Search

Estimating forest biomass is a necessary task to assess the carbon sequestration potential and storage, which serves to evaluate the environmental value of forests. It is possible to develop models for predicting forest biomass by combining remote sensing, field data and statistical models. In this study, we assessed the feasibility of estimating aboveground biomass (AGB) of Rhizophora apiculata plantation forests in Thanh Phu Nature Reserve by combining PlanetScope imagery and field inventory data obtained from 55 sample plots. Furthermore, we investigated the potential to enhance the accuracy of AGB estimation by applying four statistical models, generalized linear model (GLM), generalized exponential model (GEM), support vector machine (SVM) and random forest (RF). Our results showed that incorporating gray—level co-occurrence matrix (GLCM) texture features led to a more robust AGB estimation compared to using only spectral bands or vegetation indices. The RF model achieved the highest accuracy of AGB estimation based on the combination of spectral bands, vegetation indices and the optimum texture features, with an R2 value of 0.77. In addition, the spectral and texture features of the green and near-infrared bands were also important in predicting AGB. Finally, the results indicated that PlanetScope imagery has a great potential for mapping the AGB of R. apiculata plantations in mangrove forests, with relatively good accuracy (e.g., 78.26 and 86.36% for low and high values, respectively). [ABSTRACT FROM AUTHOR]

Estimating the number of trees within a forest stand, i.e., the forest stand density (FSD), is challenging at large scales. Recently, researchers have turned to a combination of remote sensing and machine learning techniques to derive these estimates. However, in most cases, the developed models rely heavily upon additional data such as LiDAR-based elevations or multispectral information and are mostly applied to managed environments rather than natural/mixed forests. Furthermore, they often require the time-consuming manual digitization or masking of target features, or an annotation using a bounding box rather than a simple point annotation. Here, we introduce the Tree Convolutional Row Neural Network (Tree-CRowNN), an alternative model for tree counting inspired by Multiple-Column Neural Network architecture to estimate the FSD over 12.8 m × 12.8 m plots from high-resolution RGB aerial imagery. Our model predicts the FSD with very high accuracy (MAE: ±2.1 stems/12.8 m2, RMSE: 3.0) over a range of forest conditions and shows promise in linking to Sentinel-2 imagery for broad-scale mapping (R2: 0.43, RMSE: 3.9 stems/12.8 m2). We believe that the satellite imagery linkage will be strengthened with future efforts, and transfer learning will enable the Tree-CRowNN model to predict the FSD accurately in other ecozones. [ABSTRACT FROM AUTHOR]

The photovoltaic (PV) industry boom has accelerated the need for accurately understanding the spatial distribution of PV energy systems. The synergy of remote sensing and artificial intelligence presents significant prospects for PV energy monitoring. Currently, numerous studies have focused on extracting rooftop PV systems from airborne or satellite imagery, but their small-scale and size-varying characteristics make the segmentation results suffer from PV internal incompleteness and small PV omission. To address these issues, this study proposed a size-aware deep learning network called Rooftop PV Segmenter (RPS) for segmenting small-scale rooftop PV systems from high-resolution imagery. In detail, the RPS network introduced a Semantic Refinement Module (SRM) to sense size variations of PV panels and reconstruct high-resolution deep semantic features. Moreover, a Feature Aggregation Module (FAM) enhanced the representation of robust features by continuously aggregating deeper features into shallower ones. In the output stage, a Deep Supervised Fusion Module (DSFM) was employed to constrain and fuse the outputs at different scales to achieve more refined segmentation. The proposed RPS network was tested and shown to outperform other models in producing segmentation results closer to the ground truth, with the F1 score and IoU reaching 0.9186 and 0.8495 on the publicly available California Distributed Solar PV Array Dataset (C-DSPV Dataset), and 0.9608 and 0.9246 on the self-annotated Heilbronn Rooftop PV System Dataset (H-RPVS Dataset). This study has provided an effective solution for obtaining a refined small-scale energy distribution database. [ABSTRACT FROM AUTHOR]

The sweet potato is an essential food and economic crop that is often threatened by the devastating sweet potato virus disease (SPVD), especially in developing countries. Traditional laboratory-based direct detection methods and field scouting are commonly used to rapidly detect SPVD. However, these molecular-based methods are costly and disruptive, while field scouting is subjective, labor-intensive, and time-consuming. In this study, we propose a deep learning-based object detection framework to assess the feasibility of detecting SPVD from ground and aerial high-resolution images. We proposed a novel object detector called SPVDet, as well as a lightweight version called SPVDet-Nano, using a single-level feature. These detectors were prototyped based on a small-scale publicly available benchmark dataset (PASCAL VOC 2012) and compared to mainstream feature pyramid object detectors using a leading large-scale publicly available benchmark dataset (MS COCO 2017). The learned model weights from this dataset were then transferred to fine-tune the detectors and directly analyze our self-made SPVD dataset encompassing one category and 1074 objects, incorporating the slicing aided hyper inference (SAHI) technology. The results showed that SPVDet outperformed both its single-level counterparts and several mainstream feature pyramid detectors. Furthermore, the introduction of SAHI techniques significantly improved the detection accuracy of SPVDet by 14% in terms of mean average precision (mAP) in both ground and aerial images, and yielded the best detection accuracy of 78.1% from close-up perspectives. These findings demonstrate the feasibility of detecting SPVD from ground and unmanned aerial vehicle (UAV) high-resolution images using the deep learning-based SPVDet object detector proposed here. They also have great implications for broader applications in high-throughput phenotyping of sweet potatoes under biotic stresses, which could accelerate the screening process for genetic resistance against SPVD in plant breeding and provide timely decision support for production management. [ABSTRACT FROM AUTHOR]

Urban planning within Riyadh, the capital of Saudi Arabia, has been impacted by the presence of informal settlements. An understanding of the spatial distribution of these settlements is essential in developing urban policies. This study used remotely sensed imagery to evaluate and characterize informal settlements within the city, both with and without expert knowledge of the study area (defined as expert knowledge, EK). An informal settlement ontology for four study sites within Riyadh City was developed using an analytical hierarchy process (AHP). Local knowledge was translated into a ruleset to identify and map settlement areas using spatial, spectral, textural, and geometric techniques. These were combined with an object-based image analysis (OBIA) approach. The study demonstrated that combining expert knowledge and remotely sensed data can efficiently and accurately identify informal settlements. Two classified images were produced, one with EK, and one without EK, to investigate how a detailed understanding of local conditions could affect the final image classification. Overall accuracy when using EK was 94%, with a kappa coefficient of 89%, while without EK accuracy was 68% (kappa coefficient of 61%). The final OBIA classes included formal and informal settlements, road networks, vacant blocks, shaded areas, and vegetation. This study demonstrated that local expert knowledge and OBIA helpful in urban mapping. It also indicated the value of integrating a local ontological process during digital image classification. This work provided improved techniques for mapping informal settlements in Middle Eastern cities. [ABSTRACT FROM AUTHOR]

