Next Issue
Volume 13, February-2
Previous Issue
Volume 13, January-2

Remote Sens., Volume 13, Issue 3 (February-1 2021) – 208 articles

Cover Story (view full-size image): Plant phenology is closely related to natural cycles of light, which, notably, have been disrupted by artificial light at night (ALAN) due to recent urbanization. Here, we showed that ALAN tended to advance the start date of the growing season (SOS), although the overall response of SOS to ALAN was relatively weak. The phenological impact of ALAN showed a spatially divergent pattern, whereby ALAN predominantly advanced SOS at climatically moderate regions, while at very cold and hot regions, its effect was insignificant or even reversed. Such a divergent pattern was mainly attributed to its high sensitivity to chilling insufficiency, though other mechanisms may also play a part, such as the interplay between chilling, forcing and photoperiods, as well as the difference in the life strategies of species. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Order results
Result details
Select all
Export citation of selected articles as:
Open AccessArticle
Thermal Summer Diurnal Hot-Spot Analysis: The Role of Local Urban Features Layers
Remote Sens. 2021, 13(3), 538; https://doi.org/10.3390/rs13030538 - 02 Feb 2021
Viewed by 805
Abstract
This study was focused on the metropolitan area of Florence in Tuscany (Italy) with the aim of mapping and evaluating thermal summer diurnal hot- and cool-spots in relation to the features of greening, urban surfaces, and city morphology. The work was driven by [...] Read more.
This study was focused on the metropolitan area of Florence in Tuscany (Italy) with the aim of mapping and evaluating thermal summer diurnal hot- and cool-spots in relation to the features of greening, urban surfaces, and city morphology. The work was driven by Landsat 8 land surface temperature (LST) data related to 2015–2019 summer daytime periods. Hot-spot analysis was performed adopting Getis-Ord Gi* spatial statistics applied on mean summer LST datasets to obtain location and boundaries of hot- and cool-spot areas. Each hot- and cool-spot was classified by using three significance threshold levels: 90% (LEVEL-1), 95% (LEVEL-2), and 99% (LEVEL-3). A set of open data urban elements directly or indirectly related to LST at local scale were calculated for each hot- and cool-spot area: (1) Normalized Difference Vegetation Index (NDVI), (2) tree cover (TC), (3) water bodies (WB), (4) impervious areas (IA), (5) mean spatial albedo (ALB), (6) surface areas (SA), (7) Shape index (SI), (8) Sky View Factor (SVF), (9) theoretical solar radiation (RJ), and (10) mean population density (PD). A General Dominance Analysis (GDA) framework was adopted to investigate the relative importance of urban factors affecting thermal hot- and cool-spot areas. The results showed that 11.5% of the studied area is affected by cool-spots and 6.5% by hot-spots. The average LST variation between hot- and cold-spot areas was about 10 °C and it was 15 °C among the extreme hot- and cool-spot levels (LEVEL-3). Hot-spot detection was magnified by the role of vegetation (NDVI and TC) combined with the significant contribution of other urban elements. In particular, TC, NDVI and ALB were identified as the most significant predictors (p-values < 0.001) of the most extreme cool-spot level (LEVEL-3). NDVI, PD, ALB, and SVF were selected as the most significant predictors (p-values < 0.05 for PD and SVF; p-values < 0.001 for NDVI and ALB) of the hot-spot LEVEL-3. In this study, a reproducible methodology was developed applicable to any urban context by using available open data sources. Full article
(This article belongs to the Section Urban Remote Sensing)
Show Figures

Graphical abstract

Open AccessArticle
The Indian COSMOS Network (ICON): Validating L-Band Remote Sensing and Modelled Soil Moisture Data Products
Remote Sens. 2021, 13(3), 537; https://doi.org/10.3390/rs13030537 - 02 Feb 2021
Viewed by 697
Abstract
Availability of global satellite based Soil Moisture (SM) data has promoted the emergence of many applications in climate studies, agricultural water resource management and hydrology. In this context, validation of the global data set is of substance. Remote sensing measurements which are representative [...] Read more.
Availability of global satellite based Soil Moisture (SM) data has promoted the emergence of many applications in climate studies, agricultural water resource management and hydrology. In this context, validation of the global data set is of substance. Remote sensing measurements which are representative of an area covering 100 m2 to tens of km2 rarely match with in situ SM measurements at point scale due to scale difference. In this paper we present the new Indian Cosmic Ray Network (ICON) and compare it’s data with remotely sensed SM at different depths. ICON is the first network in India of the kind. It is operational since 2016 and consist of seven sites equipped with the COSMOS instrument. This instrument is based on the Cosmic Ray Neutron Probe (CRNP) technique which uses non-invasive neutron counts as a measure of soil moisture. It provides in situ measurements over an area with a radius of 150–250 m. This intermediate scale soil moisture is of interest for the validation of satellite SM. We compare the COSMOS derived soil moisture to surface soil moisture (SSM) and root zone soil moisture (RZSM) derived from SMOS, SMAP and GLDAS_Noah. The comparison with surface soil moisture products yield that the SMAP_L4_SSM showed best performance over all the sites with correlation (R) values ranging from 0.76 to 0.90. RZSM on the other hand from all products showed lesser performances. RZSM for GLDAS and SMAP_L4 products show that the results are better for the top layer R = 0.75 to 0.89 and 0.75 to 0.90 respectively than the deeper layers R = 0.26 to 0.92 and 0.6 to 0.8 respectively in all sites in India. The ICON network will be a useful tool for the calibration and validation activities for future SM missions like the NASA-ISRO Synthetic Aperture Radar (NISAR). Full article
Show Figures

Graphical abstract

Open AccessArticle
Understanding Vine Hyperspectral Signature through Different Irrigation Plans: A First Step to Monitor Vineyard Water Status
Remote Sens. 2021, 13(3), 536; https://doi.org/10.3390/rs13030536 - 02 Feb 2021
Viewed by 527
Abstract
The main challenge encountered by Mediterranean winegrowers is water management. Indeed, with climate change, drought events are becoming more intense each year, dragging the yield down. Moreover, the quality of the vineyards is affected and the level of alcohol increases. Remote sensing data [...] Read more.
The main challenge encountered by Mediterranean winegrowers is water management. Indeed, with climate change, drought events are becoming more intense each year, dragging the yield down. Moreover, the quality of the vineyards is affected and the level of alcohol increases. Remote sensing data are a potential solution to measure water status in vineyards. However, important questions are still open such as which spectral, spatial, and temporal scales are adapted to achieve the latter. This study aims at using hyperspectral measurements to investigate the spectral scale adapted to measure their water status. The final objective is to find out whether it would be possible to monitor the vine water status with the spectral bands available in multispectral satellites such as Sentinel-2. Four Mediterranean vine plots with three grape varieties and different water status management systems are considered for the analysis. Results show the main significant domains related to vine water status (Short Wave Infrared, Near Infrared, and Red-Edge) and the best vegetation indices that combine these domains. These results give some promising perspectives to monitor vine water status. Full article
Show Figures

