High Spatial Resolution Multispectral Imagery Research Articles

Archaeology in the Fourth Dimension: Studying Landscapes with Multitemporal PlanetScope Satellite Data

AbstractFor the last seven years, PlanetScope satellites have started near-daily imaging of parts of the Earth’s surface, making high-density multitemporal, multispectral, 3-m pixel imagery accessible to researchers. Multitemporal satellite data enables landscape archaeologists to examine changes in environmental conditions at time scales ranging from daily to decadal. This kind of temporal resolution can accentuate landscape features on the ground by de-emphasizing non-permanent signatures caused by seasonal or even daily changes in vegetation. We argue that the availability of high spatial and temporal resolution multispectral imagery from Planet Inc. will enable new approaches to studying archaeological visibility in landscapes. While palimpsests are discrete overlapping layers of material accumulation, multitemporal composites capture cyclical and seasonal time and can be used to interpret past landscape histories at multiple scales. To illustrate this perspective, we present three case studies using PlanetScope imagery in tropical environments on the Indian Ocean islands of Madagascar, Mauritius, and Zanzibar.

Inversion of Nutrient Concentrations Using Machine Learning and Influencing Factors in Minjiang River

Remote sensing is widely used for lake-water-quality monitoring, but the inversion of the total nitrogen (TN) and total phosphorus (TP) of rivers and non-optical parameters is still a difficult problem. The use of high spatial and temporal resolution multispectral imagery combined with machine learning techniques is an effective solution for this difficulty. Three machine learning methods based on support vector regression (SVR), neural network (NN) and random forest (RF) were used to invert TN and TP using actual water-quality measurement data and Sentine-2 remote-sensing images, and analyzed the factors influencing water quality in terms of pollutant emissions and land use. The results show that RF performs the best in both TN (R2 = 0.800, RMSE = 0.640, MSE = 0.400, MAE = 0.480) and TP (R2 = 0.830, RMSE = 0.033, MSE = 0.001, MAE = 0.022) inversion models, and that the optimal selection of feature variables improves model performance. The TN and TP concentrations in the Minjiang River Meishan Water Function Development Zone were the highest in the downstream section and in 2018. Analysis of the factors influencing water quality shows that pollution sources and amounts were closely related to land-use types, and land use in riparian zones at different spatial scales had different degrees of impact on water quality.

Detection of Eucalyptus Leaf Disease with UAV Multispectral Imagery

Forest disease is one of the most important factors affecting tree growth and product quality, reducing economic values of forest ecosystem goods and services. In order to prevent and control forest diseases, accurate detection in a timely manner is essential. Unmanned aerial vehicles (UAVs) are becoming an important tool for acquiring multispectral imagery, but have not been extensively used for detection of forest diseases. This research project selected a eucalyptus forest as a case study to explore the performance of leaf disease detection using high spatial resolution multispectral imagery that had been acquired by UAVs. The key variables sensitive to eucalyptus leaf diseases, including spectral bands and vegetation indices, were identified by using a mutual information–based feature selection method, then distinguishing disease levels using random forest and spectral angle mapper approaches. The results show that green, red edge, and near-infrared wavelengths, nitrogen reflectance index, and greenness index are sensitive to forest diseases. The random forest classifier, based on a combination of sensitive spectral bands (green, red edge, and near-infrared wavelengths) and a nitrogen reflectance index, provided the best differentiation results for healthy and three disease severity levels (mild, moderate, and severe) with overall accuracy of 90.1% and kappa coefficient of 0.87. This research provides a new way to detect eucalyptus leaf diseases, and the proposed method may be suitable for other forest types.