Spartina alterniflora (smooth cordgrass), China's most common invasive species, has posed significant challenges to native plant communities and coastal environments. Monitoring the invasion and dieback process of S. alterniflora by multisource high-resolution imagery is necessary to manage the invasion of the species. Current spatial analyses, however, are insufficient. As a result, we first extracted S. alterniflora by integrating multisource high-resolution images through the multiscale object-oriented classification method, then identified the expansion patterns of S. alterniflora on the seaward side by the landscape expansion index, and conformed the main drivers of S. alterniflora dieback on the landward side in the Jiangsu Dafeng Milu National Nature Reserve. The findings revealed that the area of S. alterniflora decreased in size from 1511.26 ha in 2010 to 910.25 ha in 2020. S. alterniflora continues to grow to the sea and along the tidal creek on the seaward side, with a total increase of 159.13 ha. External isolation expansion patterns accounted for 65.16% of the total expansion patches, with marginal expansion patches accounting for 24.22% and tidal creek-leading expansion patches accounting for 10.62%. While the landward side showed a declining trend, the total area decreased by 852.36 ha, with an annual average change rate of 8.67%. S. alterniflora dieback was negatively related to the number of tidal creeks and positively related to the number of wild Elaphures davidianus and the length of artificial ditches. Our findings provide a scientific foundation for the ecological control of S. alterniflora. Its presence in coastal wetlands inspires evidence-based protection and management strategies to protect the coastal wetland ecosystem. [ABSTRACT FROM AUTHOR]

Proliferation of plastic-covered greenhouse (PCG) farming areas has been unparalleled in recent decades around the globe. Therefore, PCG's proper mapping and continuous monitoring are required to maintain protected farming sustainability and to reduce plastic pollution. Topography is one of the key factors affecting PCG mapping accuracy from satellite imagery. In this research, in order to understand the influence of elevation on PCG mapping accuracy in a Moroccan (with altitude below 200 m) and Vietnamese (an average altitude of 1,500 m) area, five supervised algorithms were applied to high-resolution PlanetScope and RapidEye imagery: maximum likelihood classification (MLC), k-nearest neighbours (k-NN), random forest (RF), support vector machine with linear kernel (SVML) and radial basis kernel (SVMRB). The findings indicated that k-NN (SVMRB) produced the greatest overall accuracy, followed by SVMRB (RF) for Dalat City (Loukkos). The present study also found that RapidEye outperforms PlanetScope in both areas and independently of the machine learning algorithm. Elevation data inclusion significantly improves (1.6% to 6.8%) various satellites' performance, particularly in Dalat City. Thus, this study demonstrated that topography has an impact on PCG mapping, especially in hilly areas. [ABSTRACT FROM AUTHOR]

Digital elevation models (DEMs) provide fundamental data for scientific and engineering applications in lunar exploration missions. Lunar DEMs have been mainly generated by laser altimetry and stereophotogrammetry. Complementarity to stereo photogrammetry, reflection-based surface reconstruction methods, such as shape from shading (SFS), have been studied and applied in lunar DEM reconstruction from a single image. However, this method often suffers from solution ambiguity and instability. In this paper, we propose a generative adversarial network (GAN)-based method that is able to generate high-resolution pixel-scale DEMs from a single image aided by a low-resolution DEM. We have evaluated the accuracy of the reconstructed high-resolution DEMs from 25 LROC NAC images of four regions using LROC NAC DEMs (2 m/pixel) as ground truth. The experimental results demonstrate good accuracy and adaptability to changes in illumination conditions. The root mean square error (RMSE) can reach about 2 m in areas where the degree of elevation variation is less than 100 m, and the RMSE value ranges from around 3 m to 10 m without considering the degree of the elevation variation in large-area reconstruction. As high-resolution monocular images and low-resolution DEMs are available for the entire lunar surface, the proposed GAN-based method has great potential in high-resolution lunar DEM reconstruction for lunar mapping applications. [ABSTRACT FROM AUTHOR]

The increasing development of imaging technology has made aerial image analysis one of the most widely used fields in image processing. Building extraction is the basic step in analysing urban structures, detecting construction violations, updating urban geographical divisions, and forecasting natural disasters. In this study, the aim is to automatically segment buildings in high-resolution satellite images using a new hybrid deep learning model, named Gated Residual Supervision Network (GRSNet). GRSNet extends the UNet framework by including three important components, i.e. attention gates (AG), residual units, and deep supervision part, with the main focus on transferring and reusing features. At first, the AG mechanism utilizes channel and spatial fine features to merge them effectively and deep supervision transfers feature details from the depths of the network. Then, residual units retrieve the information at different levels to train the model quickly. Finally, a fully connected classifier recovers features from the input image. GRSNet is evaluated on Massachusetts buildings public dataset and Inria aerial image labeling benchmark. The obtained results show the superiority of the proposed method compared to other deep learning-based state-of-the-art building segmentation methods with an intersection over union (IOU) of 89.86% and an F1-score of 94.53%. [ABSTRACT FROM AUTHOR]

Landslide extraction is one of the most popular topics in remote sensing. Numerous techniques have been proposed to manage the landslide identification problem. However, most aim to extract landslides that have already occurred or delineate the potential landslide manually. It is greatly important to identify and delineate potential landslides automatically, which has not been investigated. In this paper, we propose an automatic identification and delineation method, i.e., object-based image analysis (OBIA) of potential landslides by integrating optical imagery with a deformation map. We applied a deformation map generated by the interferometric synthetic aperture radar (InSAR) technique, rather than the digital elevation model (DEM) for landslide segmentation. Then, we used a classification and regression tree (CART) model with the spectral, spatial, contextual and deformation characteristics for landslide classification. For accuracy assessment, we implemented the evaluation indicators of recall and precision. The proposed method is verified in both specific landslide-prone regions (Jinpingzi and Shuanglongtan landslides) and a large catchment of the Jinsha River, China. By comparing our results with the ones using purely optical imagery, the precision of the Jinpingzi landslide is improved by 14.12%, and the recall and precision of the Shuanglongtan landslide are improved by 3.1% and 3.6%, respectively, and the recall for the large catchment is improved by 9.95%. Our method can improve delineation of potential landslides significantly, which is crucial for landslide early warning and prevention. [ABSTRACT FROM AUTHOR]

This article develops and examines methods for the production of real-world, very high-resolution imagery using a high-frequency drone-borne synthetic aperture radar (SAR) operating at short ranges. The significance of motion errors which lead to space-invariant/variant phase errors is discussed. Subsequently, an imaging algorithm capable of handling these errors is proposed and presented. The validity of the approach is tested through both simulation and experiment. We present novel short-range, fine-resolution imagery (less than 2 cm in cross-range) of an extended target area generated using a low-cost, drone-borne vehicular frequency-modulated continuous-wave (FMCW) radar operating at 77 GHz, without using a dedicated inertial navigation system (INS) or Global Positioning System (GPS). [ABSTRACT FROM AUTHOR]

