WorldView-2 Imagery Research Articles

UAV and High Resolution Satellite Mapping of Forage Lichen (Cladonia spp.) in a Rocky Canadian Shield Landscape

Reindeer lichens (Cladonia spp.) are an important food source for woodland and barren ground caribou herds. In this study, we assessed Cladonia classification accuracy in a rocky, Canadian Shield landscape near Yellowknife, Northwest Territories using both Unmanned Aerial Vehicle (UAV) sensors and high-resolution satellite sensors. At the UAV scale, random forest classifications derived from a multispectral, visible-near infrared sensor (Micasense Altum) had an average 5% higher accuracy for mapping Cladonia (i.e., 95.5%) than when using a conventional color RGB camera (DJI Phantom 4 RTK). We aggregated Altum lichen classifications from three 5 ha study sites to train random forest regression models of fractional lichen cover using predictor features from WorldView-3 and Planet CubeSat satellite imagery. WorldView models at 6 m resolution had an average 6.8% RMSE (R 2 = 0.61) when tested at independent study sites and outperformed the 6 m Planet models, which had a 9.9% RMSE (R 2 = 0.34). These satellite results are comparable to previous lichen mapping studies focusing on woodlands, but the small cover of Cladonia in our study area (11.6% or 16.8% within the barren portions) results in a high relative RMSE (62.2%) expressed as a proportion of mean lichen cover.

Assessing Deep Convolutional Neural Networks and Assisted Machine Perception for Urban Mapping

High-spatial-resolution satellite imagery has been widely applied for detailed urban mapping. Recently, deep convolutional neural networks (DCNNs) have shown promise in certain remote sensing applications, but they are still relatively new techniques for general urban mapping. This study examines the use of two DCNNs (U-Net and VGG16) to provide an automatic schema to support high-resolution mapping of buildings, road/open built-up, and vegetation cover. Using WorldView-2 imagery as input, we first applied an established OBIA method to characterize major urban land cover classes. An OBIA-derived urban map was then divided into a training and testing region to evaluate the DCNNs’ performance. For U-Net mapping, we were particularly interested in how sample size or the number of image tiles affect mapping accuracy. U-Net generated cross-validation accuracies ranging from 40.5 to 95.2% for training sample sizes from 32 to 4096 image tiles (each tile was 256 by 256 pixels). A per-pixel accuracy assessment led to 87.8 percent overall accuracy for the testing region, suggesting U-Net’s good generalization capabilities. For the VGG16 mapping, we proposed an object-based framing paradigm that retains spatial information and assists machine perception through Gaussian blurring. Gaussian blurring was used as a pre-processing step to enhance the contrast between objects of interest and background (contextual) information. Combined with the pre-trained VGG16 and transfer learning, this analytical approach generated a 77.3 percent overall accuracy for per-object assessment. The mapping accuracy could be further improved given more robust segmentation algorithms and better quantity/quality of training samples. Our study shows significant promise for DCNN implementation for urban mapping and our approach can transfer to a number of other remote sensing applications.

Evaluating pixel-based vs. object-based image analysis approaches for lithological discrimination using VNIR data of WorldView-3

The object-based against pixel-based image analysis approaches were assessed for lithological mapping in a geologically complex terrain using Visible Near Infrared (VNIR) bands of WorldView-3 (WV-3) satellite imagery. The study area is Hormuz Island, southern Iran, a salt dome composed of dominant sedimentary and igneous rocks. When performing the object-based image analysis (OBIA) approach, the textural and spectral characteristics of lithological features were analyzed by the use of support vector machine (SVM) algorithm. However, in the pixel-based image analysis (PBIA), the spectra of lithological end-members, extracted from imagery, were used through the spectral angle mapper (SAM) method. Several test samples were used in a confusion matrix to assess the accuracy of classification methods quantitatively. Results showed that OBIA was capable of lithological mapping with an overall accuracy of 86.54% which was 19.33% greater than the accuracy of PBIA. OBIA also reduced the salt-and-pepper artifact pixels and produced a more realistic map with sharper lithological borders. This research showed limitations of pixel-based method due to relying merely on the spectral characteristics of rock types when applied to high-spatial-resolution VNIR bands of WorldView-3 imagery. It is concluded that the application of an object-based image analysis approach obtains a more accurate lithological classification when compared to a pixel-based image analysis algorithm.

