Larsemann Hills, situated on continental east Antarctica. The results indicated that the customized NDVI approach achieved superior performance (average bias error ranged from ~6.44 ± 1.34% to ~11.55 ± 1.34%) and highest statistical stability in terms of performance when compared with existing feature extraction approaches. Overall, the accuracy analysis of the vegetation mapping relative to manually digitized reference data (supplemented by validation with ground truthing) indicated that the 16 semi-automatic mapping methods representing four general feature extraction approaches extracted vegetated area from Fisher Island and Stornes Peninsula totalling between 2.38 and 3.72 km2 (2.85 ± 0.10 km2 on average) with bias values ranging from 3.49 to 31.39% (average 12.81 ± 1.88%) and average root mean square error (RMSE) of 0.41 km2 (14.73 ± 1.88%). Further, the robustness of the analyses and results were endorsed by a cross-validation experiment conducted to map vegetation from the Schirmacher Oasis, East Antarctica. Based on the robust comparative analysis of these 16 methods, vegetation maps of the Larsemann Hills and Schirmacher Oasis were derived by ensemble merging of the five top-performing methods (Mixture Tuned Matched Filtering, Matched Filtering, Matched Filtering/Spectral Angle Mapper Ratio, NDVI-2, and NDVI-4). This study is the first of its kind to detect and map sparse and isolated vegetated patches (with smallest area of 0.25 m2) in East Antarctica using VHR data and to use ensemble merging of feature extraction methods, and provides access to an important indicator for environmental change.

Application of feature selection methods and machine learning algorithms for saltmarsh biomass estimation using Worldview-2 imagery

Assessing large scale plant productivity of coastal marshes is essential to understand the resilience of these systems to climate change. Two machine learning approaches, random forest (RF) and support vector machine (SVM) regression were tested to estimate biomass of a common saltmarshes species, salt couch grass (Sporobolus virginicus). Reflectance and vegetation indices derived from 8 bands of Worldview-2 multispectral data were used for four experiments to develop the biomass model. These four experiments were, Experiment-1: 8 bands of Worldview-2 image, Experiment-2: Possible combination of all bands of Worldview-2 for Normalized Difference Vegetation Index (NDVI) type vegetation indices, Experiment-3: Combination of bands and vegetation indices, Experiment-4: Selected variables derived from experiment-3 using variable selection methods. The main objectives of this study are (i) to recommend an affordable low cost data source to predict biomass of a common saltmarshes species, (ii) to suggest a variable selection method suitable for multispectral data, (iii) to assess the performance of RF and SVM for the biomass prediction model. Cross-validation of parameter optimizations for SVM showed that optimized parameter of ɛ-SVR failed to provide a reliable prediction. Hence, ν-SVR was used for the SVM model. Among the different variable selection methods, recursive feature elimination (RFE) selected a minimum number of variables (only 4) with an RMSE of 0.211 (kg/m2). Experiment-4 (only selected bands) provided the best results for both of the machine learning regression methods, RF (R 2= 0.72, RMSE= 0.166 kg/m2) and SVR (R 2= 0.66, RMSE = 0.200 kg/m2) to predict biomass. When a 10-fold cross validation of the RF model was compared with a 10-fold cross validation of SVR, a significant difference (p = <0.0001) was observed for RMSE. One to one comparisons of actual to predicted biomass showed that RF underestimates the high biomass values, whereas SVR overestimates the values; this suggests a need for further investigation and refinement.