High-resolution land cover mapping over large areas is a challenging task due to the lack of high-quality labels. A potential solution is to leverage the existing knowledge contained in the freely available lower-resolution land cover products. However, the relatively low resolution and low accuracy of the products lead to numerous inaccurate labels, which harms the performance of the neural network. This article addresses the challenge by jointly optimizing the network parameters and correcting the noisy labels with a novel online noise correction approach and a synergistic noise correction loss. By incorporating the information entropy as a measurement to determine the probable correct labels, the proposed noise correction approach learns to make effective correction of the noisy labels during training and eventually boosts the performance with a training set containing less noisy labels. Experimental results show that the proposed method can effectively correct the noisy labels and reduce their negative impact on network training. By employing the proposed method, we produce a refined high-resolution (3-m) land cover map from a lower-resolution (10-m) product in China and improve the accuracy from 74.96% (10-m) to 81.32% (3-m). Such an approach that can effectively learn from noisy data sets leads to many potential opportunities for using and magnifying existing knowledge and results. [ABSTRACT FROM AUTHOR]

Building extraction based on high-resolution remote sensing imagery has been widely used in automatic surveying and mapping. However, few methods have been developed for building instance extraction, i.e., extracting each building’s footprint separately, which is required in a number of applications, such as the smallest unit of a cadastral database. In building instance extraction, there are two challenges: 1) buildings with various scales exist in the imagery and 2) precise building footprints are difficult to extract due to the blurry boundaries. In this article, to solve these problems, a multiscale U-shaped convolutional neural network building instance extraction framework with edge constraint (EMU-CNN) for high-spatial-resolution remote sensing imagery is proposed. The proposed framework consists of three components: 1) a multiscale fusion U-shaped network (MFUN); 2) a region proposal network (RPN); and 3) an edge-constrained multitask network (ECMN). First, in the proposed method, the MFUN includes three parallel branches to learn multiple building features with different scales. The RPN then detects the positions of the building instances, even for buildings that are connected with each other. Moreover, according to the instance positions, the ECMN is proposed to extract a precise mask and suppress overfitting. The experiments conducted on a self-annotated data set and two public data sets (the ISPRS Vaihingen semantic labeling contest data set and the WHU aerial image data set) show that the EMU-CNN method can achieve excellent performance and shows great robustness at different scales. [ABSTRACT FROM AUTHOR]

A key component in constructing a broad-scale, gridded population dataset is fine resolution geospatial data accurately depicting the extent of human activity. Analogous datasets are often developed using a wide range of methods and classification techniques, including the use of spatial features, spectral features, or the coupling of both to identify the presence of man-made structures from high-resolution satellite imagery. By using spatial and textural-based descriptors to generate high-resolution settlement layers for two dissimilar regions at the peak of seasonal disparity, this study attempts to quantify the influence of seasonality on the accuracy of a supervised, multi-scale, feature extraction framework for automated delineation of human settlement. Results generated by numerous models are evaluated against a reference dataset allowing for assessment of seasonal and feature differences in the context of accuracy. Global or regional mapping of human settlement requires the assemblage of high-resolution satellite images with variegated acquisition characteristics (season, sun elevation, off-nadir, etc.) to produce a cloud-free composite image from which features are extracted. Results of this study suggest an emphasis on imagery criteria, in particular acquisition date, could improve classification accuracy when mapping human settlement at scale. [ABSTRACT FROM AUTHOR]

Urban scenes refer to city blocks which are basic units of megacities, they play an important role in citizens' welfare and city management. Remote sensing imagery with largescale coverage and accurate target descriptions, has been regarded as an ideal solution for monitoring the urban environment. However, due to the heterogeneity of remote sensing images, it is difficult to access their geographical content at the object level, let alone understanding urban scenes at the block level. Recently, deep learning-based strategies have been applied to interpret urban scenes with remarkable accuracies. However, the deep neural networks require a substantial number of training samples which are hard to satisfy, especially for high-resolution images. Meanwhile, the crowed-sourced Open Street Map (OSM) data provides rich annotation information about the urban targets but may encounter the problem of insufficient sampling (limited by the places where people can go). As a result, the combination of OSM and remote sensing images for efficient urban scene recognition is urgently needed. In this paper, we present a novel strategy to transfer existing OSM data to high-resolution images for semantic element determination and urban scene understanding. To be specific, the object-based convolutional neural network (OCNN) can be utilized for geographical object detection by feeding it rich semantic elements derived from OSM data. Then, geographical objects are further delineated into their functional labels by integrating points of interest (POIs), which contain rich semantic terms, such as commercial or educational labels. Lastly, the categories of urban scenes are easily acquired from the semantic objects inside. Experimental results indicate that the proposed method has an ability to classify complex urban scenes. The classification accuracies of the Beijing dataset are as high as 91% at the object-level and 88% at the scene level. Additionally, we are probably the first to investigate the object level semantic mapping by incorporating high-resolution images and OSM data of urban areas. Consequently, the method presented is effective in delineating urban scenes that could further boost urban environment monitoring and planning with high-resolution images. [ABSTRACT FROM AUTHOR]

The study present the results of the satellite monitoring of Arctic icebergs formed from the outlet glaciers of the Severnaya Zemlya, Novaya Zemlya, and Franz Josef Land archipelagos during the autumn-winter and spring periods. The algorithms for iceberg detection in satellite images under different meteorological and ice conditions are described. [ABSTRACT FROM AUTHOR]

Accurately and quickly detecting maize tassels is crucial for successful maize breeding and seed production. However, the complex planting environment in the field, including unsynchronized growth stages, cluttered backgrounds, severe occlusions, and varying tassel sizes and shapes, presents a challenge for detection methods. Current methods either use mainstream object detectors off-the-shelf or employ shallow adaptations on the modular level, lacking a systematic design that balances both speed and accuracy. Furthermore, most studies only report evaluation results on sliced image patches instead of original high-resolution images, which can offer limited guidance for large-scale crop management. In this study, we propose a novel one-stage anchor-free maize tassel detector (MT-Det), which is based on a single level feature and designed to be simple yet effective. Extensive comparisons with both one-level counterparts and feature pyramid detectors demonstrate that MT-Det outperforms them in both detection accuracy and inference speed. To address the issue of significant accuracy drop when directly inferring on high-resolution images, we introduce a bundle of slicing-aided hyper inference technologies to our proposed MT-Det, which results in a 13% and 38% improvement of mean average precision (m A P) on proximal and unmanned aerial vehicle (UAV) high-resolution images, respectively. We believe that MT-Det provides a promising high-throughput solution for accurate and efficient detection and counting of maize tassels in real-world field conditions. • MT-Det: a novel fast one-stage anchor-free object detector using single feature level. • MT-Det outperforms one-level counterparts and feature pyramid detectors in speed and accuracy. • SAHI bridges performance gap between image patches and high-resolution images. • High-throughput detection results inferred and registered on original high-resolution images. [ABSTRACT FROM AUTHOR]