Machine-Learning for Mapping and Monitoring Shallow Coral Reef Habitats

Mapping and monitoring coral reef benthic composition using remotely sensed imagery provides a large-scale inference of spatial and temporal dynamics. These maps have become essential components in marine science and management, with their utility being dependent upon accuracy, scale, and repeatability. One of the primary factors that affects the utility of a coral reef benthic composition map is the choice of the machine-learning algorithm used to classify the coral reef benthic classes. Current machine-learning algorithms used to map coral reef benthic composition and detect changes over time achieve moderate to high overall accuracies yet have not demonstrated spatio-temporal generalisation. The inability to generalise limits their scalability to only those reefs where in situ reference data samples are present. This limitation is becoming more pronounced given the rapid increase in the availability of high temporal (daily) and high spatial resolution (<5 m) multispectral satellite imagery. Therefore, there is presently a need to identify algorithms capable of spatio-temporal generalisation in order to increase the scalability of coral reef benthic composition mapping and change detection. This review focuses on the most commonly used machine-learning algorithms applied to map coral reef benthic composition and detect benthic changes over time using multispectral satellite imagery. The review then introduces convolutional neural networks that have recently demonstrated an ability to spatially and temporally generalise in relation to coral reef benthic mapping; and recurrent neural networks that have demonstrated spatio-temporal generalisation in the field of land cover change detection. A clear conclusion of this review is that existing convolutional neural network and recurrent neural network frameworks hold the most potential in relation to increasing the spatio-temporal scalability of coral reef benthic composition mapping and change detection due to their ability to spatially and temporally generalise.

NonRegSRNet: A Nonrigid Registration Hyperspectral Super-Resolution Network

Due to the limitations of imaging systems, satellite hyperspectral imagery (HSI), which yields rich spectral information in many channels, often suffers from poor spatial resolution. HSI super-resolution (SR) refers to the fusion of high spatial resolution multispectral imagery (MSI) and low spatial resolution HSI to generate HSI that has both a high spatial and high spectral resolution. However, most existing SR methods assume that the two original images used are perfectly registered: in reality, nonrigid deformation areas can exist locally in the two images even if prior registration of the control points has been carried out. To address this problem, we propose a novel unsupervised spectral unmixing and image deformation correction network&#x2014;NonRegSRNet&#x2014;with multimodal and multitask learning that can be used for the joint registration of HSI and MSI and to produce SR imagery. More specifically, NonRegSRNet integrates the dense registration and SR tasks into a unified model that includes a triplet convolutional neural network. This allows these two tasks to complement each other so that better registration and SR results can be achieved. Furthermore, because the point spread function (PSF) and spectral response function (SRF) are often unavailable, two special convolutional layers are designed to adaptively learn the parameters of the PSF and SRF, which makes the proposed model more adaptable. Experimental results demonstrate that the proposed method has the ability to produce highly accurate and stable reconstructed images under complex nonrigid deformation conditions. (Code available at <uri>https://github.com/saber-zero/NonRegSRNet</uri>)

Very high resolution aboveground carbon mapping in subtropical thicket

Aboveground carbon (AGC) maps will assist with the monitoring and verification of carbon stored through restoration of subtropical thicket. Field methods are required to capture AGC ground truth data at the plot scale, but they are highly impractical for large area mapping of carbon stocks. Against this background, a remote sensing method to estimate AGC from very high spatial resolution multi-spectral imagery was developed. AGC ground truth was acquired for 85 plots in a small study area in the Baviaanskloof, South Africa. Using the ground truth, univariate and multivariate snapshot models were developed to predict AGC from features in a 2017 WorldView-3 (0.34-m resolution 8-band) satellite image. Informative features were selected from a large set of spectral, textural, and vegetation index features using stepwise forward selection. Using this approach, the multivariate model produced a coefficient of determination (R2) of 0.886 and root mean square error of 2.862 t C ha − 1. This study demonstrates the efficacy of regression approaches for estimating AGC from multi-spectral imagery and provides a foundation for the spatial and temporal extension of AGC remote sensing in the thicket biome.

A global analysis of the temporal availability of PlanetScope high spatial resolution multi-spectral imagery