Quantifying coconut palm extent on Pacific islands using spectral and textural analysis of very high resolution imagery

ABSTRACTNative forests on islands throughout the global tropics face increasing pressure from the human-driven expansion of coconut palm (Cocos nucifera) planted for the purposes of coconut oil harvest. Conversion from native forests to Cocos monocultures leads to drastic ecological consequences in island environments and alters terrestrial and marine food webs through a variety of cascading effects and feedbacks. Despite the ecological significance and geographic range of Cocos expansion, large-scale assessments of coconut proliferation are still lacking due to the isolated nature of many islands where Cocos is found. Remote sensing approaches are often used to monitor forest composition at broad scales, but the small physical size of most islands limits the use of many popular satellite sensors with 15–30 m resolution. The recent availability of very high resolution (<5 m) satellite imagery facilitates novel assessment of this major ecological pattern, but the increased resolution introduces problematic ‘salt-and-pepper’ effects due to the heterogeneous nature of palm frond canopies. This case study evaluates the effectiveness of applying grey-level co-occurrence matrix (GLCM) textural features to very high resolution (0.5–2 m) WorldView-2 imagery to resolve the canopy heterogeneity problem and map the extent of Cocos spread on 21 islets of Palmyra Atoll, a protected United States National Wildlife Refuge in the Northern Line Islands. A random forest (RF)-driven classification scheme differentiating between coconut palms, native trees including Pisonia grandis, and endemic Scaevola sericea shrubs achieved 97.0% overall accuracy and 98.4% producer’s and user’s accuracies for the coconut palm class when trained on a combined spectral and GLCM textural feature set. Classifications restricted to the eight spectral bands of WorldView-2 are not only less accurate (89.4% overall accuracy), but also significantly worse at identifying Cocos canopies (79.0% versus 98.0% accuracy when GLCM textures are included). However, paring down the full set of sixteen spectral and textural features to the three most important of each type did not result in significant changes in accuracy. These results demonstrate the effectiveness of a joint high-resolution textural and spectral approach for remotely quantifying the spread of Cocos and its impacts on native tree communities throughout the tropics, including remote island locations.

Detailed urban surface characterization using spectra from enhanced spatial resolution Sentinel-2 imagery and a hierarchical multiple endmember spectral mixture analysis approach

Detailed mapping of urban surfaces is one of the most challenging tasks in remote sensing due to the three-dimensional structure of cities, spatial diversity, and material spectral variability. Satellite urban applications demand better spatial, spectral, and temporal resolution, although there are strict technical constraints among them. Therefore, the development of sophisticated methods that exploit both high spectral and spatial data sources becomes necessary. A hierarchical multiple endmember spectral mixture analysis (MESMA) approach is developed and applied on Sentinel-2 imagery for the detailed quantification of the urban land cover, taking advantage of Worldview-2 high spatial resolution. The case study is the urban and peri-urban area of Heraklion, Greece. The area to point regression kriging (ATPRK) method is applied to downscale Sentinel-2 bands from 10 and 20 m to 2 m (WorldView-2 spatial resolution) and create a spectral library (SL) of urban materials, which contain 180 separate spectra. The urban SL is then used in the developed hierarchical MESMA approach to estimate the abundances of 11 urban land cover classes based on the original Sentinel-2 image. The estimated land cover fractions validate against a very high-resolution (1 m) land cover map of the area. It is proved that the complexity of the urban land cover can be efficiently investigated by the proposed methodology. Error analysis shows good accuracy of the results in all estimated class fractions. Moreover, the good validation results lead to the conclusion that ATPRK fusion algorithm between Sentinel-2 and WorldView-2 bands produced reliable urban material spectra, capable for advanced spectral analysis on Sentinel-2 imagery. The developed methodology is easily transferable to other cities since it is based exclusively on earth observation data and is suitable for multiple urban applications related to urban climate, urban sprawl, and urban regeneration.