Salt marsh vegetation extent and zonation are often controlled by bottom up factors determined in part by the frequency and duration of tidal inundation. Tidal inundation during remote-sensing mapping of salt marsh resources can alter the resulting image classification. The degree of this impact on mapping with very high resolution (VHR) imagery has yet to be determined. This paper utilizes topobathymetric light detection and ranging (LiDAR) data and bathtub models of a tidal stage at 5 cm intervals from mean low water (MLW) to mean high water (MHW) and determines the impact of tidal variation in salt marsh mapping within Jamaica Bay, NY, USA. Tidal inundation models were compared with the Worldview-2 and Quickbird-2 imageries acquired at a range of tidal stages. The modeled inundation of normalized difference vegetation index and smooth cordgrass (S. alterniflora) maps was compared from MLW to MHW. This paper finds that at 0.6 m above MLW, only 3.5% of S. alterniflora is inundated. This paper demonstrates a modeling approach integrating VHR satellite remote-sensing data and topobathymetric LiDAR data to address tidal variation in salt marsh mapping. The incremental modeling of the tidal stage is important for understanding areas most at risk from sea level rise and informs management decisions in accordance with this. [ABSTRACT FROM AUTHOR]

Semantic segmentation of LiDAR and high-resolution aerial imagery is one of the most challenging topics in the remote sensing domain. Deep convolutional neural network (CNN) and its derivatives have recently shown the abilities in pixel-wise prediction of remote sensing data. Many existing deep learning methods fuse LiDAR and high-resolution aerial imagery towards an inter-modal mode and thus overlook the intra-modal statistical characteristics. Additionally, the patch-based CNNs could generate the salt-and-pepper artifacts as characterized by isolated and spurious pixels on the object boundaries and patch edges leading to unsatisfied labelling results. This paper presents a semantic segmentation scheme that combines multi-filter CNN and multi-resolution segmentation (MRS). The multi-filter CNN aggregates LiDAR data and high-resolution optical imagery by multi-modal data fusion for semantic labelling, and the MRS is further used to delineate object boundaries for reducing the salt-and-pepper artifacts. The proposed method is validated against two datasets: the ISPRS 2D semantic labelling contest of Potsdam and an area of Guangzhou in China labelled based on existing geodatabases. Various designs of data fusion strategy, CNN architecture and MRS scale are analyzed and discussed. Compared with other classification methods, our method improves the overall accuracies. Experiment results show that our combined method is an efficient solution for the semantic segmentation of LiDAR and high-resolution imagery. [ABSTRACT FROM AUTHOR]

In object-based image analysis (OBIA), object classification performance is jointly determined by image segmentation, sample or rule setting, and classifiers. Typically, as a crucial step to obtain object primitives, image segmentation quality significantly influences subsequent feature extraction and analyses. By contrast, template matching extracts specific objects from images and prevents shape defects caused by image segmentation. However, creating or editing templates is tedious and sometimes results in incomplete or inaccurate templates. In this study, we combine OBIA and template matching techniques to address these problems and aim for accurate photovoltaic panel (PVP) extraction from very high-resolution (VHR) aerial imagery. The proposed method is based on the previously proposed region–line primitive association framework, in which complementary information between region (segment) and line (straight line) primitives is utilized to achieve a more powerful performance than routine OBIA. Several novel concepts, including the mutual fitting ratio and best-fitting template based on region–line primitive association analyses, are proposed. Automatic template generation and matching method for PVP extraction from VHR imagery are designed for concept and model validation. Results show that the proposed method can successfully extract PVPs without any user-specified matching template or training sample. High user independency and accuracy are the main characteristics of the proposed method in comparison with routine OBIA and template matching techniques. [ABSTRACT FROM AUTHOR]

This work presents the coregistered, orthorectified and mosaiced high-resolution products of the MC11 quadrangle of Mars, which have been processed using novel, fully automatic, techniques. We discuss the development of a pipeline that achieves fully automatic and parameter independent geometric alignment of high-resolution planetary images, starting from raw input images in NASA PDS format and following all required steps to produce a coregistered geotiff image, a corresponding footprint and useful metadata. Additionally, we describe the development of a radiometric calibration technique that post-processes coregistered images to make them radiometrically consistent. Finally, we present a batch-mode application of the developed techniques over the MC11 quadrangle to validate their potential, as well as to generate end products, which are released to the planetary science community, thus assisting in the analysis of Mars static and dynamic features. This case study is a step towards the full automation of signal processing tasks that are essential to increase the usability of planetary data, but currently, require the extensive use of human resources. [ABSTRACT FROM AUTHOR]

The Fodongmo-Hongyazi fault (FHF) is a major thrust of Northeastern Tibet, bounding the Qilian Shan. It accommodates crustal shortening across this region and has produced a strong historical earthquake. Until now the slip rate has been poorly constrained, limiting our understanding of its role in the accommodation of deformation across this region. In this paper, faulted terraces at two sites on the western and middle segments of the FHF were mapped with satellite imagery and field observations. Chronological constraints are placed on the ages of displaced river terraces at these sites using terrestrial cosmogenic nuclide (TCN) exposure dating. These ages combined with offsets measured from SPOT 6 DEM’s yield average vertical slip rates of 1.3 ± 0.1 mm/yr for the western segment since ∼207 ka and 0.9 ± 0.1 mm/yr since ∼46 ka for the middle segment. These data suggest that the FHF accommodates ∼15–20% of the total shortening across the Qilian Shan (5.5–7 mm/yr). In addition, comparisons of our data with published slip rates along the Northern Qilian Thrust Fault Zone show that the fastest tectonic uplift occurs along the western portion of the Northern Qilian Shan. This is consistent with estimates deduced from geomorphology. The western portion of the Qilian Shan is mainly controlled by compressional deformation produced by the northward movement of the Northeastern Tibetan Plateau, while the eastern Qilian Shan is mainly controlled by the eastward extrusion of material along the left-lateral Haiyuan strike-slip Fault. [ABSTRACT FROM AUTHOR]

Remote multispectral data can provide valuable information for monitoring coastal water ecosystems. Specifically, high resolution satellite-based imaging systems, as WorldView-2 (WV-2), can generate information at spatial scales needed to implement conservation actions for protected littoral zones. However, coastal water-leaving radiance arriving at the space-based sensor is often small as compared to reflected radiance. In this work, complex approaches, which usually use an accurate radiative transfer code to correct the atmospheric effects, such as FLAASH, ATCOR and 6S, have been implemented for high resolution imagery. They have been assessed in real scenarios using field spectroradiometer data. In this context, the three approaches have achieved excellent results and a slightly superior performance of 6S model-based algorithm has been observed. Finally, for the mapping of benthic habitats in shallow-waters marine protected environments, a relevant application of the proposed atmospheric correction combined with an automatic deglinting procedure is presented. This approach is based on the integration of a linear mixing model of benthic classes within the radiative transfer model of the water. The complete methodology has been applied to selected ecosystems in Canary Islands (Spain), but the obtained results allow the robust mapping of the spatial distribution and density of seagrass in coastal waters and the analysis of multitemporal variations related to the human activity and climate change in littoral zones. [ABSTRACT FROM AUTHOR]