The PlanetScope CubeSat constellation is providing unprecedented global coverage, visible to near infrared, atmospherically corrected, 3 m imagery. The revisit interval between successive overpasses varies in space and time in a complex manner because of a variety of factors and particularly because of the different sensor orbits. The temporal availability of PlanetScope imagery is quantified in this study considering all of the publicly available images acquired globally for a 12 month period from December 1st 2019 to November 30th 2020. A total of 175.8 million images were acquired by the constellation that was composed of between 100 and 133 unique PlanetScope sensors each month and three sensor generations. The local morning overpass times of the three sensor generations were quantified and the most frequently occurring times were 10:16, 10:29, and 10:03 (to the nearest minute) with 90% of the images acquired with a range of morning overpass times of 2 h and 13 min, 1 h and 30 min, and 1 h and 50 min, for PlanetScope-0, PlanetScope-1, and PlanetScope-2, respectively. Maps, histograms and summary statistics of the total number of observations and revisit intervals are derived with respect to a global grid of 4.7 million land points spaced 5.6 km apart in the equal area sinusoidal projection. The annual and monthly number of PlanetScope observations and average revisit intervals did not vary in a geographically uniform manner. This is due to several factors including the different PlanetScope orbits, seasonal high latitude darkness at the time of sensor overpass, and because of the changing number of sensors on orbit as PlanetScope sensors were decommissioned and later generations became operational over the 12 month study period. In addition, the images in each frame of sensed data are not made available if they cannot be geolocated due to cloud and/or featureless or unstructured terrain precluding ground control matching. The PlanetScope constellation provided higher temporal resolution than provided by sensors such as Landsat-8 or Sentinel-2 although 9% of the global land grid locations, predominantly in the interior of Greenland and non-coastal Antarctica, had no observations. Considering the 12 months of global observations, the median average revisit interval was only 30.3 h, and 9.6%, 71.8%, and 88.4% of the land points had average revisit intervals <24 h, <36 h, and < 48 h, respectively. Globally, the median minimum revisit interval was 25 s and the median maximum revisit interval was 9.15 days; 95.4% of the land grid points had a minimum revisit <180 s, and 89.1% had a maximum revisit <480 h (20 days). The PlanetScope images are labelled as “standard” or as “test” quality based on solar geometry, saturated pixel, and geolocation accuracy criteria. The median annual proportion of observations labelled as “standard” at each land grid point over the 12 months was 78.14%. A global cloud analysis was undertaken to quantify the probability of there being at least one and at least two cloud-free PlanetScope observations within 5, 7 and 10 day consecutive periods. Lower probabilities occurred in cloudy regions and where there were fewer observations. The global mean average probability of there being at least one cloud-free observation over the 12 study months was 0.84, 0.88 and 0.92 for the 5, 7 and 10 day periods respectively. The global mean average probability of there being at least two cloud-free observations was 0.65, 0.76 and 0.84 for the 5, 7 and 10 day periods respectively. The probabilities varied seasonally and the northern hemisphere winter (December–February) and spring (March–May) had lower and higher global mean average seasonal probabilities, respectively, than those derived over the 12 months. The high temporal global coverage provided by the PlanetScope constellation will benefit new applications in particular those concerned with assessment of rapidly changing phenomena and assessment of phenomena that cannot be resolved at moderate and coarse resolution.

USE OF VERY HIGH SPATIAL RESOLUTION IMAGERY FOR MAPPING WOOD ENERGY POTENTIAL FROM TROPICAL MANAGED FOREST STANDS, REUNION ISLAND

Abstract. The development of a sustainable wood energy chain is an essential part of ecological and energy transition in Reunion Island (Indian Ocean), where Acacia mearnsii is the main potential wood energy resource identified to date. In order to assess future wood biomass supply chain strategies, a major first issue is to gain knowledge of the spatial distribution of this species forest stands.In this study, we assessed the potential of very high spatial resolution multispectral imagery for mapping the main forest stands in a study area located the Western Highlands region, where Acacia mearnsii expands alongside Acacia heterophylla, an endemic forest species and Cryptomeria japonica, an exotic forest stand. A reference database including 150 samples of seven classes (Acacia mearnsii (mature and non-mature), Acacia heterophylla (mature and non-mature), Cryptomeria japonica, ‘herbaceous areas’, and ‘bare soils’) was used to classify a Pleiades image acquired in May 2020. Spectral and textural indices were used in an incremental classification procedure using a random classifier.The best results (Kappa = 0.84, global accuracy = 84%) were obtained for the classification using all spectral and textural bands. The resulting map enables analyzing the spatial distribution of the different forest stands.