High-resolution remote sensing and advanced classification techniques for the prospection of archaeological sites’ markers: The case of dung deposits in the Shashi-Limpopo Confluence area (southern Africa)

Archaeological prospection through remote sensing is based on the contrast between areas of archaeological interest and their surroundings. It has been used as the cheapest and the fastest way of locating and documenting areas of archaeological interest since the 1920s, initially with the aid of film-based aerial photographs. In recent years, there has been a shift towards the use of multispectral satellite data in prospecting for archaeological sites because of their ability to give information on spectral characteristics of archaeological material beyond the visible spectrum. However, spectral signatures for identifying archaeological sites are not universal, and an assessment of the applicability of remote sensing techniques in different archaeological landscapes is needed. This study tests the feasibility of prospecting for archaeological sites previously occupied by farming communities in the Shashi-Limpopo Confluence Area of southern Africa, using very high-resolution satellite WorldView-2 images. It also assesses the performance of advanced classification algorithms (support vector machine and random forest) and the contribution of new WorldView-2 bands in detecting archaeological sites. Two independent accuracy assessments were carried out, using a data set collected by Huffman (2011, 2009a) and a randomly generated holdout test dataset, respectively. The results demonstrate the potential of remote sensing methods in prospecting for archaeological sites previously occupied by farming communities using very high-resolution satellite images and advanced classification algorithms. Very high overall accuracies were achieved by: random forest, 95.29% using holdout sample and 97.71% using independent dataset; support vector machine, 88.82% using holdout sample and 95.88% using independent dataset, respectively. The new WorldView-2 bands were of least importance (compared to traditional bands) in detecting sites in Shashi-Limpopo Confluence Area. Despite high classification accuracies achieved by both classifiers, there were some misclassifications between vitrified dung sites and river sand. Therefore, to address this problem, this study recommends the use of robust classifiers such as object-based algorithms because of their ability to segment an image into homogenous objects and classify them using a combination of spectral, textual, sub-pixels, spatial, relational and contextual methods.

Quantifying the discriminatory power of remote sensing technologies for benthic habitat mapping

ABSTRACTWhen mapping benthic habitats using remotely sensed data, the ability to discriminate between pairs of habitats is a key measure of the usefulness of a set of one or more input covariates. In the case where some input data is already available, but a superior map is sought, map-makers would like to know which additional remote sensing data would make the greatest improvement to the quality of their maps. Depending on the purpose of the map, this could be measured by the extent to which a selected pair of habitats is discriminated.This study exploits an existing data-rich study site in order to provide guidance for the use of remote sensing technology in regions where such data do not exist already. LiDAR (light detection and ranging) reflectivity, multibeam backscatter, World View 2 (WV2) bands 1–4, multibeam bathymetry, and depth-derived variables are analysed to determine the extent to which they enable benthic habitats of interest to be discriminated from one another in a statistical sense. Ground truth is employed in the form of towed video.Quantitative results are tabulated for each of the six pairs of four key habitat classes: macroalgae, seagrass, sand, and reef. The technique of Canonical Variate Analysis (CVA) is used to calculate ratios of between-class to within-class variation and cross-validated error rate estimates are calculated for the best combination of N variables, where N varies from 1 to 8. It is found that: Reef and Macroalgae classes cannot be statistically distinguished with the technologies and training methods studied here; WV2 augmented with depth provides good discrimination between the separable classes; multibeam echosounder depth and backscatter data both provide good information for mapping cover types, but in general are not as useful as optical data if it is available. LiDAR reflectivity is a very useful covariate, which has comparable discriminatory power to any one of the first three WV2 bands, with the added potential to penetrate to greater depths than the passive satellite sensors.

Individual tree crown delineation in a highly diverse tropical forest using very high resolution satellite images

Mapping tropical tree species at landscape scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. For this purpose, detection and delineation of individual tree crowns (ITCs) is a prerequisite. Here, we present a new method of automatic tree crown delineation based only on very high resolution images from WorldView-2 satellite and apply it to a region of the Atlantic rain forest with highly heterogeneous tropical canopy cover – the Santa Genebra forest reserve in Brazil. The method works in successive steps that involve pre-processing, selection of forested pixels, enhancement of borders, detection of pixels in the crown borders, correction of shade in large trees and, finally, segmentation of the tree crowns. Principally, the method uses four techniques: rolling ball algorithm and mathematical morphological operations to enhance the crown borders and ease the extraction of tree crowns; bimodal distribution parameters estimations to identify the shaded pixels in the gaps, borders, and crowns; and focal statistics for the analysis of neighbouring pixels. Crown detection is validated by comparing the delineated ITCs with a sample of ITCs delineated manually by visual interpretation. In addition, to test if the spectra of individual species are conserved in the automatic delineated crowns, we compare the accuracy of species prediction with automatic and manual delineated crowns with known species. We find that our method permits detection of up to 80% of ITCs. The seven species with over 10 crowns identified in the field were mapped with reasonable accuracy (30.5–96%) given that only WorldView-2 bands and texture features were used. Similar classification accuracies were obtained using both automatic and manual delineation, thereby confirming that species’ spectral responses are preserved in the automatic method and thus permitting the recognition of species at the landscape scale. Our method might support tropical forest applications, such as mapping species and canopy characteristics at the landscape scale.