Remote multispectral data can provide valuable information for monitoring coastal water ecosystems. Specifically, high-resolution satellite-based imaging systems, asWorldView-2 (WV-2), can generate information at spatial scales needed to implement conservation actions for protected littoral zones. However, coastal water-leaving radiance arriving at the space-based sensor is often small as compared to reflected radiance. In this work, complex approaches, which usually use an accurate radiative transfer code to correct the atmospheric effects, such as FLAASH, ATCOR and 6S, have been implemented for high-resolution imagery. They have been assessed in real scenarios using field spectroradiometer data. In this context, the three approaches have achieved excellent results and a slightly superior performance of 6S model-based algorithm has been observed. Finally, for the mapping of benthic habitats in shallow-waters marine protected environments, a relevant application of the proposed atmospheric correction combined with an automatic deglinting procedure is presented. This approach is based on the integration of a linear mixing model of benthic classes within the radiative transfer model of the water. The complete methodology has been applied to selected ecosystems in the Canary Islands (Spain) but the obtained results allow the robust mapping of the spatial distribution and density of seagrass in coastal waters and the analysis of multitemporal variations related to the human activity and climate change in littoral zones. [ABSTRACT FROM AUTHOR]

Terraces are typical artificial landforms on the Loess Plateau, with ecological functions in water and soil conservation, agricultural production, and biodiversity. Recording the spatial distribution of terraces is the basis of monitoring their extent and understanding their ecological effects. The current terrace extraction method mainly relies on high-resolution imagery, but its accuracy is limited due to vegetation coverage distorting the features of terraces in imagery. High-resolution topographic data reflecting the morphology of true terrace surfaces are needed. Terraces extraction on the Loess Plateau is challenging because of the complex terrain and diverse vegetation after the implementation of "vegetation recovery". This study presents an automatic method of extracting terraces based on 1 m resolution digital elevation models (DEMs) and 0.3 m resolution Worldview-3 imagery as auxiliary information used for object-based image analysis (OBIA). A multi-resolution segmentation method was used where slope, positive and negative terrain index (PN), accumulative curvature slope (AC), and slope of slope (SOS) were determined as input layers for image segmentation by correlation analysis and Sheffield entropy method. The main classification features based on DEMs were chosen from the terrain features derived from terrain factors and texture features by gray-level co-occurrence matrix (GLCM) analysis; subsequently, these features were determined by the importance analysis on classification and regression tree (CART) analysis. Extraction rules based on DEMs were generated from the classification features with a total classification accuracy of 89.96%. The red band and near-infrared band of images were used to exclude construction land, which is easily confused with small-size terraces. As a result, the total classification accuracy was increased to 94%. The proposed method ensures comprehensive consideration of terrain, texture, shape, and spectrum characteristics, demonstrating huge potential in hilly-gully loess region with similarly complex terrain and diverse vegetation covers. [ABSTRACT FROM AUTHOR]

We present preliminary results of an Earth observation approach for the study of past human occupation and landscape reconstruction in the Central Sahara. This region includes a variety of geomorphological features such as palaeo-oases, dried river beds, alluvial fans and upland plateaux whose geomorphological characteristics, in combination with climate changes, have influenced patterns of human dispersal and sociocultural activities during the late Holocene. In this paper, we discuss the use of medium- and high-resolution remotely sensed data for the mapping of anthropogenic features and paleo- and contemporary hydrology and vegetation. In the absence of field inspection in this inaccessible region, we use different remote sensing methods to first identify and classify archaeological features, and then explore the geomorphological factors that might have influenced their spatial distribution. [ABSTRACT FROM AUTHOR]

Determining the appropriate scale of image objects is a critical aspect that affects segmentation quality in object-based classification. This research aims to assess the influence of three objective segmentation optimization methods for object-based vegetation classification through high-resolution imagery at mine rehabilitation site. These methods included estimation of scale parameter, segmentation error index, and Euclidean distance 2 index, which were employed to determine segmentation parameters, final classification accuracy, and optimal scale parameters for segmentation. The results showed that segmentation optimization may increase the classification accuracy of object-based analysis to extract information from artificial objects with regular shape, such as rehabilitated vegetation and urban green space. Given the high-resolution image with multi-spectral bands, the segmentation error and Euclidean distance 2 indices improved final classification accuracy relative to the control. Final classification accuracy obtained from each of four workflows further indicated that relatively small differences in scale parameters can lead to considerable differences in final classification accuracy. These methods automate the mail classification steps and improve the classification accuracy, only some parts of the classification require manual intervention, resulting in a more transferable approach with potentially less time required for classifying new imagery. [ABSTRACT FROM AUTHOR]

The U.S. Geological Survey (USGS) has begun the development of operational, 30-m resolution annual thematic land cover data to meet the needs of a variety of land cover data users. The Continuous Change Detection and Classification (CCDC) algorithm is being evaluated as the likely methodology following early trials. Data for training and testing of CCDC thematic maps have been provided by the USGS Land Cover Trends (LC Trends) project, which offers sample-based, manually classified thematic land cover data at 2755 probabilistically located sample blocks across the conterminous United States. These samples represent a high quality, well distributed source of data to train the Random Forest classifier invoked by CCDC. We evaluated the suitability of LC Trends data to train the classifier by assessing the agreement of annual land cover maps output from CCDC with output from the LC Trends project within 14 Landsat path/row locations across the conterminous United States. We used a small subset of circa 2000 data from the LC Trends project to train the classifier, reserving the remaining Trends data from 2000, and incorporating LC Trends data from 1992, to evaluate measures of agreement across time, space, and thematic classes, and to characterize disagreement. Overall agreement ranged from 75% to 98% across the path/rows, and results were largely consistent across time. Land cover types that were well represented in the training data tended to have higher rates of agreement between LC Trends and CCDC outputs. Characteristics of disagreement are being used to improve the use of LC Trends data as a continued source of training information for operational production of annual land cover maps. [ABSTRACT FROM AUTHOR]

Spatial information remains to be an important topic in geographic information system and in remote sensing fields, and spatial relationships have been increasingly incorporated into the image classification processes. Previous studies have employed multiple occurrences of spatial features (shape, texture, etc.,) to improve classification results. However, less attention has been focused on using higher-level spatial relationships for image classification. In this study, two novel spatial relationships, namely, maximum spatial adjacency (MSA) and directional spatial adjacency (DSA), were proposed to assist in image classification. The proposed methods were implemented to extract buildings, beach, and emergent vegetation land-cover classes according to their spatial relationships with their corresponding reference classes. The promising results obtained from this study suggest that the proposed MSA and DSA spatial relationships can be valuable information in defining rule sets for a more reasonable and accurate classification. [ABSTRACT FROM PUBLISHER]