Figure 1

Open AccessArticle
MDECNN: A Multiscale Perception Dense Encoding Convolutional Neural Network for Multispectral Pan-Sharpening
Remote Sens. 2021, 13(3), 535; https://doi.org/10.3390/rs13030535 - 02 Feb 2021
Viewed by 471
Abstract
With the rapid development of deep neural networks in the field of remote sensing image fusion, the pan-sharpening method based on convolutional neural networks has achieved remarkable effects. However, because remote sensing images contain complex features, existing methods cannot fully extract spatial features [...] Read more.
With the rapid development of deep neural networks in the field of remote sensing image fusion, the pan-sharpening method based on convolutional neural networks has achieved remarkable effects. However, because remote sensing images contain complex features, existing methods cannot fully extract spatial features while maintaining spectral quality, resulting in insufficient reconstruction capabilities. To produce high-quality pan-sharpened images, a multiscale perception dense coding convolutional neural network (MDECNN) is proposed. The network is based on dual-stream input, designing multiscale blocks to separately extract the rich spatial information contained in panchromatic (PAN) images, designing feature enhancement blocks and dense coding structures to fully learn the feature mapping relationship, and proposing comprehensive loss constraint expectations. Spectral mapping is used to maintain spectral quality and obtain high-quality fused images. Experiments on different satellite datasets show that this method is superior to the existing methods in both subjective and objective evaluations. Full article
Show Figures

Graphical abstract

Open AccessArticle
Sub-Auroral, Mid-Latitude, and Low-Latitude Troughs during Severe Geomagnetic Storms
Remote Sens. 2021, 13(3), 534; https://doi.org/10.3390/rs13030534 - 02 Feb 2021
Viewed by 465
Abstract
The dynamics of ionospheric troughs during intense geomagnetic storms is considered in this paper. The study is based on electron density measurements at CHAMP satellite altitudes of 405–465 km in the period from 2000 to 2002. A detailed analysis of four storms with [...] Read more.
The dynamics of ionospheric troughs during intense geomagnetic storms is considered in this paper. The study is based on electron density measurements at CHAMP satellite altitudes of 405–465 km in the period from 2000 to 2002. A detailed analysis of four storms with Kp from 5+ to 9− is presented. Three troughs were identified: sub-auroral, mid-latitude, and low-latitude. The sub-auroral trough is usually defined as the main ionospheric trough (MIT). The mid-latitude trough is observed equatorward of the MIT and is associated with the magnetospheric ring current; therefore, it is named the ring ionospheric trough (RIT). The RIT appears at the beginning of the storm recovery phase at geomagnetic latitudes of 40–45° GMLat (L = 1.75–2.0) and exists, for a long time, at the late stage of the recovery phase at latitudes of the residual ring current 50–55° GMLat (L ~ 2.5–3.0). The low-latitude trough (LLT) is discovered for the first time. It forms only during great storms at the latitudes of the internal radiation belt (IRB), 34–45° GMLat (L = 1.45–2.0). The LLT’s lowest latitude of 34° GMLat was recorded in the night sector (2–3 LT). The occurrence probability and position of the RIT and LLT depend on the hemisphere and longitude. Full article
Show Figures

Graphical abstract

Open AccessArticle
Spatiotemporal Characteristics and Trend Analysis of Two Evapotranspiration-Based Drought Products and Their Mechanisms in Sub-Saharan Africa
Remote Sens. 2021, 13(3), 533; https://doi.org/10.3390/rs13030533 - 02 Feb 2021
Viewed by 516
Abstract
Drought severity still remains a serious concern across Sub-Saharan Africa (SSA) due to its destructive impact on multiple sectors of society. In this study, the interannual variability and trends in the changes of the self-calibrating Palmer Drought Severity Index (scPDSI) based on the [...] Read more.
Drought severity still remains a serious concern across Sub-Saharan Africa (SSA) due to its destructive impact on multiple sectors of society. In this study, the interannual variability and trends in the changes of the self-calibrating Palmer Drought Severity Index (scPDSI) based on the Penman–Monteith (scPDSIPM) and Thornthwaite (scPDSITH) methods for measuring potential evapotranspiration (PET), precipitation (P), normalized difference vegetation index (NDVI), and sea surface temperature (SST) anomalies were investigated through statistical analysis of modeled and remote sensing data. It was shown that scPDSIPM and scPDSITH differed in the representation of drought characteristics over SSA. The regional trend magnitudes of scPDSI in SSA were 0.69 (scPDSIPM) and 0.2 mm/decade (scPDSITH), with a difference in values attributed to the choice of PET measuring method used. The scPDSI and remotely sensed-based anomalies of P and NDVI showed wetting and drying trends over the period 1980–2012 with coefficients of trend magnitudes of 0.12 mm/decade (0.002 mm/decade). The trend analysis showed increased drought events in the semi-arid and arid regions of SSA over the same period. A correlation analysis revealed a strong relationship between the choice of PET measuring method and both P and NDVI anomalies for monsoon and pre-monsoon seasons. The correlation analysis of the choice of PET measuring method with SST anomalies indicated significant positive and negative relationships. This study has demonstrated the applicability of multiple data sources for drought assessment and provides useful information for regional drought predictability and mitigation strategies. Full article
(This article belongs to the Special Issue Satellite Remote Sensing for Tropical Meteorology and Climatology)
Show Figures

Graphical abstract

Open AccessArticle
Modelling and Comparing Shading Effects of 3D Tree Structures with Virtual Leaves
Remote Sens. 2021, 13(3), 532; https://doi.org/10.3390/rs13030532 - 02 Feb 2021
Viewed by 743
Abstract
Reduced solar radiation brought about by trees on agricultural land can both positively and negatively affect crop growth. For a better understanding of this issue, we aim for an improved simulation of the shade cast by trees in agroforestry systems and a precise [...] Read more.
Reduced solar radiation brought about by trees on agricultural land can both positively and negatively affect crop growth. For a better understanding of this issue, we aim for an improved simulation of the shade cast by trees in agroforestry systems and a precise estimation of insolation reduction. We present a leaf creation algorithm to generate realistic leaves to be placed upon quantitative structure models (QSMs) of real trees. Further, we couple it with an enhanced approach of a 3D model capable of quantifying shading effects of a tree, at a high temporal and spatial resolution. Hence, 3D data derived from wild cherry trees (Prunus avium L.) generated by terrestrial laser scanner technology formed a basis for the tree reconstruction, and served as leaf-off mode. Two leaf-on modes were simulated: realistic leaves, fed with leaf data from wild cherry trees; and ellipsoidal leaves, having ellipsoids as leaf-replacement. For comparison, we assessed the shading effects using hemispherical photography as an alternative method. Results showed that insolation reduction was higher using realistic leaves, and that the shaded area was greater in size than with the ellipsoidal leaves or leaf-off conditions. All shading effects were similarly distributed on the ground, with the exception of those derived through hemispherical photography, which were greater in size, but with less insolation reduction than realistic leaves. The main achievements of this study are: the enhancement of the leaf-on mode for QSMs with realistic leaves, the updates of the shadow model, and the comparison of shading effects. We provide evidence that the inclusion of realistic leaves with precise 3D data might be fundamental to accurately model the shading effects of trees. Full article
Show Figures