Forest roads extraction through a convolution neural network aided method

ABSTRACT Forest roads are important features of the environment that have significant impacts on wildlife habitats. The U-net and U-shaped Fully Convoluted Network (FCN) deep-learning methods have demonstrated great potential in successfully extracting paved roads in urban environments; however, they require a large amount of pixel-based training samples, which is resource-consuming. During this study, a convolutional neural network (CNN) aided method for forest road identification and extraction was developed. The algorithm utilized the multivariate Gaussian and Laplacian of Gaussian (LoG) filters and VGG 16 on high spatial resolution multispectral imagery to extract both primary road and secondary roads in forested areas. It was tested on imagery over two areas in the Hearst forest located in central Ontario, Canada. Based on validation against manually digitized roads, over 74% of the roads from both test areas were successfully extracted.

Delineation of Individual Tree Crowns Using High Spatial Resolution Multispectral WorldView-3 Satellite Imagery

Delineation of individual tree crowns can provide valuable information for sustainable forest management and environmental protection. However, it is hard to find a reliable tree crown delineation method that can continually generate expected results in high spatial resolution multispectral satellite images, because most of the existing methods need user-assigned parameters that greatly affect the quality of the delineation results. In this article, we propose a method based on the marker-controlled watershed segmentation to delineate individual tree crowns using high spatial resolution multispectral WorldView-3 satellite imagery. A gradient binarization process is proposed to accurately locate tree crown borders. The threshold for the binarization is determined by a supervised searching process. Markers used in marker-controlled watershed segmentation are spatial local maxima detected from the information provided by tree crown borders. Moreover, the definition of spatial local maxima from the literature is improved to eliminate false treetops. To validate the performance of the proposed delineation method, delineation results are compared with those obtained from the spectral angle segmentation (SAS) method that has been proposed in literature because the quality of delineation results generated by SAS does not rely on user-assigned parameters. The experiment results in two test images demonstrate that the proposed method outperforms SAS in terms of both delineation accuracy and visual quality of the delineation map. Moreover, it is proved that the modified spatial local maxima are more reliable for detecting treetops.

Tree species classification using UAS-based digital aerial photogrammetry point clouds and multispectral imageries in subtropical natural forests

Tree species composition of forest stand is an important indicator of forest inventory attributes for assessing ecosystem health, understanding successional processes, and digitally displaying forest biodiversity. In this study, we acquired high spatial resolution multispectral and RGB imagery over a subtropical natural forest in southwest China using a fixed-wing UAV system. Digital aerial photogrammetric (DAP) technique was used to generate multi-spectral and RGB derived point clouds, upon which individual tree crown (ITC) delineation algorithms and a machine learning classifier were used to identify dominant tree species. To do so, the structure-from-motion method was used to generate RGB imagery-based DAP point clouds. Then, three ITC delineation algorithms (i.e., point cloud segmentation (PCS), image-based multiresolution segmentation (IMRS), and advanced multiresolution segmentation (AMRS)) were used and assessed for ITC detection. Finally, tree-level metrics (i.e., multispectral, texture and point cloud metrics) were used as metrics in the random forest classifier used to classify eight dominant tree species. Results indicated that the accuracy of the AMRS ITC segmentation was highest (F1-score = 82.5 %), followed by the segmentation using PCS (F1-score = 79.6 %), the IMRS exhibited the lowest accuracy (F1-score = 78.6 %); forest types classification (coniferous and deciduous) had a higher accuracy than the classification of all eight tree species, and the combination of spectral, texture and structural metrics had the highest classification accuracy (overall accuracy = 80.20 %). In the classification of both eight tree species and two forest types, the classification accuracies were lowest when only using spectral metrics, indicated that the texture metrics and point cloud structural metrics had a positive impact on the classification (the overall accuracy and kappa accuracy increased by 1.49–4.46 % and 2.86–6.84 %, respectively).