Shorelines are line features that mark the interface between water and land and they are essential due to their mapping, ecological, and engineering values. A shoreline can be an instantaneous, which shows the water-land boundary at any time or a tide-referenced, which indicates the intersection of a tidal datum surface such as mean high water and the coastal topobathymetric surface. Instantaneous shorelines can be extracted from geo-referenced aerial photographs and satellite imagery without the need to have its acquisition to be tide-coordinated as in the case of tide-referenced shorelines. In this study, a semiautomatic method of extracting the shoreline from high-resolution satellite imagery and a coastal terrain model (CTM) is presented. This study was motivated by the frequent need for shorelines for input in the numerical models used by Dubai Municipality for obtaining essential parameters for various coastal planning activities. The method utilizes the Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA) for classifying a RapidEye image of the study area, then vectorizing and extracting the shoreline, and finally extracting the elevation of shoreline points from the CTM and adding that to the shoreline point attribute table. The accuracy of the extracted shoreline was carried out by comparing it to a shoreline digitized from an orthophotograph of the study area. The comparison was carried out by computing the point-to-point distances between corresponding points established on the two shorelines using a parametric technique. The results suggest that this method can be used to accurately extract robust shorelines from high-resolution satellite imagery and CTMs. [ABSTRACT FROM AUTHOR]

This paper presents an integrated approach for the automatic extraction of rectangular- and circular-shape buildings from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping. The building patches are detected from the image using the binary SVM classification. The generated normalized digital surface model (nDSM) and the normalized difference vegetation index (NDVI) are incorporated in the classification process as additional bands. After detecting the building patches, the building boundaries are extracted through sequential processing of edge detection, Hough transformation and perceptual grouping. Those areas that are classified as building are masked and further processing operations are performed on the masked areas only. The edges of the buildings are detected through an edge detection algorithm that generates a binary edge image of the building patches. These edges are then converted into vector form through Hough transform and the buildings are constructed by means of perceptual grouping. To validate the developed method, experiments were conducted on pan-sharpened and panchromatic Ikonos imagery, covering the selected test areas in Batikent district of Ankara, Turkey. For the test areas that contain industrial buildings, the average building detection percentage (BDP) and quality percentage (QP) values were computed to be 93.45% and 79.51%, respectively. For the test areas that contain residential rectangular-shape buildings, the average BDP and QP values were computed to be 95.34% and 79.05%, respectively. For the test areas that contain residential circular-shape buildings, the average BDP and QP values were found to be 78.74% and 66.81%, respectively. [ABSTRACT FROM AUTHOR]

Google Earth is a virtual globe, map and geographical information program that is controlled by Google corporation. It maps the Earth by the superimposition of images obtained from satellite imagery, aerial photography and GIS 3D globe. With millions of users all around the globe, GoogleEarth® has become the ultimate source of spatial data and information for private and public decision-support systems besides many types and forms of social interactions. Many users mostly in developing countries are also using it for surveying applications, the matter that raises questions about the positional accuracy of the Google Earth program. This research presents a small-scale assessment study of the positional accuracy of GoogleEarth® Imagery in Riyadh; capital of Kingdom of Saudi Arabia (KSA). The results show that the RMSE of the GoogleEarth imagery is 2.18 m and 1.51 m for the horizontal and height coordinates respectively. [ABSTRACT FROM AUTHOR]

Highlights: [•] We propose a set of urban metrics to describe the streets with remotely sensed data. [•] A methodology is defined to relate street space to urban blocks. [•] Results show that street metrics are useful for improving the characterisation of cities. [ABSTRACT FROM AUTHOR]

Under the background of global change, increasing attention has been paid to the changes of benthic habitats in shallow ocean ecosystems (e.g., seagrass beds and coral reefs). Optical satellite remote sensing via both active and passive methods plays an important role in monitoring the health of benthic habitats by retrieving benthic reflectance spectra, but it remains difficult to accurately retrieve benthic reflectance spectra from only active or passive remote sensing because of the coupling between water column scattering and benthic reflectance. Here, we developed a semi-analytical model to retrieve benthic reflectance spectra in Case-I waters by combining active lidar and passive high-resolution imagery. Based on two-stream radiative transfer theory, the analytical relationship among the remote sensing reflectance (R rs) and water column reflectance (R w), benthic reflectance (R b), diffuse attenuation coefficient (K d), and water depth was established. The lidar data at a certain wavelength were applied to derive the water depth and the chlorophyll concentration (chl) along the lidar track. Then, the values of K d at different wavelengths were estimated from the derived chl. In addition, we established a look-up-table (LUT) for the relationship between R w and chl and water depth using Hydrolight simulation, and the R w values at different wavelengths were then estimated by the lidar-derived chl and water depth. Finally, R b (λ) values at different wavelengths along the lidar track were retrieved from the R rs (λ) values observed by passive high-resolution imagery and the values of R w (λ), K d (λ), and water depth derived by lidar observation. The accuracy of the model was verified by using the Hydrolight simulated datasets, and the high correlation coefficient (R) revealed promising model performance for different benthic habitats, e.g., R > 0.9 for typical clean shallow water (chl = 0.5 mg/m3, H < 4 m) for the wavelength range of 400–640 nm. The model was further applied to real satellite data from ICESat-2 lidar and passive high-resolution satellite imagery (multispectral imagery of Sentinel-2 and hyperspectral imagery of Zhuhai−1) at two different benthic habitat sites (seagrass beds in Xincun Bay and coral reefs in the Huaguang Reef) in the South China Sea, and the results revealed that the model could reproduce the benthic spectra in both magnitude and shape. Overall, the proposed model can reliably yield benthic reflectance spectra along the lidar track without any requirement on prior knowledge, which should be beneficial for further benthic habitat health monitoring. • A semi-analytical model was established for benthic reflectance retrieval. • A novel method was proposed by combining active lidar and passive imagery. • Retrieved benthic reflectance reproduced known values in both magnitude and shape. [ABSTRACT FROM AUTHOR]

This paper evaluates accuracies of selected image classification strategies, as applied to Landsat imagery to assess urban impervious surfaces by comparing them to reference data manually delineated from high-resolution aerial photos. Our goal is to identify the most effective methods for delineating urban impervious surfaces using Landsat imagery, thereby guiding applications for selecting cost-effective delineation techniques. A high-resolution aerial photo was used to delineate impervious surfaces for selected census tracts for the City of Roanoke, Virginia. National Land Cover Database Impervious Surface data provided an overall accuracy benchmark at the city scale which was used to assess the Landsat classifications. Three different classification methods using three different band combinations provided overall accuracies in excess of 70% for the entire city. However, there were substantial variations in accuracy when the results were subdivided by census tract. No single classification method was found most effective across all census tracts; the best method for a specific tract depended on method, band combination, and physical characteristics of the area. These results highlight impacts of inherent local variability upon attempts to characterize physical structures of urban regions using a single metric, and the value of analysis at finer spatial scales. [ABSTRACT FROM AUTHOR]