Sentinel-2 and WorldView-3 atmospheric correction and signal normalization based on ground-truth spectroradiometric measurements

Remote sensing satellite Earth Observing Systems (EOS) provide a variety of products for monitoring Earth surface processes at varying spatial and spectral resolutions. Combining information from high and medium spatial resolution images is valuable for monitoring ground cover and vegetation status in cropland, grassland, forests, and other natural settings. However, coupling information from different EOS requires compensating for atmospheric and view angle effects before integrating comparable surface reflectance (SR) values. The objectives of this study were i) to assess how different atmospheric constituents affect the atmospheric correction results in Sentinel-2 and WorldView-3 imagery, ii) to establish a relationship with field spectra measurements, and iii) to develop an empirical approach to ensure that SR values extracted from different EOS can be normalized for use in monitoring vegetation and land cover status. We compared surface reflectance values derived from Sentinel-2 images corrected with Sen2Cor, MODTRAN or FLAASH atmospheric correction approaches for the visible-to-near infrared regions. Additionally, this information was compared to SR values extracted from WorldView-3 imagery acquired from the same dates and location (Central Spain) and corrected with MODTRAN and FLAASH approaches. Assessment of the atmospheric correction was conducted by comparing satellite image SR with ground-truth spectra acquired with a FieldSpec hand-held spectroradiometer. The results emphasized the importance of using common atmospheric parameters collected from ancillary data sources (i.e. MODIS Atmosphere & Land products) to ensure a reliable SR comparison. When compared to field-collected spectral data, SR from corrected Sentinel-2 push-broom imagery showed a reliable match (<4% difference in the visible bands and <0.52% difference in the near infrared bands). However, SR imagery from the pointable WorldView-3 instrument showed significant deviation, likely resulting from the effects of steep off-nadir acquisition angles (24.6° to 39.1°) combined with surface anisotropy. The magnitude and sign of the deviation in SR differed depending on the vegetation type, wavelength and sun-surface-sensor geometry. Therefore, it was necessary to account for angular effects to ensure reliable comparisons of imagery from the different EOS. In this study, an empirical angular correction approach was developed based on calibrating each WorldView-3 band against the ground-truth spectra. This correction allowed for the accurate signal normalization of WorldView-3 and Sentinel-2 imagery SR in the visible-to-near infrared regions.

ESTIMASI BIOMASSA VEGETASI KEBUN RAYA BOGOR MENGGUNAKAN KOMBINASI CITRA WORLDVIEW-2 DAN ALGORITMA PEMELAJARAN MESIN

An effective and efficient measurement method is required for estimating the vegetation biomass of an area with high canopy density. The combination of WorldView-2 imagery and machine learning algorithms can be an alternative approach for estimating vegetation biomass in Bogor Botanic Gardens. The research aimed to determine the variables from WorldView-2 imagery that can be used to estimate the vegetation biomass of Bogor Botanic Gardens, to identity several types of machine learning algorithms that produce the best prediction in estimating vegetation biomass in the field, to estimate and to map vegetation biomass in Bogor Botanic Gardens. The variables that had a significant correlation with biomass were NIR-reflectance, Blue-Correlation, Green-Correlation, NIR-Mean, and NIR-Variance. The NIR-Mean variable was the most important variable for estimating vegetation biomass. The random forest algorithm produced the best model for estimating vegetation biomass with r, PBIAS, RMSE, MAE and RSR values of 0,83, -11,51%, 185,47 Mg/ha, 139,43 Mg/ha, and 0,56 respectively. The estimated vegetation biomass of the Bogor Botanic Gardens had a range from 6,27 to 1.576,90 Mg/ha with an average of 183,96 Mg/ha and total biomass of 13,23 Gg. The combination of WorldView-2 imagery and the Random Forest algorithm produced a good predictive model compared to Artificial Neural Network and Support Vector Machine for estimating the vegetation biomass of Bogor Botanic Gardens. Bogor Botanic Gardens has a very important role in climate change mitigation, especially for the Bogor City.