ANALYSIS OF IN-SITU SPECTRAL REFLECTANCE OF SAGO AND OTHER PALMS: IMPLICATIONS FOR THEIR DETECTION IN OPTICAL SATELLITE IMAGES

Abstract. We present a characterization, comparison and analysis of in-situ spectral reflectance of Sago and other palms (coconut, oil palm and nipa) to ascertain on which part of the electromagnetic spectrum these palms are distinguishable from each other. The analysis also aims to reveal information that will assist in selecting which band to use when mapping Sago palms using the images acquired by these sensors. The datasets used in the analysis consisted of averaged spectral reflectance curves of each palm species measured within the 345–1045 nm wavelength range using an Ocean Optics USB4000-VIS-NIR Miniature Fiber Optic Spectrometer. This in-situ reflectance data was also resampled to match the spectral response of the 4 bands of ALOS AVNIR-2, 3 bands of ASTER VNIR, 4 bands of Landsat 7 ETM+, 5 bands of Landsat 8, and 8 bands of Worldview-2 (WV2). Examination of the spectral reflectance curves showed that the near infra-red region, specifically at 770, 800 and 875 nm, provides the best wavelengths where Sago palms can be distinguished from other palms. The resampling of the in-situ reflectance spectra to match the spectral response of optical sensors made possible the analysis of the differences in reflectance values of Sago and other palms in different bands of the sensors. Overall, the knowledge learned from the analysis can be useful in the actual analysis of optical satellite images, specifically in determining which band to include or to exclude, or whether to use all bands of a sensor in discriminating and mapping Sago palms.

Retrieval of total suspended matter concentrations from high resolution WorldView-2 imagery: a case study of inland rivers

Satellite imagery has played an important role in monitoring water quality of lakes or coastal waters presently, but scarcely been applied in inland rivers. This paper presents an attempt of feasibility to apply regression model to quantify and map the concentrations of total suspended matter (CTSM) in inland rivers which have a large scale of spatial and a high CTSM dynamic range by using high resolution satellite remote sensing data, WorldView-2. An empirical approach to quantify CTSM by integrated use of high resolution WorldView-2 multispectral data and 21 in situ CTSM measurements. Radiometric correction, geometric and atmospheric correction involved in image processing procedure is carried out for deriving the surface reflectance to correlate the CTSM and satellite data by using single-variable and multivariable regression technique. Results of regression model show that the single near-infrared (NIR) band 8 of WorldView-2 have a relative strong relationship (R2=0.93) with CTSM. Different prediction models were developed on various combinations of WorldView-2 bands, the Akaike Information Criteria approach was used to choose the best model. The model involving band 1, 3, 5, and 8 of WorldView-2 had a best performance, whose R2 reach to 0.92, with SEE of 53.30 g/m3. The spatial distribution maps were produced by using the best multiple regression model. The results of this paper indicated that it is feasible to apply the empirical model by using high resolution satellite imagery to retrieve CTSM of inland rivers in routine monitoring of water quality.