Graphical abstract

Open AccessReview
Remote Sensing and Machine Learning in Crop Phenotyping and Management, with an Emphasis on Applications in Strawberry Farming
Remote Sens. 2021, 13(3), 531; https://doi.org/10.3390/rs13030531 - 02 Feb 2021
Viewed by 591
Abstract
Measurement of plant characteristics is still the primary bottleneck in both plant breeding and crop management. Rapid and accurate acquisition of information about large plant populations is critical for monitoring plant health and dissecting the underlying genetic traits. In recent years, high-throughput phenotyping [...] Read more.
Measurement of plant characteristics is still the primary bottleneck in both plant breeding and crop management. Rapid and accurate acquisition of information about large plant populations is critical for monitoring plant health and dissecting the underlying genetic traits. In recent years, high-throughput phenotyping technology has benefitted immensely from both remote sensing and machine learning. Simultaneous use of multiple sensors (e.g., high-resolution RGB, multispectral, hyperspectral, chlorophyll fluorescence, and light detection and ranging (LiDAR)) allows a range of spatial and spectral resolutions depending on the trait in question. Meanwhile, computer vision and machine learning methodology have emerged as powerful tools for extracting useful biological information from image data. Together, these tools allow the evaluation of various morphological, structural, biophysical, and biochemical traits. In this review, we focus on the recent development of phenomics approaches in strawberry farming, particularly those utilizing remote sensing and machine learning, with an eye toward future prospects for strawberries in precision agriculture. The research discussed is broadly categorized according to strawberry traits related to (1) fruit/flower detection, fruit maturity, fruit quality, internal fruit attributes, fruit shape, and yield prediction; (2) leaf and canopy attributes; (3) water stress; and (4) pest and disease detection. Finally, we present a synthesis of the potential research opportunities and directions that could further promote the use of remote sensing and machine learning in strawberry farming. Full article
(This article belongs to the Special Issue Digital Agriculture with Remote Sensing)
Show Figures

Graphical abstract

Open AccessArticle
Framework for Reconstruction of Pseudo Quad Polarimetric Imagery from General Compact Polarimetry
Remote Sens. 2021, 13(3), 530; https://doi.org/10.3390/rs13030530 - 02 Feb 2021
Viewed by 497
Abstract
Pseudo quad polarimetric (quad-pol) image reconstruction from the hybrid dual-pol (or compact polarimetric (CP)) synthetic aperture radar (SAR) imagery is a category of important techniques for radar polarimetric applications. There are three key aspects concerned in the literature for the reconstruction methods, i.e., [...] Read more.
Pseudo quad polarimetric (quad-pol) image reconstruction from the hybrid dual-pol (or compact polarimetric (CP)) synthetic aperture radar (SAR) imagery is a category of important techniques for radar polarimetric applications. There are three key aspects concerned in the literature for the reconstruction methods, i.e., the scattering symmetric assumption, the reconstruction model, and the solving approach of the unknowns. Since CP measurements depend on the CP mode configurations, different reconstruction procedures were designed when the transmit wave varies, which means the reconstruction procedures were not unified. In this study, we propose a unified reconstruction framework for the general CP mode, which is applicable to the mode with an arbitrary transmitted ellipse wave. The unified reconstruction procedure is based on the formalized CP descriptors. The general CP symmetric scattering model-based three-component decomposition method is also employed to fit the reconstruction model parameter. Finally, a least squares (LS) estimation method, which was proposed for the linear π/4 CP data, is extended for the arbitrary CP mode to estimate the solution of the system of non-linear equations. Validation is carried out based on polarimetric data sets from both RADARSAT-2 (C-band) and ALOS-2/PALSAR (L-band), to compare the performances of reconstruction models, methods, and CP modes. Full article
(This article belongs to the Section Remote Sensing Image Processing)
Show Figures

Graphical abstract

Open AccessArticle
Monitoring the Coastal Changes of the Po River Delta (Northern Italy) since 1911 Using Archival Cartography, Multi-Temporal Aerial Photogrammetry and LiDAR Data: Implications for Coastline Changes in 2100 A.D.
Remote Sens. 2021, 13(3), 529; https://doi.org/10.3390/rs13030529 - 02 Feb 2021
Viewed by 393
Abstract
Interaction between land subsidence and sea level rise (SLR) increases the hazard in coastal areas, mainly for deltas, characterized by flat topography and with great social, ecological, and economic value. Coastal areas need continuous monitoring as a support for human intervention to reduce [...] Read more.
Interaction between land subsidence and sea level rise (SLR) increases the hazard in coastal areas, mainly for deltas, characterized by flat topography and with great social, ecological, and economic value. Coastal areas need continuous monitoring as a support for human intervention to reduce the hazard. Po River Delta (PRD, northern Italy) in the past was affected by high values of artificial land subsidence: even if at low rates, anthropogenic settlements are currently still in progress and produce an increase of hydraulic risk due to the loss of surface elevation both of ground and levees. Many authors have provided scenarios for the next decades with increased flooding in densely populated areas. In this work, a contribution to the understanding future scenarios based on the morphological changes that occurred in the last century on the PRD coastal area is provided: planimetric variations are reconstructed using two archival cartographies (1911 and 1924), 12 multi-temporal high-resolution aerial photogrammetric surveys (1933, 1944, 1949, 1955, 1962, 1969, 1977, 1983, 1990, 1999, 2008, and 2014), and four LiDAR (light detection and ranging) datasets (acquired in 2006, 2009, 2012, and 2018): obtained results, in terms of emerged surfaces variations, are linked to the available land subsidence rates (provided by leveling, GPS—global positioning system, and SAR—synthetic aperture radar data) and to the expected SLR values, to perform scenarios of the area by 2100: results of this work will be useful to mitigate the hazard by increasing defense systems and preventing the risk of widespread flooding. Full article
(This article belongs to the Special Issue Remote Sensing Applications in Coastal Environment)
Show Figures