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.

An In-Flight Radiometric Calibration Method Considering Adjacency Effects for High-Resolution Optical Sensors Over Artificial Targets

When using a field calibration site to perform in-orbit radiometric calibration of a space-borne remote sensor, the measured signal by the sensor may contain radiation from adjacent pixels, due to scattering in the Earth’s atmosphere and the sensor viewing characteristics. If this is not accounted for in the modeling, the accuracy of the radiometric calibration will be reduced. Nonuniformities of the ground target are more significant for the calibration of high-resolution sensors. In addition, if the brightness contrast of neighboring targets is not small, the impact of the adjacency effects will be more significant. It is important to quantitatively analyze and estimate the influence of this kind of adjacency effects, to reduce the uncertainty of in-orbit radiometric calibration. To evaluate the adjacency effects caused by atmospheric multiple scattering, this article constructed a local atmospheric point spread function model using long time-series satellite-ground synchronous observation data and developed an adjacency effects simulation method, which considers background reflectance spectral information. Tests on Sentinel-2A and Worldview-3 imagery overpassing the Baotou calibration and validation site (Baotou C&V site) (China) indicate that the proposed modeling method can effectively account for the influence of the adjacency effects in vicarious calibration. Uncertainties of relevant parameters and their contributions to the calibration result were also analyzed, and uncertainty assessment results show that the vicarious radiometric calibration scheme considering adjacency effects correction can bring about a total uncertainty less than 7%.

Mapping and estimating harvest potential of seaweed culture using Worldview-2 Satellite images: a case study in Nusa Lembongan, Bali − Indonesia

Unreliable information on harvest potential is a persistent challenge for the Indonesian government and industry alike to manage an efficient supply chain of seaweed raw material. The use of remote sensing technology to assess seaweed harvest potential has been scarcely available in the literature. This current research aimed at estimating the harvest potential of seaweed Kappaphycus alvarezii through remote sensing using supervised classification with maximum likelihood (MLC) and contextual editing (CE) methods. This research evaluated the capabilities of different band combinations along with depth invariant index (DII) to enhance the remote sensing accuracy in estimating seaweed harvest potential. The seaweed classification using Worldview-2 imagery was compared with the in-situ references (ground-truthing). The potential data bias resulted from different imagery acquisition timestamps with the in-situ measurement was kept minimal as both data time stamps were ten days apart and within the same seaweed culture cycle. The average dry weight of all seaweed samples collected during the research was 924 ± 278.91 g/m2 with culture ages between 1 and 40 days. The classification results based on MLC+CE with a 5-band combination method without DII showed a better correlation and closer fit with the in-situ references compared to the other methods, with an overall accuracy of 79.05% and Tau coefficient value of 0.75. The estimated total harvest potential based on the combined seaweed classes was 531.26 ± 250.29 tons dry weight.

Multitemporal Relearning With Convolutional LSTM Models for Land Use Classification

In this article, we present a novel hybrid framework, which integrates spatial-temporal semantic segmentation with postclassification relearning, for multitemporal land use and land cover (LULC) classification based on very high resolution (VHR) satellite imagery. To efficiently obtain optimal multitemporal LULC classification maps, the hybrid framework utilizes a spatial-temporal semantic segmentation model to harness temporal dependency for extracting high-level spatial-temporal features. In addition, the principle of postclassification relearning is adopted to efficiently optimize model output. Thereby, the initial outcome of a semantic segmentation model is provided to a subsequent model via an extended input space to guide the learning of discriminative feature representations in an end-to-end fashion. Last, object-based voting is coupled with postclassification relearning for coping with the high intraclass and low interclass variances. The framework was tested with two different postclassification relearning strategies (i.e., pixel-based relearning and object-based relearning) and three convolutional neural network models, i.e., UNet, a simple Convolutional LSTM, and a UNet Convolutional-LSTM. The experiments were conducted on two datasets with LULC labels that contain rich semantic information and variant building morphologic features (e.g., informal settlements). Each dataset contains four time steps from WorldView-2 and Quickbird imagery. The experimental results unambiguously underline that the proposed framework is efficient in terms of classifying complex LULC maps with multitemporal VHR images.