Exploring the Potential of WorldView-2 Red-Edge Band-Based Vegetation Indices for Estimation of Mangrove Leaf Area Index with Machine Learning Algorithms

To accurately estimate leaf area index (LAI) in mangrove areas, the selection of appropriate models and predictor variables is critical. However, there is a major challenge in quantifying and mapping LAI using multi-spectral sensors due to the saturation effects of traditional vegetation indices (VIs) for mangrove forests. WorldView-2 (WV2) imagery has proven to be effective to estimate LAI of grasslands and forests, but the sensitivity of its vegetation indices (VIs) has been uncertain for mangrove forests. Furthermore, the single model may exhibit certain randomness and instability in model calibration and estimation accuracy. Therefore, this study aims to explore the sensitivity of WV2 VIs for estimating mangrove LAI by comparing artificial neural network regression (ANNR), support vector regression (SVR) and random forest regression (RFR). The results suggest that the RFR algorithm yields the best results (RMSE = 0.45, 14.55% of the average LAI), followed by ANNR (RMSE = 0.49, 16.04% of the average LAI), and then SVR (RMSE = 0.51, 16.56% of the average LAI) algorithms using 5-fold cross validation (CV) using all VIs. Quantification of the variable importance shows that the VIs derived from the red-edge band consistently remain the most important contributor to LAI estimation. When the red-edge band-derived VIs are removed from the models, estimation accuracies measured in relative RMSE (RMSEr) decrease by 3.79%, 2.70% and 4.47% for ANNR, SVR and RFR models respectively. VIs derived from red-edge band also yield better accuracy compared with other traditional bands of WV2, such as near-infrared-1 and near-infrared-2 band. Furthermore, the estimated LAI values vary significantly across different mangrove species. The study demonstrates the utility of VIs of WV2 imagery and the selected machine-learning algorithms in developing LAI models in mangrove forests. The results indicate that the red-edge band of WV2 imagery can help alleviate the saturation problem and improve the accuracy of LAI estimation in a mangrove area.

Potential of RapidEye and WorldView-2 Satellite Data for Improving Rice Nitrogen Status Monitoring at Different Growth Stages

For in-season site-specific nitrogen (N) management of rice to be successful, it is crucially important to diagnose rice N status efficiently across large areas within a short time frame. In recent studies, the FORMOSAT-2 satellite images with traditional blue (B), green (G), red (R), and near-infrared (NIR) wavebands have been used to estimate rice N status due to its high spatial resolution, daily revisit capability, and relatively lower cost. This study aimed to evaluate the potential improvements of RapidEye and WorldView-2 data over FORMOSAT-2 for rice N status monitoring, as the former two sensors provide additional wavelengths besides the traditional four wavebands. Ten site-year N rate experiments were conducted in Jiansanjiang, Heilongjiang Province of Northeast China from 2008 to 2011. Plant samples and field hyperspectral data were collected at three growth stages: panicle initiation (PI), stem elongation (SE), and heading (HE). The canopy-scale hyperspectral data were upscaled to simulate the satellite bands. Vegetation index (VI) analysis, stepwise multiple linear regression (SMLR), and partial least squares regression (PLSR) were performed to derive plant N status indicators. The results indicated that the best-performed VIs calculated from the simulated RapidEye and WorldView-2 bands, especially those based on the red edge (RE) bands, explained significantly more variability for above ground biomass (AGB), plant N uptake (PNU), and nitrogen nutrition index (NNI) estimations than their FORMOSAT-2-based counterparts did, especially at the PI and SE stages. The SMLR and PLSR models based on the WorldView-2 bands generally had the best performance, followed by the ones based on the RapidEye bands. The SMLR results revealed that both the NIR and RE bands were important for N status estimation. In particular, the NIR1 band (760–900 nm from RapidEye or 770–895 nm from WorldView-2) was most important for estimating all the N status indicators. The RE band (690–730 nm or 705–745 nm) improved AGB, PNU, and NNI estimations at all three stages, especially at the PI and SE stages. AGB and PNU were best estimated using data across the stages while plant N concentration (PNC) and NNI were best estimated at the HE stage. The PLSR analysis confirmed the significance of the NIR1 band for AGB, PNU, and NNI estimations at all stages except for the HE stage. It also showed the importance of including extra bands (coastal, yellow, and NIR2) from the WorldView-2 sensor for N status estimation. Overall, both the RapidEye and WorldView-2 data with RE bands improved the results relative to FORMOSAT-2 data. However, the WorldView-2 data with three extra bands in the visible and NIR regions showed the highest potential in estimating rice N status.