Graphical abstract

Open AccessArticle
C3Net: Cross-Modal Feature Recalibrated, Cross-Scale Semantic Aggregated and Compact Network for Semantic Segmentation of Multi-Modal High-Resolution Aerial Images
Remote Sens. 2021, 13(3), 528; https://doi.org/10.3390/rs13030528 - 02 Feb 2021
Viewed by 405
Abstract
Semantic segmentation of multi-modal remote sensing images is an important branch of remote sensing image interpretation. Multi-modal data has been proven to provide rich complementary information to deal with complex scenes. In recent years, semantic segmentation based on deep learning methods has made [...] Read more.
Semantic segmentation of multi-modal remote sensing images is an important branch of remote sensing image interpretation. Multi-modal data has been proven to provide rich complementary information to deal with complex scenes. In recent years, semantic segmentation based on deep learning methods has made remarkable achievements. It is common to simply concatenate multi-modal data or use parallel branches to extract multi-modal features separately. However, most existing works ignore the effects of noise and redundant features from different modalities, which may not lead to satisfactory results. On the one hand, existing networks do not learn the complementary information of different modalities and suppress the mutual interference between different modalities, which may lead to a decrease in segmentation accuracy. On the other hand, the introduction of multi-modal data greatly increases the running time of the pixel-level dense prediction. In this work, we propose an efficient C3Net that strikes a balance between speed and accuracy. More specifically, C3Net contains several backbones for extracting features of different modalities. Then, a plug-and-play module is designed to effectively recalibrate and aggregate multi-modal features. In order to reduce the number of model parameters while remaining the model performance, we redesign the semantic contextual extraction module based on the lightweight convolutional groups. Besides, a multi-level knowledge distillation strategy is proposed to improve the performance of the compact model. Experiments on ISPRS Vaihingen dataset demonstrate the superior performance of C3Net with 15× fewer FLOPs than the state-of-the-art baseline network while providing comparable overall accuracy. Full article
(This article belongs to the Special Issue Big Remotely Sensed Data)
Show Figures

Figure 1

Open AccessReview
Hand Gestures Recognition Using Radar Sensors for Human-Computer-Interaction: A Review
Remote Sens. 2021, 13(3), 527; https://doi.org/10.3390/rs13030527 - 02 Feb 2021
Viewed by 580
Abstract
Human–Computer Interfaces (HCI) deals with the study of interface between humans and computers. The use of radar and other RF sensors to develop HCI based on Hand Gesture Recognition (HGR) has gained increasing attention over the past decade. Today, devices have built-in radars [...] Read more.
Human–Computer Interfaces (HCI) deals with the study of interface between humans and computers. The use of radar and other RF sensors to develop HCI based on Hand Gesture Recognition (HGR) has gained increasing attention over the past decade. Today, devices have built-in radars for recognizing and categorizing hand movements. In this article, we present the first ever review related to HGR using radar sensors. We review the available techniques for multi-domain hand gestures data representation for different signal processing and deep-learning-based HGR algorithms. We classify the radars used for HGR as pulsed and continuous-wave radars, and both the hardware and the algorithmic details of each category is presented in detail. Quantitative and qualitative analysis of ongoing trends related to radar-based HCI, and available radar hardware and algorithms is also presented. At the end, developed devices and applications based on gesture-recognition through radar are discussed. Limitations, future aspects and research directions related to this field are also discussed. Full article
Show Figures

Graphical abstract

Open AccessArticle
Hyperspectral Image Classification with Localized Graph Convolutional Filtering
Remote Sens. 2021, 13(3), 526; https://doi.org/10.3390/rs13030526 - 02 Feb 2021
Viewed by 522
Abstract
The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be [...] Read more.
The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors. Full article
Show Figures

Graphical abstract

Open AccessArticle
Mapping 20 Years of Urban Expansion in 45 Urban Areas of Sub-Saharan Africa
Remote Sens. 2021, 13(3), 525; https://doi.org/10.3390/rs13030525 - 02 Feb 2021
Viewed by 608
Abstract
By 2050, half of the net increase in the world’s population is expected to reside in sub-Saharan Africa (SSA), driving high urbanization rates and drastic land cover changes. However, the data-scarce environment of SSA limits our understanding of the urban dynamics in the [...] Read more.
By 2050, half of the net increase in the world’s population is expected to reside in sub-Saharan Africa (SSA), driving high urbanization rates and drastic land cover changes. However, the data-scarce environment of SSA limits our understanding of the urban dynamics in the region. In this context, Earth Observation (EO) is an opportunity to gather accurate and up-to-date spatial information on urban extents. During the last decade, the adoption of open-access policies by major EO programs (CBERS, Landsat, Sentinel) has allowed the production of several global high resolution (10–30 m) maps of human settlements. However, mapping accuracies in SSA are usually lower, limited by the lack of reference datasets to support the training and the validation of the classification models. Here we propose a mapping approach based on multi-sensor satellite imagery (Landsat, Sentinel-1, Envisat, ERS) and volunteered geographic information (OpenStreetMap) to solve the challenges of urban remote sensing in SSA. The proposed mapping approach is assessed in 17 case studies for an average F1-score of 0.93, and applied in 45 urban areas of SSA to produce a dataset of urban expansion from 1995 to 2015. Across the case studies, built-up areas averaged a compound annual growth rate of 5.5% between 1995 and 2015. The comparison with local population dynamics reveals the heterogeneity of urban dynamics in SSA. Overall, population densities in built-up areas are decreasing. However, the impact of population growth on urban expansion differs depending on the size of the urban area and its income class. Full article
Show Figures

Graphical abstract

Open AccessArticle
Earth Observation-Informed Risk Maps of the Lyme Disease Vector Ixodes scapularis in Central and Eastern Canada
Remote Sens. 2021, 13(3), 524; https://doi.org/10.3390/rs13030524 - 02 Feb 2021
Viewed by 519
Abstract
Climate change is facilitating the geographic range expansion of populations of the tick vector of Lyme disease Ixodes scapularis in Canada. Here, we characterize and map the spatio-temporal variability of environments suitable for I. scapularis using Earth observation (EO) data. A simple algorithm [...] Read more.
Climate change is facilitating the geographic range expansion of populations of the tick vector of Lyme disease Ixodes scapularis in Canada. Here, we characterize and map the spatio-temporal variability of environments suitable for I. scapularis using Earth observation (EO) data. A simple algorithm for I. scapularis occurrence (cumulative degree-days and forest: CSDF) was developed by combining cumulative annual surface degree-days above 0 °C and forest cover. To map the environmental risk of I. scapularis (risk of I. scapularis: RIS) in central and eastern Canada from 2000 to 2015, CSDF was adjusted using data from an I. scapularis population model. CSDF was validated using cumulative annual degree days >0 °C (CADD) from meteorological stations, and CSDF was strongly associated with CADD (n = 52, R2 > 0.86, p < 0.001). Data on field surveillance for I. scapularis ticks (2008 to 2018) were used to validate the risk maps. The presence of I. scapularis ticks was significantly associated with CSDF, and at a limit of 2800, sensitivity approached 100%. RIS increased over the study period, with the highest values in 2012 and the lowest in 2000. The RIS was on average higher in Ontario and Quebec compared to other provinces, and it was higher in the southern parts of the provinces. The proportion of the populated areas with a positive RIS increased on average in central and eastern Canada from 2000 to 2015. Predicted I. scapularis occurrence identifies areas with a more probable risk of tick bites, Lyme disease, and other I. scapularis-borne diseases, which can help guide targeted surveillance, prevention, and control interventions. Full article
Show Figures