Testing the value of freely available Landsat 8 Operational Land Imager (OLI) and OLI pan-sharpened imagery in discriminating commercial forest species

ABSTRACT The adoption of remotely sensed data in forest applications has grown significantly. Whereas high spatial resolution sensors have been successful in mapping and monitoring commercial forests, their cost, accessibility, and spatial coverage remain a critical challenge. Hence, it is was necessary to investigate the value of new and improved freely available sensors in forest species mapping using the Partial Least Square-Discriminant Analysis (PLS-DA). This study evaluated the performance of new freely available and improved raw and pan-sharpened Landsat 8 Operational Land Imager (OLI) imagery in discriminating seven key plantation forest species in KwaZulu-Natal, South Africa. Accuracies achieved using the Landsat (OLI) imagery were benchmarked against the WorldView-2 imagery. Results show that raw and pan-sharpened bands successfully delineated commercial forest species, with overall classification accuracies of 79% and 77.8%, respectively. Although these accuracies were lower than the 86.5% achieved from the higher resolution Worldview-2 image data, our findings demonstrate that the Landsat 8 OLI’s lower spatial resolution (30 m) generated a plausible performance in discriminating forest species. Hence, Landsat 8 OLI could be useful in providing existing and historical preliminary forestry assessment due to its free availability, wide spatial coverage as well as its rich archive dating back to the 1970s.

Geometric Accuracy Assessment of Deimos-2 Panchromatic Stereo Pairs: Sensor Orientation and Digital Surface Model Production.

Accurate elevation data, which can be extracted from very high-resolution (VHR) satellite images, are vital for many engineering and land planning applications. In this way, the main goal of this work is to evaluate the capabilities of VHR Deimos-2 panchromatic stereo pairs to obtain digital surface models (DSM) over different land covers (bare soil, urban and agricultural greenhouse areas). As a step prior to extracting the DSM, different orientation models based on refined rational polynomial coefficients (RPC) and a variable number of very accurate ground control points (GCPs) were tested. The best sensor orientation model for Deimos-2 L1B satellite images was the RPC model refined by a first-order polynomial adjustment (RPC1) supported on 12 accurate and evenly spatially distributed GCPs. Regarding the Deimos-2 based DSM, its completeness and vertical accuracy were compared with those obtained from a WorldView-2 panchromatic stereo pair by using exactly the same methodology and semiglobal matching (SGM) algorithm. The Deimos-2 showed worse completeness values (about 6% worse) and vertical accuracy results (RMSEZ 42.4% worse) than those computed from WorldView-2 imagery over the three land covers tested, although only urban areas yielded statistically significant differences (p < 0.05).

Species-level classification of urban trees from worldview-2 imagery in Debrecen, Hungary: an effective tool for planning a comprehensive green network to reduce dust pollution

Urban green spaces of cities are crucial elements of city structure that ensure habitat for species and ecological functionality of habitat patches, maintain biodiversity, and provide environmental services. However, detailed maps intended for planning and improving the existing network require a quick and effective technique for assessing the possibilities. Multispectral imagery is an accessible source for species-level classification of urban trees. Using a multispectral image from the WorldView–2 satellite sensor, we classified six of the most common urban tree species in Debrecen, Hungary. Maximum Likelihood (ML) and Support Vector Machine (SVM) classifiers were applied to different numbers of the MNF-transformed bands. The best overall accuracy was achieved with the ML algorithm applied to the first four transformed bands (75.1%), and with the SVM algorithm applied to eight bands (71.0%). In general, ML performed better than SVM. Despite the relatively low number of spectral bands, we achieved moderately good accuracy for basic vegetation mapping, which can be used in spatial planning and decision making. In a future interdisciplinary research study, we could merge the classification results with the dust adsorption capacity of individual species to assess the reduction of dust pollution by urban trees.

Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods

Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.

An Adaptive Blended Algorithm Approach for Deriving Bathymetry from Multispectral Imagery

The log-ratio method (LRM) proposed by Stumpf et al. has been widely used to map bathymetry from multispectral imagery for oligotrophic waters, while the selection criteria of bands for the LRM have been subject to tradeoffs between maximum detectable depth and sensitivity. In this article, we first applied a method for global sensitivity analysis to a semianalytical forward model of optically shallow waters with the WorldView-2 band-set. The results show that the sensitive wavelength band in water-leaving reflectance for water depth varies from the longer wavelength band to the shorter wavelength band with increasing water depth. Then, we developed an adaptive blended algorithm approach (ABAA) to seamlessly map bathymetry from the shallower region to the deeper region. The LRM with different band combinations was selected for the sub-algorithms of the ABAA. The subalgorithms and depth range used for each subalgorithm of the ABAA were automatically determined by the proposed applicable depth range analysis that considers logarithmic regression for the LRM. The ABAA was applied to WorldView-2 and Landsat-8 imagery of the Xisha Qundao. When the in situ bathymetry data are available, compared with the LRM with the blue and green bands, the ABAA significantly improves the accuracy of the estimated depth, especially for waters shallower than 6 m (root-mean- square error (RMSE) = 0.31 to 0.94 m for WorldView-2 data, RMSE= 0.25 to 1.42 m for Landsat-8 data). When the in situ bathymetry data are absent, the ABAA performs better than the LRM with a single band ratio and an optimization-based method overall.

EVALUATING ACOMP, FLAASH AND QUAC ON WORLDVIEW-3 FOR SATELLITE DERIVED BATHYMETRY (SDB) IN SHALLOW WATER

Bathymetry map is instrumental for monitoring marine ecosystem and supporting marine transportation. Optical satellite imagery has been widely utilised as an alternative method to derive bathymetry map in shallow water. Nonetheless, interactions between electromagnetic energy and Earth’s atmosphere causing the atmosphere effects pose a significant challenge in satellite-derived bathymetry (SDB) application. In this study, Worldview-3 imagery was used to obtain bathymetry map in shallow water. Three atmospheric correction models (ACOMP, FLAASH and QUAC) were employed to eliminate atmospheric effects on Worldview-3 imagery. Three simple band ratios involving coastal blue, blue, green and yellow band were used to test the performance of atmospheric correction models. ACOMP combined with blue and green band ratio efficaciously provided the best performance where it explained 77% of model values. Bathymetry map obtained from Worldview-3 was also validated using bathymetry data acquired from bathymetric survey over the study area. The estimated depths shared aggregable results with measured depths (depth &lt; 20 m) with accuracy of 2.07 m. This study shows that robust atmospheric correction combined with suitable simple band combinations offered bathymetry map retrieval with relatively high accuracy.

Probabilistic Mapping and Spatial Pattern Analysis of Grazing Lawns in Southern African Savannahs Using WorldView-3 Imagery and Machine Learning Techniques