Arctic greening associated with lengthening growing seasons in Northern Alaska

Many studies have reported that the Arctic is greening; however, we lack an understanding of the detailed patterns and processes that are leading to this observed greening. The normalized difference vegetation index (NDVI) is used to quantify greening, which has had largely positive trends over the last few decades using low spatial resolution satellite imagery such as AVHRR or MODIS over the pan-Arctic region. However, substantial fine scale spatial heterogeneity in the Arctic makes this large-scale investigation hard to interpret in terms of vegetation and other environmental changes. Here we focus on one area of the northern Alaskan Arctic using high spatial resolution (4 m) multispectral satellite imagery from DigitalGlobe™ to analyze the greening trend near Utqiaġvik (formerly known as Barrow) over 14 years from 2002 to 2016. We found that tundra vegetation has been greening (τ = 0.65, p = 0.01, NDVI increase of 0.01 yr−1) despite no overall change in vegetation community composition. The greening is most closely correlated to the number of thawing degree days (R2 = 0.77, F = 21.5, p < 0.001) which increased in a similar linear trend over the 14 year study period (1.79 ± 0.50 days per year, p < 0.01, τ = −0.56). This suggests that in this Arctic ecosystem, greening is occurring due to a lengthening growing season that appears to stimulate plant productivity without any significant change in vegetation communities. We found that vegetation communities in wetter locations greened about twice as fast as those found in drier conditions supporting the hypothesis that these communities respond more strongly to warming. We suggest that in Arctic environments, vegetation productivity may continue to rise, particularly in wet areas.

Urban Tree Species Classification Using a WorldView-2/3 and LiDAR Data Fusion Approach and Deep Learning.

Urban areas feature complex and heterogeneous land covers which create challenging issues for tree species classification. The increased availability of high spatial resolution multispectral satellite imagery and LiDAR datasets combined with the recent evolution of deep learning within remote sensing for object detection and scene classification, provide promising opportunities to map individual tree species with greater accuracy and resolution. However, there are knowledge gaps that are related to the contribution of Worldview-3 SWIR bands, very high resolution PAN band and LiDAR data in detailed tree species mapping. Additionally, contemporary deep learning methods are hampered by lack of training samples and difficulties of preparing training data. The objective of this study was to examine the potential of a novel deep learning method, Dense Convolutional Network (DenseNet), to identify dominant individual tree species in a complex urban environment within a fused image of WorldView-2 VNIR, Worldview-3 SWIR and LiDAR datasets. DenseNet results were compared against two popular machine classifiers in remote sensing image analysis, Random Forest (RF) and Support Vector Machine (SVM). Our results demonstrated that: (1) utilizing a data fusion approach beginning with VNIR and adding SWIR, LiDAR, and panchromatic (PAN) bands increased the overall accuracy of the DenseNet classifier from 75.9% to 76.8%, 81.1% and 82.6%, respectively. (2) DenseNet significantly outperformed RF and SVM for the classification of eight dominant tree species with an overall accuracy of 82.6%, compared to 51.8% and 52% for SVM and RF classifiers, respectively. (3) DenseNet maintained superior performance over RF and SVM classifiers under restricted training sample quantities which is a major limiting factor for deep learning techniques. Overall, the study reveals that DenseNet is more effective for urban tree species classification as it outperforms the popular RF and SVM techniques when working with highly complex image scenes regardless of training sample size.

Application of WorldView-3 imagery and ASTER TIR data to map alteration minerals associated with the Rodalquilar gold deposits, southeast Spain

The Rodalquilar epithermal quartz-alunite gold deposits that occur within the Rodalquilar caldera complex in southeast Spain, are associated with a pronounced hydrothermal alteration of the country rocks. The hydrothermal alteration zones that are exposed on the surface consist of the vuggy silica zone, the advanced argillic alteration zone, the intermediate argillic alteration zone, the propylitic alteration zone, and a second stage supergene acid sulfate alteration. High spatial resolution multispectral imagery recorded by the WorldView-3 satellite was used in this study to map the spatial distribution of the main alteration minerals in the Rodalquilar caldera complex. Thermal infrared (TIR) data of the ASTER satellite were used to detect the quartz-rich zones. The analysis of the Rodalquilar WorldView-3 data was based on the Adaptive Coherence Estimator (ACE), a partial unmixing algorithm. The ACE processing accurately mapped the spatial distribution of alunite, kaolinite, illite and goethite. Alunite is abundant in the vuggy silica and advanced argillic alteration zones, and in the second stage supergene acid sulfate alteration. Kaolinite is predominant in the intermediate argillic alteration zone. Illite is abundant in the outer parts of the intermediate argillic alteration zone. Goethite image maps gossans that mainly occur in the vuggy silica and advanced argillic alteration zones, and in the areas characterized by the second stage supergene acid sulfate alteration. The detection of quartz-rich zones from the ASTER TIR data complemented the WorldView-3 mapping results. The study shows the efficiency of high spatial resolution multispectral remote sensing imagery recorded by the WorldView-3 satellite for district-level mineral exploration studies.