Habitat mapping is a useful tool for ecologists to analyze spatial data. Rocky shore ecosystems comprise a mosaic of habitat types and therefore require good technology to extract fine-scale spatial data on habitat extent and quality. Airborne topographic light detection and ranging data and 0.1-m resolution digital aerial photography were used to map and quantify distinct habitats that influence the distribution of biodiversity on rocky shores. The objectives of this study were to create and test the accuracy of a classification system for the rocky shore habitat, to develop remote sensing techniques useful for the conservation of intertidal rocky shores, and to create detailed digital terrain models for five headlands in the Solitary Island Marine Park, mid-north coast, New South Wales, Australia. The intertidal rocky shore habitats were classified according to tidal heights and substrate type. Ground-truthing of remote sensing data was carried out by visual surveys during low tide. Error assessments using precision analysis and classification accuracy tests confirmed the reliability of the technique with ,5% error. The data generated from this research can be used as a platform for spatial analysis of this environment, including modelling changes in biodiversity under different climate change scenarios. [ABSTRACT FROM AUTHOR]

The development of remote sensing technology, especially the availability of high-resolution satellite imagery, has been applied to building recognition, hazard investigation and rapid pre-evaluation in post-earthquake management. Existing pixel-oriented approaches which are commonly used for satellite high-resolution imagery have limitations in information extraction, ground object classification, and processing speed. This paper presents an object-oriented method to extract earthquake-damaged building information using high-resolution remote sensing imagery of the 5.12 Wenchuan Earthquake. This method segmented the whole image into non-intersecting pieces of image objects, and then classified these pieces to extract damaged/undamaged buildings using image features such as spectral characters, textures, shapes, and their contexts. The results show a higher-precision classification than conventional methods. [ABSTRACT FROM AUTHOR]

This communication introduces a very simple generalisation of the familiar spectral angle mapper (SAM) distance. SAM is perhaps the most widely used distance in chemometrics, hyperspectral imaging, and remote sensing applications. It is shown that a nonlinear version of SAM can be readily obtained by measuring the angle between pairs of vectors in a reproducing kernel Hilbert spaces. The kernel SAM generalises the angle measure to higher‐order statistics, it is a valid reproducing kernel, it is universal, and it has consistent geometrical properties that permit deriving a metric easily. We illustrate its performance in a target detection problem using very high resolution imagery. Excellent results and insensitivity to parameter tuning over competing methods make it a valuable choice for many applications. [ABSTRACT FROM AUTHOR]

Google Earth now hosts high-resolution imagery that spans twenty percent of the Earth's landmass and more than a third of the human population. This contemporary highresolution archive represents a significant, rapidly expanding, cost-free and largely unexploited resource for scientific inquiry. To increase the scientific utility of this archive, we address horizontal positional accuracy (georegistration) by comparing Google Earth with Landsat GeoCover scenes over a global sample of 436 control points located in 109 cities worldwide. Landsat GeoCover is an orthorectified product with known absolute positional accuracy of less than 50 meters root-mean-squared error (RMSE). Relative to Landsat GeoCover, the 436 Google Earth control points have a positional accuracy of 39.7 meters RMSE (error magnitudes range from 0.4 to 171.6 meters). The control points derived from satellite imagery have an accuracy of 22.8 meters RMSE, which is significantly more accurate than the 48 control-points based on aerial photography (41.3 meters RMSE; t-test p-value < 0.01). The accuracy of control points in more-developed countries is 24.1 meters RMSE, which is significantly more accurate than the control points in developing countries (44.4 meters RMSE; t-test p-value < 0.01). These findings indicate that Google Earth highresolution imagery has a horizontal positional accuracy that is sufficient for assessing moderate-resolution remote sensing products across most of the world's peri-urban areas. [ABSTRACT FROM AUTHOR]

Meter to submeter resolution satellite images have generated new interests in extracting man-made structures in the urban area. However, classification accuracies for such purposes are far from satisfactory. Spectral characteristics of urban land cover classes are so similar that they cannot be separated using only spectral information. As a result, there is an increased interest in incorporating geometrical information. One possible approach is the use of morphological profiles (MPs). In this paper, we introduce two improvements on the use of MPs. Current approaches use disk-shaped structuring elements (SEs) to derive an MP. This profile contains information about the minimum dimension of objects. In this paper, we extend this approach by using linear SEs. This results in a profile containing information about the maximum object dimension. We show that the addition of the line-based MP gives a substantial improvement of the classification result. A second improvement is achieved by using "partial morphological reconstruction" instead of the normal morphological reconstruction. Morphological reconstruction is commonly used to better preserve the shape of objects. However, we show that this leads to "over-reconstruction" in typical remote sensing images and a decreased classification performance. With "partial reconstruction," we are able to overcome this problem and still preserve the shape of objects. [ABSTRACT FROM AUTHOR]

The effectiveness of multilayer perceptron (MLP) networks as a tool for the classification of remotely sensed images has been already proven in past years. However, most of the studies consider images characterized by high spatial resolution (around 15-30 m) while a detailed analysis of the performance of this type of classifier on very high resolution images (around 1-2 m) such as those provided by the Quickbird satellite is still lacking. Moreover, the classification problem is normally understood as the classification of a single image while the capabilities of a single network of performing automatic classification and feature extraction over a collection of archived images has not been explored so far. In this paper, besides assessing the performance of MLP for the classification of very high resolution images, we investigate on the generalization capabilities of this type of algorithms with the purpose of using them as a tool for fully automatic classification of collections of satellite images, either at very high or at highresolution. In particular, applications to urban area monitoring have been addressed. [ABSTRACT FROM AUTHOR]

Abstract: Lack of appropriate historical data has seriously impeded research into the extent and effects of deforestation in arid lands, but the declassification of corona satellite images has now made it possible to study long-term changes in arboreal vegetation. The potential and limitations of such images for long-term vegetation studies are scrutinized in the light of this research. High-resolution images (ca. 2.7m) from 1965 are compared to field data (2003) of individually mapped wadi trees (Acacia tortilis and Balanites aegyptiaca) from 20 different sites in the Eastern Desert of Egypt. Of trees mapped in 2003 (canopy area (CA) >6m2) 70% was detected in the imagery. A spatial classification shows that between 9% and 55% of the population was concealed by landscape elements that reduce image contrast. The study indicates that 97% of the population mapped in 2003 was already present in 1965 and that trees grow slowly and are older than previously assumed. Pollarded trees were detected in the imagery, and the resultant reduction in CA may lead to misinterpretations in change analyses. corona images offer a spatial and temporal dimension for ecological information which other data sources cannot furnish at a comparable cost, coverage, resolution or accessibility. [Copyright &y& Elsevier]