Savannah grazing lawns are a key food resource for large herbivores such as blue wildebeest (Connochaetes taurinus), hippopotamus (Hippopotamus amphibius) and white rhino (Ceratotherium simum), and impact herbivore densities, movement and recruitment rates. They also exert a strong influence on fire behaviour including frequency, intensity and spread. Thus, variation in grazing lawn cover can have a profound impact on broader savannah ecosystem dynamics. However, knowledge of their present cover and distribution is limited. Importantly, we lack a robust, broad-scale approach for detecting and monitoring grazing lawns, which is critical to enhancing understanding of the ecology of these vital grassland systems. We selected two sites in the Lower Sabie and Satara regions of Kruger National Park, South Africa with mesic and semiarid conditions, respectively. Using spectral and texture features derived from WorldView-3 imagery, we (i) parameterised and assessed the quality of Random Forest (RF), Support Vector Machines (SVM), Classification and Regression Trees (CART) and Multilayer Perceptron (MLP) models for general discrimination of plant functional types (PFTs) within a sub-area of the Lower Sabie landscape, and (ii) compared model performance for probabilistic mapping of grazing lawns in the broader Lower Sabie and Satara landscapes. Further, we used spatial metrics to analyse spatial patterns in grazing lawn distribution in both landscapes along a gradient of distance from waterbodies. All machine learning models achieved high F-scores (F1) and overall accuracy (OA) scores in general savannah PFTs classification, with RF (F1 = 95.73±0.004%, OA = 94.16±0.004%), SVM (F1 = 95.64±0.002%, OA = 94.02±0.002%) and MLP (F1 = 95.71±0.003%, OA = 94.27±0.003%) forming a cluster of the better performing models and marginally outperforming CART (F1 = 92.74±0.006%, OA = 90.93±0.003%). Grazing lawn detection accuracy followed a similar trend within the Lower Sabie landscape, with RF, SVM, MLP and CART achieving F-scores of 0.89, 0.93, 0.94 and 0.81, respectively. Transferring models to the Satara landscape however resulted in relatively lower but high grazing lawn detection accuracies across models (RF = 0.87, SVM = 0.88, MLP = 0.85 and CART = 0.75). Results from spatial pattern analysis revealed a relatively higher proportion of grazing lawn cover under semiarid savannah conditions (Satara) compared to the mesic savannah landscape (Lower Sabie). Additionally, the results show strong negative correlation between grazing lawn spatial structure (fractional cover, patch size and connectivity) and distance from waterbodies, with larger and contiguous grazing lawn patches occurring in close proximity to waterbodies in both landscapes. The proposed machine learning approach provides a novel and robust workflow for accurate and consistent landscape-scale monitoring of grazing lawns, while our findings and research outputs provide timely information critical for understanding habitat heterogeneity in southern African savannahs.

Mapping eucalypts trees using high resolution multispectral images: A study comparing WorldView 2 vs. SPOT 7

Invasive alien plants are considered as a major threat to many ecological and socio-economic systems. Nevertheless, the management of some of these plants is often controversial due to the positive socio-economic and ecosystem roles they play. This necessitates proper mapping and monitoring of the extent and spatial distribution of such plants to prioritize resource allocation and management. However, mapping plant species using remote sensing in a heterogeneous environment such as an urban area is often challenged by high levels of spectral muddle. This study investigated the utility of the high and medium spectral and spatial resolution imageries from the WorldView-2 (WV-2) and SPOT-7 satellites, respectively, to map eucalypts trees in urban areas. Furthermore, the classification performances of Random Forest (RF) and Support Vector Machines (SVM) were compared. Both WV-2 and SPOT-7 imageries attained overall accuracies of 81.67% (0.78 kappa) and 72.78% (0.67 kappa), respectively, when the RF algorithm was used and 80% (0.76 Kappa) and 71.11% (0.65 Kappa), respectively when SVM algorithm was used. The user’s accuracies for the eucalypts class in both WV-2 and SPOT 7 imageries were 73.33% and 60%, respectively, for the RF and 70% and 56.67% for the SVM algorithm, respectively. Thus, WV-2 imagery is more suitable for mapping eucalypts trees in a heterogeneous urban environment. Therefore, the classification of WV-2 imageries using RF produced a relatively more accurate map of the eucalypts trees for the study areas, the southern part of Johannesburg city.

Semi-Automatic Building Extraction from WorldView-2 Imagery Using Taguchi Optimization

Due to the complex spectral and spatial structures of remotely sensed images, the delineation of land use/land cover classes using conventional approaches is a challenging task. This article tackles the problem of seeking optimal parameters of multi-resolution segmentation for a classification task using WorldView-2 imagery. Taguchi optimization was applied to search optimal parameters using the plateau objective function (&lt;small&gt;POF&lt;/small&gt;) and quality rate (&lt;small&gt;Qr&lt;/small&gt;) as fitness criteria. Analysis of variance was also used to estimate the contributions of the parameters for POF and Qr, separately. The scale parameter was the most effective one, with contribution levels of 87.45% and 56.87% for POF and Qr, respectively. Linear regression and support-vector regression methods were used to predict the results of the experiment. Test results revealed that Taguchi optimization was more effective than linear regression and support-vector regression for predicting POF and Qr values.