Figure 1

Open AccessArticle
Downscaling Groundwater Storage Data in China to a 1-km Resolution Using Machine Learning Methods
Remote Sens. 2021, 13(3), 523; https://doi.org/10.3390/rs13030523 - 02 Feb 2021
Viewed by 534
Abstract
High-resolution and continuous hydrological products have tremendous importance for the prediction of water-related trends and enhancing the capability for sustainable water resources management under climate change and human impacts. In this study, we used the random forest (RF) and extreme gradient boosting (XGBoost) [...] Read more.
High-resolution and continuous hydrological products have tremendous importance for the prediction of water-related trends and enhancing the capability for sustainable water resources management under climate change and human impacts. In this study, we used the random forest (RF) and extreme gradient boosting (XGBoost) methods to downscale groundwater storage (GWS) from 1° (~110 km) to 1 km by downscaling Gravity Recovery and Climate Experiment (GRACE) and Global Land Data Assimilation System (GLDAS) data from 1° (~110 km) and 0.25° (~25 km) respectively, to 1 km for China. Three evaluation metrics were employed for the testing dataset for 2004−2016: The R2 ranged from 0.77−0.89 for XGBoost (0.74−0.86 for RF), the correlation coefficient (CC) ranged from 0.88−0.94 for XGBoost (0.88−0.93 for RF) and the root-mean-square error (RMSE) ranged from 0.37−2.3 for XGBoost (0.4−2.53 for RF). The R2 of the XGBoost models for GLDAS was 0.64−0.82 (0.63−0.82 for RF), the CC was 0.80−0.91 (0.80−0.90 for RF) and the RMSE was 0.63−1.75 (0.63−1.77 for RF). The downscaled GWS derived from GRACE and GLDAS were validated using in situ measurements by comparing the time series variations and the downscaled products maintained the accuracy of the original data. The interannual changes within 9 river basins between pre- and post-downscaling were consistent, emphasizing the reliability of the downscaled products. Ultimately, annual downscaled TWS, GLDAS and GWS products were provided from 2004 to 2016, providing a solid data foundation for studying local GWS changes, conducting finer-scale hydrological studies and adapting water resources management and policy formulation to local condition. Full article
(This article belongs to the Section Remote Sensing in Geology, Geomorphology and Hydrology)
Show Figures

Figure 1

Open AccessArticle
Investigation of Polar Mesospheric Summer Echoes Using Linear Discriminant Analysis
Remote Sens. 2021, 13(3), 522; https://doi.org/10.3390/rs13030522 - 02 Feb 2021
Viewed by 497
Abstract
Polar Mesospheric Summer Echoes (PMSE) are distinct radar echoes from the Earth’s upper atmosphere between 80 to 90 km altitude that form in layers typically extending only a few km in altitude and often with a wavy structure. The structure is linked to [...] Read more.
Polar Mesospheric Summer Echoes (PMSE) are distinct radar echoes from the Earth’s upper atmosphere between 80 to 90 km altitude that form in layers typically extending only a few km in altitude and often with a wavy structure. The structure is linked to the formation process, which at present is not yet fully understood. Image analysis of PMSE data can help carry out systematic studies to characterize PMSE during different ionospheric and atmospheric conditions. In this paper, we analyze PMSE observations recorded using the European Incoherent SCATter (EISCAT) Very High Frequency (VHF) radar. The collected data comprises of 18 observations from different days. In our analysis, the image data is divided into regions of a fixed size and grouped into three categories: PMSE, ionosphere, and noise. We use statistical features from the image regions and employ Linear Discriminant Analysis (LDA) for classification. Our results suggest that PMSE regions can be distinguished from ionosphere and noise with around 98 percent accuracy. Full article
(This article belongs to the Section Remote Sensing Image Processing)
Show Figures

Graphical abstract

Open AccessArticle
Assessing Remote Sensing Vegetation Index Sensitivities for Tall Fescue (Schedonorus arundinaceus) Plant Health with Varying Endophyte and Fertilizer Types: A Case for Improving Poultry Manuresheds
Remote Sens. 2021, 13(3), 521; https://doi.org/10.3390/rs13030521 - 02 Feb 2021
Viewed by 758
Abstract
Tall fescue (Schedonorus arundinaceus) is a common perennial forage in cattle pastures of the southeastern United States. A mutualistic fungal endophyte normally infects the grass and produces ergot alkaloids toxic to livestock, but fungal biotypes that have no ergot alkaloid production [...] Read more.
Tall fescue (Schedonorus arundinaceus) is a common perennial forage in cattle pastures of the southeastern United States. A mutualistic fungal endophyte normally infects the grass and produces ergot alkaloids toxic to livestock, but fungal biotypes that have no ergot alkaloid production have been developed. Here remote sensing methods were used to assess plant health in 1 ha grazed paddocks with application amongst different combinations of fertilizer sources (inorganic and broiler litter) and endophyte associations (wild, novel–tall fescue MaxQ type with novel endophyte, and free). Broiler litter fertilization is common in the region due to the presence of many chicken farms. Moreover, broiler litter costs are comparable to inorganic fertilizer depending on distance from source to application. Incorporating remote sensing, we tested the sensitivity of three indices: normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and land surface water index (LSWI) to assess fescue plant health. Indices were obtained from satellite imagery provided by Landsat 7 ETM+ between the years 2005 and 2009. Sensitivity analytics suggested that LSWI was the optimum index to determine fescue plant health. The year experiencing drought (determined by annual precipitation) showed significant difference between fertilizer types (p = 0.05) and a nearly significant difference between endophyte associations (p = 0.08). There was no significant difference in years with normal or wet precipitation rates due to tall fescue endophyte association or type of fertilization. Limited availability of satellite imagery during parts of the five years of study might have influenced outcomes of statistical analyses. Nevertheless, the data and findings point to the potential use of satellite imagery in assessing grazingland tall fescue health and advancing the concept of poultry manureshed in the region or elsewhere where poultry manure production is extensive. Full article
Show Figures