Monitoring opencast mine restorations using Unmanned Aerial System (UAS) imagery

Open-pit mine is still an unavoidable activity but can become unsustainable without the restoration of degraded sites. Monitoring the restoration after extractive activities is a legal requirement for mine companies and public administrations in many countries, involving financial provisions for environmental liabilities. The objective of this contribution is to present a rigorous, low-cost and easy-to-use application of Unmanned Aerial Systems (UAS) for supporting opencast mining and restoration monitoring, complementing the inspections with very high (<10 cm) spatial resolution multispectral imagery, and improving any restoration documentation with detailed land cover maps. The potential of UAS as a tool to control restoration works is presented in a calcareous quarry that has undergone different post-mining restoration actions in the last 20 years, representing 4 reclaimed stages. We used a small (<2 kg) drone equipped with a multispectral sensor, along with field spectroradiometer measurements that were used to radiometrically correct the UAS sensor data. Imagery was processed with photogrammetric and Remote Sensing and Geographical Information Systems software, resulting in spectral information, vegetation and soil indices, structural information and land cover maps. Spectral data and land cover classification, which were validated through ground-truth plots, aided in the detection and quantification of mine waste dumping, bare soil and other land cover extension. Moreover, plant formations and vegetation development were evaluated, allowing a quantitative, but at the same time visual and intuitive comparison with the surrounding reference systems. The protocol resulting from this research constitutes a pipeline solution intended for the implementation by public administrations and privates companies for precisely evaluating restoration dynamics in an expedient manner at a very affordable budget. Furthermore, the proposed solution prevents subjective interpretations by providing objective data, which integrate new technologies at the service of scientists, environmental managers and decision makers.

A Novel Classification Optimization Approach Integrating Class Adaptive MRF and Fuzzy Local Information for High Spatial Resolution Multispectral Imagery

This paper develops a novel classification optimization approach integrating class adaptive Markov Random Field (MRF) and fuzzy local information (CAMRF-FLI) for high spatial resolution multispectral imagery (HSRMI). Firstly, the raw classification results, including initial fuzzy memberships and class labels of every pixel, are achieved by a pixel-wise classification method for a given image. Secondly, the class adaptive MRF-based data energy function is developed to integrate class spatial dependency information. Thirdly, a novel spatial energy function integrating fuzzy local information is constructed. Finally, based on the total of data and spatial energies, the raw classification map is regularized by a global minimization of the energy function using its iterated conditional modes (ICM). The effectiveness of CAMRF-FLI is performed by two data sets. The results indicate it can refine the classification map in homogeneous areas, meanwhile, reduce most of the edge blurring artifact, and improve the classification accuracy compared with some conventional approaches.

Remote sensing of tamarisk beetle (Diorhabda carinulata) impacts along 412 km of the Colorado River in the Grand Canyon, Arizona, USA

Tamarisk (Tamarix spp.) is an invasive plant species that is rapidly expanding along arid and semi-arid rivers in the western United States. A biocontrol agent, tamarisk beetle (Diorhabda carinulata), was released in 2001 in California, Colorado, Utah, and Texas. In 2009, the tamarisk beetle was found further south than anticipated in the Colorado River ecosystem within the Grand Canyon National Park and Glen Canyon National Recreation Area. Our objectives were to classify tamarisk stands along 412 km of the Colorado River from the Glen Canyon Dam through the Grand Canyon National Park using 2009 aerial, high spatial resolution multispectral imagery, and then quantify tamarisk beetle impacts by comparing the pre-beetle images from 2009 with 2013 post-beetle images. We classified tamarisk presence in 2009 using the Mahalanobis Distance method with a total of 2500 training samples, and assessed the classification accuracy with an independent set of 7858 samples across 49 image quads. A total of 214 ha of tamarisk were detected in 2009 along the Colorado River, where each image quad, on average, included an 8.4 km segment of the river. Tamarisk detection accuracies varied across the 49 image quads, but the combined overall accuracy across the entire study region was 74%. Using the Normalized Difference Vegetation Index (NDVI) from 2009 and 2013 with a region-specific ratio of >1.5 decline between the two image dates (2009NDVI/2013NDVI), we detected tamarisk defoliation due to beetle herbivory. The total beetle-impacted tamarisk area was 32 ha across the study region, where tamarisk defoliation ranged 1–86% at the local levels. Our tamarisk classification can aid long-term efforts to monitor the spread and impact of the beetle along the river and the eventual mortality of tamarisk due to beetle impacts. Identifying areas of tamarisk defoliation is a useful ecological indicator for managers to plan restoration and tamarisk removal efforts.