Performance across WorldView-2 and RapidEye for reproducible seagrass mapping

Satellite remote sensing offers an effective remedy to challenges in ground-based and aerial mapping that have previously impeded quantitative assessments of global seagrass extent. Commercial satellite platforms offer fine spatial resolution, an important consideration in patchy seagrass ecosystems. Currently, no consistent protocol exists for image processing of commercial data, limiting reproducibility and comparison across space and time. Additionally, the radiometric performance of commercial satellite sensors has not been assessed against the dark and variable targets characteristic of coastal waters. This study compared data products derived from two commercial satellites: DigitalGlobe's WorldView-2 and Planet's RapidEye. A single scene from each platform was obtained at St. Joseph Bay in Florida, USA, corresponding to a November 2010 field campaign. A reproducible processing regime was developed to transform imagery from basic products, as delivered from each company, into analysis-ready data usable for various scientific applications. Satellite-derived surface reflectances were compared against field measurements. WorldView-2 imagery exhibited high disagreement in the coastal blue and blue spectral bands, chronically overpredicting. RapidEye exhibited better agreement than WorldView-2, but overpredicted slightly across all spectral bands. A deep convolutional neural network was used to classify imagery into deep water, land, submerged sand, seagrass, and intertidal classes. Classification results were compared to seagrass maps derived from photointerpreted aerial imagery. This study offers the first radiometric assessment of WorldView-2 and RapidEye over a coastal system, revealing inherent calibration issues in shorter wavelengths of WorldView-2. Both platforms demonstrated as much as 97% agreement with aerial estimates, despite differing resolutions. Thus, calibration issues in WorldView-2 did not appear to interfere with classification accuracy, but could be problematic if estimating biomass. The image processing routine developed here offers a reproducible workflow for WorldView-2 and RapidEye imagery, which was tested in two additional coastal systems. This approach may become platform independent as more sensors become available.

Assessing Worldview-3 multispectral imaging abilities to map the tree diversity in semi-arid parklands

Semi-arid parkland agrosystems are strongly sensitive to climate change and anthropic pressure. In the context of sustainability research, trees are considered critical for various ecosystem services covering environment quality as well as food security and health. But their actual ecological impact on both cropland and natural vegetation is not well understood yet, and collecting spatial and structural information around agroforestry systems is becoming an important issue. Tree mapping in semi-arid parklands could be one of these prerequisites. While for obtaining an exhaustive inventory of individual trees and for analysing their spatial distribution, remote sensing is the ideal tool. However, it has been noted that depending on the spatial resolution and sensor spectral characteristics, tree species cannot be distinguished clearly, even in the sparsely vegetated semi-arid ecosystems of West Africa. Thus, this work focuses on assessing the capabilities of Worldview-3 imagery, acquired in 8 spectral bands, to detect, delineate, and identify certain key tree species in the Faidherbia albida parkland in Bambey, Senegal, based on a ground-truth database corresponding to 5000 trees. The tree crowns are delineated through NDVI thresholding and consecutive filtering to provide object-based radiometric signatures, radiometric indices, and textural information. A factorial discriminant analysis is then performed, which indicates that only four out of the seven most abundant species in the study area can be discriminated: “Faidherbia albida”,” Azadirachta indica”, “Balanites aegyptiaca” and “Tamarindus indica”. Next, random forest and support vector machine classifiers are employed to identify the optimal combination of classifier parameters to discriminate these classes with a high accuracy, robustness, and stability. The linear support vector machine with cost=1 and gamma=0.01 provides the optimal results with a global accuracy of 88 % and kappa of 0.71. This classifier is applied to the whole study area to map all the trees with crowns larger than 2 m, sorted in four identified species and a fifth common group of unidentified species. This map thus enables analysing the variability in tree density and the spatial distribution of different species. Such information can afterwards be correlated to the ecological functioning of the parkland and local practices, and offers promising opportunities to help future sustainability initiatives in different socio-ecological contexts.