Graphical abstract

Open AccessArticle
Ecological Monitoring with Spy Satellite Images—The Case of Red Wood Ants in Romania
Remote Sens. 2021, 13(3), 520; https://doi.org/10.3390/rs13030520 - 01 Feb 2021
Viewed by 796
Abstract
Dynamics of habitat conditions drive important changes in distribution and abundance of animal species making monitoring an important but also a challenging task when data from the past are scarce. We compared the distribution of ant mounds in the 1960s with recent inventories [...] Read more.
Dynamics of habitat conditions drive important changes in distribution and abundance of animal species making monitoring an important but also a challenging task when data from the past are scarce. We compared the distribution of ant mounds in the 1960s with recent inventories (2018), looking at changes in canopy cover over time, in a managed forest. Both historical and recent sources of information were used. Habitat suitability at present was determined using a Normalized Difference Vegetation Index (NDVI) image as a proxy for stand canopy cover. The NDVI product was obtained using Google Earth Engine and Sentinel 2 repository. For past conditions (no spectral information available), presence of edges and more open canopies was assessed on a Corona spy-satellite image and based on information from old forest management plans. A threshold distance of 30 m was used to assess location of ant nests compared to favorable habitats. Both old and new information sources showed that ants prefer intermediate canopy cover conditions in their vicinity. Nests remained clustered because of the heterogeneous habitat conditions, but spatial distribution has changed due to canopy alteration along time. The analysis on the NDVI was effective for 82% of cases (i.e., nests occurred within 30 m from favorable habitats). For all the remaining nests (18%), the Google Earth high resolution satellite image revealed in their vicinity the presence of small canopy gaps (undetected by the NDVI). These results show that historical satellite images are very useful for explaining the long-term dynamics of ant colonies. In addition, the use of modern remote sensing techniques provides a reliable and expedite method in determining the presence of favorable small-scale habitat, offering a very useful tool for ecological monitoring across large landscapes and in very different areas, especially in the context of ecosystem dynamics driven and exacerbated by climate change. Full article
(This article belongs to the Section Forest Remote Sensing)
Show Figures

Graphical abstract

Open AccessEditorial
Editorial for the Special Issue: Multispectral and Hyperspectral Remote Sensing Data for Mineral Exploration and Environmental Monitoring of Mined Areas
Remote Sens. 2021, 13(3), 519; https://doi.org/10.3390/rs13030519 - 01 Feb 2021
Viewed by 552
Abstract
In recent decades, multispectral and hyperspectral remote sensing data provide unprecedented opportunities for the initial stages of mineral exploration and environmental hazard monitoring [...] Full article
Open AccessArticle
Shore Evidences of a High Antarctic Ocean Wave Event: Geomorphology, Event Reconstruction and Coast Dynamics through a Remote Sensing Approach
Remote Sens. 2021, 13(3), 518; https://doi.org/10.3390/rs13030518 - 01 Feb 2021
Viewed by 437
Abstract
Remote sensing can be helpful in defining the dynamic of a high-latitude coastal environment where the role of cryogenic processes like sea-ice or permafrost are the main drivers together with storm surge and wind action. Here we examined the geomorphological dynamics of a [...] Read more.
Remote sensing can be helpful in defining the dynamic of a high-latitude coastal environment where the role of cryogenic processes like sea-ice or permafrost are the main drivers together with storm surge and wind action. Here we examined the geomorphological dynamics of a beach located at Edmonson Point (74° S) not far from the Italian Antarctic Station “Mario Zucchelli” between 1993 and 2019 using different remote sensing techniques and field measurements. Our data demonstrate that the average rate of surficial increase of the beach (0.002 ± 0.032 m yr−1) was slightly higher than the uplift rate determined by previous authors (0–1 cm yr−1) in case of pure isostatic rebound. However, we suggest that the evolution of EPNB is likely due to the couple effect of vertical uplift and high wave-energy events. Indeed, the coastline accumulation could be related to the subsurface sea water infiltration and annually freezing at the permafrost table interface as aggradational ice as suggested by the ERT carried out in 1996. This ERT suggests the occurrence of saline frozen permafrost or hypersaline brines under the sea level while permafrost with ice occurred above the sea level. The beach also revealed areas that had quite high subsidence values (between 0.08 and 0.011 m yr−1) located in the area where ice content was higher in 1996 and where the active layer thickening and wind erosion could explain the measured erosion rates. Here, we also dated at the late morning of 15 February 2019 coastal flooding and defined a significant wave height of 1.95 m. During the high oceanic wave event the sea level increased advancing shoreward up to 360 m, three times higher than the previous reported storm surge (81 m) and with a sea level rise almost five times higher than has been previously recorded in the Ross Sea. Full article
(This article belongs to the Section Remote Sensing in Geology, Geomorphology and Hydrology)
Show Figures

Graphical abstract

Open AccessTechnical Note
Decreased Anthropogenic CO2 Emissions during the COVID-19 Pandemic Estimated from FTS and MAX-DOAS Measurements at Urban Beijing
Remote Sens. 2021, 13(3), 517; https://doi.org/10.3390/rs13030517 - 01 Feb 2021
Viewed by 535
Abstract
The COVID-19 pandemic has led to ongoing reductions in economic activity and anthropogenic emissions. Beijing was particular badly affected by lockdown measures during the early months of the COVID-19 pandemic. It has significantly reduced the CO2 emission and toxic air pollution (CO [...] Read more.
The COVID-19 pandemic has led to ongoing reductions in economic activity and anthropogenic emissions. Beijing was particular badly affected by lockdown measures during the early months of the COVID-19 pandemic. It has significantly reduced the CO2 emission and toxic air pollution (CO and NO2). We use column-averaged dry-air mole fractions of CO2 and CO (XCO2 and XCO) observed by a ground-based EM27/SUN Fourier transform spectrometer (FTS), the tropospheric NO2 column observed by MAX-DOAS and satellite remote sensing data (GOSAT and TROPOMI) to investigate the variations in anthropogenic CO2 emission related to COVID-19 lockdown in Beijing. The anomalies describe the spatio-temporal enhancement of gas concentration, which relates to the emission. Anomalies in XCO2 and XCO, and XNO2 (ΔXCO2, ΔXCO, and ΔXNO2) for ground-based measurements were calculated from the diurnal variability. Highly correlated daily XCO and XCO2 anomalies derived from FTS time series data provide the ΔXCO to ΔXCO2 ratio (the correlation slope). The ΔXCO to ΔXCO2 ratio in Beijing was lower in 2020 (8.2 ppb/ppm) than in 2019 (9.6 ppb/ppm). The ΔXCO to ΔXCO2 ratio originating from a polluted area was significantly lower in 2020. The reduction in anthropogenic CO2 emission was estimated to be 14.2% using FTS data. A comparable value reflecting the slowdown in growth of atmospheric CO2 over the same time period was estimated to be 15% in Beijing from the XCO2 anomaly from GOSAT, which was derived from the difference between the target area and the background area. The XCO anomaly from TROPOMI is reduced by 8.7% in 2020 compared with 2019, which is much smaller than the reduction in surface air pollution data (17%). Ground-based NO2 observation provides a 21.6% decline in NO2. The NO2 to CO2 correlation indicates a 38.2% decline in the CO2 traffic emission sector. Overall, the reduction in anthropogenic CO2 emission relating to COVID-19 lockdown in Beijing can be detected by the Bruker EM27/SUN Fourier transform spectrometer (FTS) and MAX-DOAS in urban Beijing. Full article
(This article belongs to the Special Issue Remote Sensing of Air Pollutants and Carbon Emissions in Megacities)
Show Figures