Multi-phenology WorldView-2 imagery improves remote sensing of savannah tree species

Biodiversity mapping in African savannah is important for monitoring changes and ensuring sustainable use of ecosystem resources. Biodiversity mapping can benefit from multi-spectral instruments such as WorldView-2 with very high spatial resolution and a spectral configuration encompassing important spectral regions not previously available for vegetation mapping. This study investigated i) the benefits of the eight-band WorldView-2 (WV-2) spectral configuration for discriminating tree species in Southern African savannah and ii) if multiple-images acquired at key points of the typical phenological development of savannahs (peak productivity, transition to senescence) improve on tree species classifications. We first assessed the discriminatory power of WV-2 bands using interspecies-Spectral Angle Mapper (SAM) via Band Add-On procedure and tested the spectral capability of WorldView-2 against simulated IKONOS for tree species classification. The results from interspecies-SAM procedure identified the yellow and red bands as the most statistically significant bands (p=0.000251 and p=0.000039 respectively) in the discriminatory power of WV-2 during the transition from wet to dry season (April). Using Random Forest classifier, the classification scenarios investigated showed that i) the 8-bands of the WV-2 sensor achieved higher classification accuracy for the April date (transition from wet to dry season, senescence) compared to the March date (peak productivity season) ii) the WV-2 spectral configuration systematically outperformed the IKONOS sensor spectral configuration and iii) the multi-temporal approach (March and April combined) improved the discrimination of tress species and produced the highest overall accuracy results at 80.4%. Consistent with the interspecies-SAM procedure, the yellow (605nm) band also showed a statistically significant contribution in the improved classification accuracy from WV-2. These results highlight the mapping opportunities presented by WV-2 data for monitoring the distribution status of e.g. species often harvested by local communities (e.g. Sclerocharya birrea), encroaching species, or species-specific tree losses induced by elephants.

Incorporation of satellite remote sensing pan-sharpened imagery into digital soil prediction and mapping models to characterize soil property variability in small agricultural fields

Soil prediction models based on spectral indices from some multispectral images are too coarse to characterize spatial pattern of soil properties in small and heterogeneous agricultural lands. Image pan-sharpening has seldom been utilized in Digital Soil Mapping research before. This research aimed to analyze the effects of pan-sharpened (PAN) remote sensing spectral indices on soil prediction models in smallholder farm settings. This research fused the panchromatic band and multispectral (MS) bands of WorldView-2, GeoEye-1, and Landsat 8 images in a village in Southern India by Brovey, Gram-Schmidt and Intensity-Hue-Saturation methods. Random Forest was utilized to develop soil total nitrogen (TN) and soil exchangeable potassium (Kex) prediction models by incorporating multiple spectral indices from the PAN and MS images. Overall, our results showed that PAN remote sensing spectral indices have similar spectral characteristics with soil TN and Kex as MS remote sensing spectral indices. There is no soil prediction model incorporating the specific type of pan-sharpened spectral indices always had the strongest prediction capability of soil TN and Kex. The incorporation of pan-sharpened remote sensing spectral data not only increased the spatial resolution of the soil prediction maps, but also enhanced the prediction accuracy of soil prediction models.Small farms with limited footprint, fragmented ownership and diverse crop cycle should benefit greatly from the pan-sharpened high spatial resolution imagery for soil property mapping. Our results show that multiple high and medium resolution images can be used to map soil properties suggesting the possibility of an improvement in the maps’ update frequency. Additionally, the results should benefit the large agricultural community through the reduction of routine soil sampling cost and improved prediction accuracy.