Deciduous tree species classification using object-based analysis and machine learning with unmanned aerial vehicle multispectral data

ABSTRACTObject-based image analysis and machine-learning classification were applied to multispectral camera array data acquired by a small rotating blade unmanned aerial vehicle (UAV) over a hardwood forest in eastern Ontario. White birch, aspen, and two species of maple were surveyed in the field. Images were segmented and the resulting objects were visually confirmed to correspond with the sampled tree crowns. Following the application of machine-learning classification using the Random Forest algorithm, an independent validation sample of 23 tree crowns was, overall, approximately 78% correct. Aspen and birch were the most distinct species; the two maples appeared to be confused with each other and with immature trees and understory shrubs. Classification accuracy, commission errors, and variable importance were interpreted to be consistent with experience documented in aerial photointerpretation selection and elimination keys for northern hardwoods. Additional tests are recommended to more fully analyse the accuracy of deciduous tree species classification using digital analysis of high spatial resolution multispectral UAV imagery.

Detection of Hydromorphologic Characteristics of Indus River Estuary, Pakistan, Using Satellite and Field Data

Natural and anthropogenic factors directly determine the hydromorphologic and ecologic equilibrium of riverine environment. The present study was designed to detect the hydromorphologic characteristics of Indus River Estuary (IRE) using medium and high spatial resolution multispectral satellite imagery along with field data. Qualitative (visual) and quantitative (analytical) analysis was undertaken, and accuracy of each method as well as remotely sensed data was assessed. Single-band density slicing method was used for water bodies, while multiband supervised and unsupervised classification methods were adopted for the identification of hydromorphologic habitat along with key ecologic features of the IRE. The analysis of satellite imagery showed that the shortwave infrared-2 (band 7) of Landsat-8 Operational Land Imager (OLI) sensor performed better than its visible bands for delineating water bodies. The overall classification accuracy was 89%. Supervised classification with the maximum likelihood algorithm performed better for OLI imagery (30 m) than high spatial resolution RapidEye (5 m) imagery. However, unsupervised classification method was not suitable due to the significant overlapping of inter- and intra-class pixels. Overall, due to its adequate spectral range Landsat OLI imagery was utilized for monitoring of terrestrial water bodies and their morphologic features. Thus, we recommend that selecting the spatial resolution of the imagery should be based on the size of the objects to be recognized.

Object-based habitat mapping using very high spatial resolution multispectral and hyperspectral imagery with LiDAR data

This study investigated the combined use of multispectral/hyperspectral imagery and LiDAR data for habitat mapping across parts of south Cumbria, North West England. The methodology adopted in this study integrated spectral information contained in pansharp QuickBird multispectral/AISA Eagle hyperspectral imagery and LiDAR-derived measures with object-based machine learning classifiers and ensemble analysis techniques. Using the LiDAR point cloud data, elevation models (such as the Digital Surface Model and Digital Terrain Model raster) and intensity features were extracted directly. The LiDAR-derived measures exploited in this study included Canopy Height Model, intensity and topographic information (i.e. mean, maximum and standard deviation). These three LiDAR measures were combined with spectral information contained in the pansharp QuickBird and Eagle MNF transformed imagery for image classification experiments. A fusion of pansharp QuickBird multispectral and Eagle MNF hyperspectral imagery with all LiDAR-derived measures generated the best classification accuracies, 89.8 and 92.6% respectively. These results were generated with the Support Vector Machine and Random Forest machine learning algorithms respectively. The ensemble analysis of all three learning machine classifiers for the pansharp QuickBird and Eagle MNF fused data outputs did not significantly increase the overall classification accuracy. Results of the study demonstrate the potential of combining either very high spatial resolution multispectral or hyperspectral imagery with LiDAR data for habitat mapping.