Figure 1

Open AccessArticle
Vision Transformers for Remote Sensing Image Classification
Remote Sens. 2021, 13(3), 516; https://doi.org/10.3390/rs13030516 - 01 Feb 2021
Viewed by 563
Abstract
In this paper, we propose a remote-sensing scene-classification method based on vision transformers. These types of networks, which are now recognized as state-of-the-art models in natural language processing, do not rely on convolution layers as in standard convolutional neural networks (CNNs). Instead, they [...] Read more.
In this paper, we propose a remote-sensing scene-classification method based on vision transformers. These types of networks, which are now recognized as state-of-the-art models in natural language processing, do not rely on convolution layers as in standard convolutional neural networks (CNNs). Instead, they use multihead attention mechanisms as the main building block to derive long-range contextual relation between pixels in images. In a first step, the images under analysis are divided into patches, then converted to sequence by flattening and embedding. To keep information about the position, embedding position is added to these patches. Then, the resulting sequence is fed to several multihead attention layers for generating the final representation. At the classification stage, the first token sequence is fed to a softmax classification layer. To boost the classification performance, we explore several data augmentation strategies to generate additional data for training. Moreover, we show experimentally that we can compress the network by pruning half of the layers while keeping competing classification accuracies. Experimental results conducted on different remote-sensing image datasets demonstrate the promising capability of the model compared to state-of-the-art methods. Specifically, Vision Transformer obtains an average classification accuracy of 98.49%, 95.86%, 95.56% and 93.83% on Merced, AID, Optimal31 and NWPU datasets, respectively. While the compressed version obtained by removing half of the multihead attention layers yields 97.90%, 94.27%, 95.30% and 93.05%, respectively. Full article
Show Figures

Figure 1

Open AccessArticle
Evaluation of Pre-Earthquake Anomalies of Borehole Strain Network by Using Receiver Operating Characteristic Curve
Remote Sens. 2021, 13(3), 515; https://doi.org/10.3390/rs13030515 - 01 Feb 2021
Viewed by 402
Abstract
In order to monitor temporal and spatial crustal activities associated with earthquakes, ground- and satellite-based monitoring systems have been installed in China since the 1990s. In recent years, the correlation between monitoring strain anomalies and local major earthquakes has been verified. In this [...] Read more.
In order to monitor temporal and spatial crustal activities associated with earthquakes, ground- and satellite-based monitoring systems have been installed in China since the 1990s. In recent years, the correlation between monitoring strain anomalies and local major earthquakes has been verified. In this study, we further evaluate the possibility of strain anomalies containing earthquake precursors by using Receiver Operating Characteristic (ROC) prediction. First, strain network anomalies were extracted in the borehole strain data recorded in Western China during 2010–2017. Then, we proposed a new prediction strategy characterized by the number of network anomalies in an anomaly window, Nano, and the length of alarm window, Talm. We assumed that clusters of network anomalies indicate a probability increase of an impending earthquake, and consequently, the alarm window would be the duration during which a possible earthquake would occur. The Area Under the ROC Curve (AUC) between true predicted rate, tpr, and false alarm rate, fpr, is measured to evaluate the efficiency of the prediction strategies. We found that the optimal strategy of short-term forecasts was established by setting the number of anomalies greater than 7 within 14 days and the alarm window at one day. The results further show the prediction strategy performs significantly better when there are frequent enhanced network anomalies prior to the larger earthquakes surrounding the strain network region. The ROC detection indicates that strain data possibly contain the precursory information associated with major earthquakes and highlights the potential for short-term earthquake forecasting. Full article
Show Figures

Graphical abstract

Open AccessArticle
Variations of Water Transparency and Impact Factors in the Bohai and Yellow Seas from Satellite Observations
Remote Sens. 2021, 13(3), 514; https://doi.org/10.3390/rs13030514 - 01 Feb 2021
Viewed by 507
Abstract
Water transparency, measured with Secchi disk depth (SDD), is an important parameter for describing the optical properties of a water body. This study evaluates variations of SDD and related impact factors in the Bohai and Yellow Seas (BYS). Based on a new mechanistic [...] Read more.
Water transparency, measured with Secchi disk depth (SDD), is an important parameter for describing the optical properties of a water body. This study evaluates variations of SDD and related impact factors in the Bohai and Yellow Seas (BYS). Based on a new mechanistic model proposed by Lee et al. (2015) applied to MODIS remote sensing reflectance data, climatological SDD variation from 2003 to 2019 was estimated. The annual mean images showed an increasing trend from the coastal zone to the deep ocean. Lower values were found in the Bohai Sea (BHS), while higher values observed in the center of the southern Yellow Sea (SYS). Additionally, the entire sea has shown a decreasing temporal tend, with the variation rate lowest in the BHS at 0.003 m y−1, and highest in the SYS at 0.015 m y−1. However, the weak increasing trend that appeared since 2017 suggests that water quality seems to have improved. Further, it displayed seasonal patterns of low in winter and spring and high in summer and autumn. The empirical orthogonal function (EOF) analysis of SDD variations over the BYS, shows that the first SDD EOF mode is the highest, strongly correlated with total suspended matter. With the high correlation coefficients of chromophoric dissolved organic matter, it illustrates that the SDD variation is mainly dominated by the optical components in the seawater, although correlation with chlorophyll-a is the weakest. The second and third EOF modes show that photosynthetically available radiation, sea surface temperature, sea surface salinity, and wind speed are the main covariates that cause SDD changes. Water transparency evaluation on a long-term scale is essential for water quality monitoring and marine ecosystem protection. Full article
(This article belongs to the Special Issue Seawater Bio-Optical Characteristics from Satellite Ocean Color Data)
Show Figures

Graphical abstract

Open AccessFeature PaperArticle
Hyperspectral Reflectance and Indices for Characterizing the Dynamics of Crop–Weed Competition for Water
Remote Sens. 2021, 13(3), 513; https://doi.org/10.3390/rs13030513 - 01 Feb 2021
Viewed by 488
Abstract
Understanding the spectral characteristics of crops in response to stress caused by weeds is a basic step in improving the precision of agricultural technologies that manage weeds in the field. This research focused on the competition between corn (Zea mays) and [...] Read more.
Understanding the spectral characteristics of crops in response to stress caused by weeds is a basic step in improving the precision of agricultural technologies that manage weeds in the field. This research focused on the competition between corn (Zea mays) and redroot pigweed (Amaranthus retroflexus), a common weed that strongly reduces corn yield. The aim of this research was to characterize the physiological changes that occur in corn during early growth because of crop–weed competition and to examine the ability to detect the effect of competition through hyperspectral measurements. A greenhouse experiment was conducted, and corn plants were examined during early growth, with and without weed competition. Hyperspectral measurements were combined with physiological measurements to examine the reflectance and photosynthetic activity of corn. Changes were expected to appear mainly in the short-wave infrared region (SWIR) due to competition for water. Relative water content (RWC), chlorophyll content, photosynthetic rate, and stomatal conductance were reduced in the presence of weeds, and intercellular CO2 levels increased. Deeper SWIR light absorption occurred in the weed treatment as expected, accompanied by spectral changes in the visible (VIS) and near infrared (NIR) ranges. The results highlight the potential of using spectral measurements as an indicator of competition for water. Full article
(This article belongs to the Special Issue Remote and Proximal Assessment of Plant Traits)
Show Figures