The Geographical Survey Institute of Japan has recently carried out an evaluation of the metric performance of QuickBird stereo satellite imagery. This paper describes the accuracy assessment of the sensor orientation and geopositioning phases of the study, the aim of which was twofold. First, it was desired to confirm the metric potential of QuickBird imagery for 1:25 000 scale topographic mapping. Second, a determination was to be made of the accuracy attainable from the Basic image product. The techniques of rational functions and affine bundle adjustment were employed, the former with bias compensation. The results obtained both reassert the high precision of the rational functions approach and cast doubt upon the applicability of the 3D affine model for accurate geopositioning from QuickBird imagery. [ABSTRACT FROM AUTHOR]

In this paper, we present an object-based approach for urban !and cover classification from high resolution multispectral image data that builds upon a pixel-based fuzzy classification approach. This combined pixel/object approach is demonstrated using pansharpened multispectral IKONOS imagery from dense urban areas. The fuzzy pixel-based classifier Utilizes both spectral and spatial information to discriminate between spectrally similar Road and Building urban !and cover classes. After the pixel-based classification, a technique that utilizes both spectral and spatial heterogeneity is used to segment the image to facilitate further object-based classification. An object-based fuzzy logic classifier is then implemented to improve upon the pixel-based classification by identifying one additional class in dense urban areas: nonroad, nonbuilding impervious surface. With the fuzzy pixel-based classification as input, the object-based classifier then uses shape, spectral, and neighborhood features to determine the final classification of the segmented image. Using these techniques, the object-based classifier is able to identify Buildings, Impervious Surface, and Roads in dense urban areas with 76%, 81%, and 99% classification accuracies, respectively. [ABSTRACT FROM AUTHOR]

Classification of panchromatic high-resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is based on three steps. First, the composition of geodesic opening and closing operations of different sizes is used in order to build a differential morphological profile that records image structural information. Although, the original panchromatic image only has one data channel, the use of the composition operations will give many additional channels, which may contain redundancies. Therefore, feature extraction or feature selection is applied in the second step. Both discriminant analysis feature extraction and decision boundary feature extraction are investigated in the second step along with a simple feature selection based on picking the largest indexes of the differential morphological profiles. Third, a neural network is used to classify the features from the second step. The proposed approach is applied in experiments on high-resolution Indian Remote Sensing lC (IRS-1C) and IKONOS remote sensing data from urban areas. In experiments, the proposed method performs well in terms of classification accuracies. It is seen that relatively few features are needed to achieve the same classification accuracies as in the original feature space. [ABSTRACT FROM AUTHOR]

Holm oak decline is a complex phenomenon mainly influenced by the presence of Phytophthora cinnamomi and water stress. Plant functional traits (PTs) are altered during the decline process — initially affecting the physiological condition of the plants with non-visual symptoms and subsequently the leaf pigment content and canopy structure — being its quantification critical for the development of scalable detection methods for effective management. This study examines the relationship between spectral-based PTs and oak decline incidence and severity. We evaluate the use of high-resolution hyperspectral and thermal imagery (< 1 m) together with a 3-D radiative transfer model (RTM) to assess a supervised classification model of holm oak decline. Field surveys comprising more than 1100 trees with varying disease incidence and severity were used to train and validate the model and predictions. Declining trees showed decreases of model-based PTs such as water, chlorophyll, carotenoid, and anthocyanin contents, as well as fluorescence and leaf area index, and increases in crown temperature and dry matter content, compared to healthy trees. Our classification model built using different PT indicators showed up to 82% accuracy for decline detection and successfully identified 34% of declining trees that were not detected by visual inspection and confirmed in a re-evaluation 2 years later. Among all variables analysed, canopy temperature was identified as the most important variable in the model, followed by chlorophyll fluorescence. This methodological approach identified spectral plant traits suitable for the detection of pre-symptomatic trees and mapping of oak forest disease outbreaks up to 2 years in advance of identification via field surveys. Early detection can guide management activities such as tree culling and clearance to prevent the spread of dieback processes. Our study demonstrates the utility of 3-D RTM models to untangle the PT alterations produced by oak decline due to its heterogeneity. In particular, we show the combined use of RTM and machine learning classifiers to be an effective method for early detection of oak decline potentially applicable to many other forest diseases worldwide. • High-resolution airborne imagery detected holm oak decline (HOD). • Plant trait quantification enables the interpretation of HOD severity levels. • Temperature and fluorescence were most important for HOD detection. • Plant traits detected HOD in 34% of visually asymptomatic trees. • 3-D radiative transfer models are needed for HOD detection. [ABSTRACT FROM AUTHOR]

Timely and accurate monitoring of tree crop extent and productivities are necessary for informing policy-making and investments. However, except for a very few tree species (e.g., oil palms) with obvious canopy and extensive planting, most small-crown tree crops are understudied in the remote sensing domain. To conduct large-scale small-crown tree mapping, several key questions remain to be answered, such as the choice of satellite imagery with different spatial and temporal resolution and model generalizability. In this study, we use olive trees in Morocco as an example to explore the two abovementioned questions in mapping small-crown orchard trees using 0.5 m DigitalGlobe (DG) and 3 m Planet imagery and deep learning (DL) techniques. Results show that compared to DG imagery whose mean overall accuracy (OA) can reach 0.94 and 0.92 in two climatic regions, Planet imagery has limited capacity to detect olive orchards even with multi-temporal information. The temporal information of Planet only helps when enough spatial features can be captured, e.g., when olives are with large crown sizes (e.g., >3 m) and small tree spacings (e.g., <3 m). Regarding model generalizability, experiments with DG imagery show a decrease in F1 score up to 5% and OA to 4% when transferring models to new regions with distribution shift in the feature space. Findings from this study can serve as a practical reference for many other similar mapping tasks (e.g., nuts and citrus) around the world. [ABSTRACT FROM AUTHOR]

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project. [ABSTRACT FROM AUTHOR]

Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84 , a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59 . Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package. [ABSTRACT FROM AUTHOR]

Invasive plants are a major agent threatening biodiversity conservation and directly affecting our living environment. This study aims to evaluate the potential of deep learning, one of the fastest-growing trends in machine learning, to detect plant invasion in urban parks using high-resolution (0.1 m) aerial image time series. Capitalizing on a state-of-the-art, popular architecture residual neural network (ResNet), we examined key challenges applying deep learning to detect plant invasion: relatively limited training sample size (invasion often confirmed in the field) and high forest contextual variation in space (from one invaded park to another) and over time (caused by varying stages of invasion and the difference in illumination condition). To do so, our evaluations focused on a widespread exotic plant, autumn olive (Elaeagnus umbellate), that has invaded 20 urban parks across Mecklenburg County (1410 km2) in North Carolina, USA. The results demonstrate a promising spatial and temporal generalization capacity of deep learning to detect urban invasive plants. In particular, the performance of ResNet was consistently over 96.2% using training samples from 8 (out of 20) or more parks. The model trained by samples from only four parks still achieved an accuracy of 77.4%. ResNet was further found tolerant of high contextual variation caused by autumn olive's progressive invasion and the difference in illumination condition over the years. Our findings shed light on prioritized mitigation actions for effectively managing urban invasive plants. [ABSTRACT FROM AUTHOR]