Graphical abstract

Open AccessArticle
Analyzing the Spatiotemporal Uncertainty in Urbanization Predictions
Remote Sens. 2021, 13(3), 512; https://doi.org/10.3390/rs13030512 - 01 Feb 2021
Viewed by 1050
Abstract
With the availability of computational resources, geographical information systems, and remote sensing data, urban growth modeling has become a viable tool for predicting urbanization of cities and towns, regions, and nations around the world. This information allows policy makers, urban planners, environmental and [...] Read more.
With the availability of computational resources, geographical information systems, and remote sensing data, urban growth modeling has become a viable tool for predicting urbanization of cities and towns, regions, and nations around the world. This information allows policy makers, urban planners, environmental and civil organizations to make investments, design infrastructure, extend public utility networks, plan housing solutions, and mitigate adverse environmental impacts. Despite its importance, urban growth models often discard the spatiotemporal uncertainties in their prediction estimates. In this paper, we analyzed the uncertainty in the urban land predictions by comparing the outcomes of two different growth models, one based on a widely applied cellular automata model known as the SLEUTH CA and the other one based on a previously published machine learning framework. We selected these two models because they are complementary, the first is based on human knowledge and pre-defined and understandable policies while the second is more data-driven and might be less influenced by any a priori knowledge or bias. To test our methodology, we chose the cities of Jiaxing and Lishui in China because they are representative of new town planning policies and have different characteristics in terms of land extension, geographical conditions, growth rates, and economic drivers. We focused on the spatiotemporal uncertainty, understood as the inherent doubt in the predictions of where and when will a piece of land become urban, using the concepts of certainty area in space and certainty area in time. The proposed analyses in this paper aim to contribute to better urban planning exercises, and they can be extended to other cities worldwide. Full article
Show Figures

Figure 1

Open AccessArticle
Airborne LiDAR Intensity Correction Based on a New Method for Incidence Angle Correction for Improving Land-Cover Classification
Remote Sens. 2021, 13(3), 511; https://doi.org/10.3390/rs13030511 - 01 Feb 2021
Viewed by 450
Abstract
Light detection and range (LiDAR) intensity is an important feature describing the characteristics of a target. The direct use of original intensity values has limitations for users, because the same objects may have different spectra, while different objects may have similar spectra in [...] Read more.
Light detection and range (LiDAR) intensity is an important feature describing the characteristics of a target. The direct use of original intensity values has limitations for users, because the same objects may have different spectra, while different objects may have similar spectra in the overlapping regions of airborne LiDAR intensity data. The incidence angle and range constitute the geometric configuration of the airborne measurement system, which has an important influence on the LiDAR intensity. Considering positional shift and rotation angle deviation of the laser scanner and the inertial measurement unit (IMU), a new method for calculating the incident angle is presented based on the rigorous geometric measurement model for airborne LiDAR. The improved approach was applied to experimental intensity data of two forms from a RIEGL laser scanner system mounted on a manned aerial platform. The results showed that the variation coefficient of the intensity values after correction in homogeneous regions is lower than that obtained before correction. The overall classification accuracy of the corrected intensity data of the first form (amplitude) is significantly improved by 30.01%, and the overall classification accuracy of the corrected intensity data of second form (reflectance) increased by 18.21%. The results suggest that the correction method is applicable to other airborne LiDAR systems. Corrected intensity values can be better used for classification, especially in more refined target recognition scenarios, such as road mark extraction and forest monitoring. This study provides useful guidance for the development of future LiDAR data processing systems. Full article
(This article belongs to the Special Issue Advances of Remote Sensing in Environmental Geoscience)
Show Figures

Graphical abstract

Open AccessArticle
Dual-Weighted Kernel Extreme Learning Machine for Hyperspectral Imagery Classification
Remote Sens. 2021, 13(3), 508; https://doi.org/10.3390/rs13030508 - 01 Feb 2021
Viewed by 466
Abstract
Due to its excellent performance in high-dimensional space, the kernel extreme learning machine has been widely used in pattern recognition and machine learning fields. In this paper, we propose a dual-weighted kernel extreme learning machine for hyperspectral imagery classification. First, diverse spatial features [...] Read more.
Due to its excellent performance in high-dimensional space, the kernel extreme learning machine has been widely used in pattern recognition and machine learning fields. In this paper, we propose a dual-weighted kernel extreme learning machine for hyperspectral imagery classification. First, diverse spatial features are extracted by guided filtering. Then, the spatial features and spectral features are composited by a weighted kernel summation form. Finally, the weighted extreme learning machine is employed for the hyperspectral imagery classification task. This dual-weighted framework guarantees that the subtle spatial features are extracted, while the importance of minority samples is emphasized. Experiments carried on three public data sets demonstrate that the proposed dual-weighted kernel extreme learning machine (DW-KELM) performs better than other kernel methods, in terms of accuracy of classification, and can achieve satisfactory results. Full article
(This article belongs to the Special Issue Classification and Feature Extraction Based on Remote Sensing Imagery)
Show Figures

Graphical abstract

Open AccessTechnical Note
Detection of Natural Gas Leakages Using a Laser-Based Methane Sensor and UAV
Remote Sens. 2021, 13(3), 510; https://doi.org/10.3390/rs13030510 - 31 Jan 2021
Viewed by 547
Abstract
The safety of the gas transmission infrastructure is one of the main concerns for infrastructure operating companies. Common gas pipelines’ tightness control is tedious and time-consuming. The development of new methods is highly desirable. This paper focuses on the applications of air-borne methods [...] Read more.
The safety of the gas transmission infrastructure is one of the main concerns for infrastructure operating companies. Common gas pipelines’ tightness control is tedious and time-consuming. The development of new methods is highly desirable. This paper focuses on the applications of air-borne methods for inspections of the natural gas pipelines. The main goal of this study is to test an unmanned aerial vehicle (UAV), equipped with a remote sensing methane detector, for natural gas leak detection from the pipeline network. Many studies of the use of the UAV with laser detectors have been presented in the literature. These studies include experiments mainly on the artificial methane sources simulating gas leaks. This study concerns the experiments on a real leakage of natural gas from a pipeline. The vehicle at first monitored the artificial source of methane to determine conditions for further experiments. Then the experiments on the selected section of the natural gas pipelines were conducted. The measurement data, along with spatial coordinates, were collected and analyzed using machine learning methods. The analysis enabled the identification of groups of spatially correlated regions which have increased methane concentrations. Investigations on the flight altitude influence on the accuracy of measurements were also carried out. A range of between 4 m and 15 m was depicted as optimal for data collection in the natural gas pipeline inspections. However, the results from the field experiments showed that areas with increased methane concentrations are significantly more difficult to identify, though they are still noticeable. The experiments also indicate that the lower altitudes of the UAV flights should be chosen. The results showed that UAV monitoring can be used as a tool for the preliminary selection of potentially untight gas pipeline sections. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop