Search

Seventy-percent of the terrestrial area of Hong Kong is covered by vegetation and 40% is protected as the Country Park. The above-ground biomass (AGB) acts as reliable source of carbon sink and while Hong Kong has recognized the importance of carbon sink in forest and urged for forest protection in the latest strategic plan, yet no study has been conducted on assessing the baseline of terrestrial AGB and its carbon storage. This study compared and estimated the AGB by the traditional allometric modeling and the Light Detection and Ranging (LiDAR) plot metrics at plot-level in a subtropical forest of Hong Kong. The study has tested five allometric models which were developed from pantropical regions, subtropical areas and locally. The best model was then selected as the dependent variable to develop the LiDAR-derived AGB model. The raw LiDAR point cloud was pre-processed to normalized height point cloud and hence generating the LiDAR metric as independent variables for the model development. Regression models were used to estimate AGB at various plot sizes (i.e., in 10-m, 5-m and 2.5-m radius). The models were then evaluated statistically and validated by bootstrapping and leave-one-out cross validation (LOOCV). The results indicated the LiDAR metric derived from larger plot size outperformed the smaller plot size, with model R2 of 0.864 and root-mean-square-error (RMSE) of 37.75 kg/ha. It also found that pantropical model was comparable to a site-specific model when including the bioclimatic variable in subtropical forests. This study provides the approach for delineating the baseline of terrestrial above-ground biomass and carbon stock in subtropical forests upon an appropriate plot size is being deployed. [ABSTRACT FROM AUTHOR]

Accurately identified trees can serve as a basis of estimating forest variables through the individual tree-based approach. Increasing richness of remote sensing data also provides opportunities to explore the potential uses of various types of data sources. This study adopted three widely used remote sensing data, including airborne light detection and ranging (LiDAR), unmanned aerial vehicle (UAV) photography and traditional digital aerial photos (DAP), and aimed to investigate their potentials on estimating tree heights and extracting individual tree information in four forested sites in Hong Kong with different tree compositions. Image-based point clouds were generated through photogrammetry. Local maxima and region growing methods were adopted to identify treetops and delineate tree crowns, respectively, with different fixed and variable window size settings. Tree heights obtained from remote sensing datasets resulted in correlation coefficients (r) = 0.58–0.94 and root-mean-square errors (RMSE) = 1.33–3.78 m compared to field-measured values and similar levels of correspondences among the datasets. Point cloud characteristics were highlighted through point-based and profile-based analysis. The highest F-scores for treetop detections in each site ranged from 0.53 to 0.69 with variations caused by different window sizes and data sources. Matched rates of reference trees were positively correlated (r = 0.19–0.49) with geometric properties including diameter at breast height (DBH), tree height, crown area, and distance to the nearest neighbour. No single remote sensing dataset was clearly superior in all methodologies in this study, but unique properties were demonstrated in terms of both data acquisitions and analysis. Knowledge and testing on both characteristics of study areas and data sources were important when deciding the best window size parameters. Heterogeneity of forest environment could be a major factor hindering the delineation performance with further influences on plot-level difference and tree-level detectability. [ABSTRACT FROM AUTHOR]

Hong Kong has great potential to develop ecotourism as an alternate tourism experience. In order to provide visitors with satisfaction and conserve and sustain natural resources, a comprehensive zoning plan is indispensable to identify areas for various purposes and activities. Geographic information system combined with multi-criteria decision analysis procedure can be used to formulate these plans in an objective and efficient way. This study used this approach to objectively identify potential sites for various ecotourism activities and tourism development potential in Lantau Island, Hong Kong SAR. The results were then used to evaluate the Lantau development plan proposed by the government. By integrating with quality conservation information, the island was further classified into four zones namely sanctuary, nature conservation, outdoor recreation, and tourism development through multi-objective analysis. The results showed that proposed sites for various recreational activities are of medium to high suitability, while other potential sites with high suitability were revealed. In addition, sites with conflicting objectives and those required further protection were also identified. The results can be used as an unbiased guide for Lantau development. This study also demonstrated ecotourism planning and development can be practically supported by geo-information tools combined with proper multi-criteria decision analysis procedures based on which better decision can be made. [ABSTRACT FROM AUTHOR]

Feature extraction has been a major area of research in remote sensing, and fractal feature is a natural characterization of complex objects across scales. Extending on the modified triangular prism (MTP) method, we systematically discuss three factors closely related to the estimation of fractal dimensions of remotely sensed images. They are namely the (F1) number of steps, (F2) step size, and (F3) estimation accuracy of the facets' areas of the triangular prisms. Differing from the existing improved algorithms that separately consider these factors, we simultaneously take all factors to construct three new algorithms, namely the modification of the eight-pixel algorithm, the four corner and the moving-average MTP. Numerical experiments based on 4000 generated images show their superior performances over existing algorithms: our algorithms not only overcome the limitation of image size suffered by existing algorithms but also obtain similar average fractal dimension with smaller standard deviation, only 50% for images with high fractal dimensions. In the case of real-life application, our algorithms more likely obtain fractal dimensions within the theoretical range. Thus, the fractal nature uncovered by our algorithms is more reasonable in quantifying the complexity of remotely sensed images. Despite the similar performance of these three new algorithms, the moving-average MTP can mitigate the sensitivity of the MTP to noise and extreme values. Based on the numerical and real-life case study, we check the effect of the three factors, (F1)–(F3), and demonstrate that these three factors can be simultaneously considered for improving the performance of the MTP method. [ABSTRACT FROM AUTHOR]

Mangrove habitat is one of the most highly productive ecosystems. The distribution of mangrove species acts as an inventory to formulate conservation management plans. This study explored the potential of combining hyperspectral (Earth-observing (EO)-1 Hyperion) and multi-temporal synthetic aperture radar (SAR) (Environmental Satellite (Envisat) ASAR) data, supported byin situfield surveys, to map mangrove species. Hyperspectral imaging captures a number of narrow contiguous spectral bands providing richer spectral details than those obtained from traditional broadband sensors. All-weather radar sensing allows continuous data acquisition and its signal penetrability can reveal canopy structural characteristics, which offer an additional data dimension that is not available in optical sensing. Through combining the two data types, this study achieved three objectives. First, facing the issue of dimensionality and limited field samples, feature selection techniques from computer science were adopted to select spectral and radar features that are crucial for mangrove species discrimination. Second, classification accuracy using various combinations of spectral and radar features was evaluated. Third, classification algorithms including maximum likelihood (ML), decision tree (DT), artificial neural network (ANN), and support vector machine (SVM) were used to estimate species distribution, and classification accuracy was compared. Results suggested that feature selection techniques are capable of identifying salient features in spectral and radar space that can effectively discriminate between mangrove species. Combining optical and radar data can improve classification accuracy. Among the classifiers, ANN produces more accurate and robust estimation. [ABSTRACT FROM PUBLISHER]

The article discusses the views of Spanish philosopher Francisco de Vitoria concerning the concepts of the supernatural and natural sovereignty. It examines Vitoria's views on sovereignty regarding Amerindians, the concept of the law of nations, also known as ius gentium, and the concept of sovereignty that pertains to the communal body as derived from the marriage of the Biblical characters and Adam and Eve. It also discusses Vitoria's idea of a Christian nation.

Remote sensing technology is a timely and cost-efficient method for leaf area index (LAI) estimation, especially for less accessible areas such as mangrove forests. Confounded by the poor penetrability of optical images, most previous studies focused on estimating the LAI of the main canopy, ignoring the understory. This study investigated the capability of multispectral Sentinel-2 (S2) imagery, airborne hyperspectral imagery (HSI), and airborne LiDAR data for overstory (OLe) and understory (ULe) LAI estimation of a multi-layered mangrove stand in Mai Po, Hong Kong, China. LiDAR data were employed to stratify the overstory and understory. Vegetation indices (VIs) and LiDAR metrics were generated as predictors to build regression models against the OLe and ULe with multiple parametric and non-parametric methods. The OLe model fitting results were typically better than ULe because of the dominant contribution of the overstory to the remotely sensed signal. A single red-edge VI derived from HSI data delivered the lowest RMSE of 0.12 and the highest R2adj of 0.79 for OLe model fitting. The synergetic use of LiDAR metrics and S2 VIs performed best for ULe model fitting with RMSE = 0.33, R2adj = 0.84. OLe estimation benefited from the high spatial and spectral resolution HSI that was found less confounded by the understory. In addition to their penetration attributes, LiDAR data could separately describe the upper and lower canopy, which reduced the noise from other components, thereby improving the ULe estimation. [ABSTRACT FROM AUTHOR]

This paper proposes a novel rough set approach to discover classification rules in real-valued spatial data in general and remotely sensed data in particular. A knowledge induction process is formulated to select optimal decision rules with a minimal set of features necessary and sufficient for a remote sensing classification task. The approach first converts a real-valued or integer-valued decision system into an interval-valued information system. A knowledge induction procedure is then formulated to discover all classification rules hidden in the information system. Two real-life applications are made to verify and substantiate the conceptual arguments. It demonstrates that the proposed approach can effectively discover in remotely sensed data the optimal spectral bands and optimal rule set for a classification task. It is also capable of unraveling critical spectral band(s) discerning certain classes. The framework paves the road for data mining in mixed spatial databases consisting of qualitative and quantitative data. [ABSTRACT FROM AUTHOR]

The green space of Hong Kong was studied using a normalized difference vegetation index (NDVI) derived from SPOT images. Spatial patterns of the magnitude and variability of 'greenness' were analyzed based on the mean and entropy of NDVI at the tertiary planning unit (TPU) level. Continuous loss of green space due to urban encroachment and hill fires was identified in many parts of the territory between 1987 and 1995. However, establishment of green belts and improved landscaping, as found in many new development projects, such as the Tsang Kwan O new town, resulted in the continuous gain in green space or percentage of woodland in a few locations. [ABSTRACT FROM AUTHOR]

Geographically and temporally weighted regression (GTWR) has been demonstrated as an effective tool for exploring spatiotemporal data under spatial and temporal heterogeneity. Exploiting the advantages of the two most popular GTWR methods, we propose an alternative GTWR with a good balance between complexity and interpretability via a unilateral temporal weighting scheme called unilateral GTWR (UGTWR). When compared to the other two popular GTWR methods, the simulation experiment shows that UGTWR has comparable estimation accuracy and model fit, but it is more efficient. Furthermore, we propose its multiscale extension, coined multiscale UGTWR (MUGTWR), to characterize the spatiotemporal dynamic regression relationships at multiple scales. The proposed MUGTWR was applied to the analysis of house prices in the period of 2014–2018 in Beijing as a case study. Our analysis reveals that MUGTWR can effectively capture different levels of spatiotemporal heterogeneity in selected factors affecting house prices at different scales. Therefore, this study is useful for the formulation of housing policy in which the spatiotemporal dynamics of house prices with respect to specific factors can be considered. [ABSTRACT FROM AUTHOR]

Land surface parameters play a crucial role in simulations of weather and air quality. This study investigated the impact of underlying surface parameters on meteorological fields and pollutant concentrations in the Greater Bay Area (GBA), China, during warm and cold season. Updated land surface parameters, namely land use type, leaf area index, vegetation fraction, albedo, and roughness length, were incorporated to improve simulations. The model showed 7%–14% improvements (in terms of the index of agreement) in wind speed simulations, whereas temperature and relative humidity were not sensitive to the adoption of updated parameters. Moreover, compared with the model with default parameters, the model with updated natural underlying surface parameters showed a 2–3 m/s reduction in cross-border wind speed during cold season in the GBA. The model also showed a 1–2 m/s increase in the wind speed in urban areas, owing to thermal contrast. During periods in which clean air came from the north, the reduced wind speed hindered ozone removal in the GBA. The use of updated underlying surface parameters enhanced the urban heat island effect by ∼2 K and increased the wind speed over urban areas by ∼2 m/s. The intensified urban heat island circulation generated strong updrafts and intensified sea breezes, promoting the penetration of sea breezes inland. Additionally, the intensified sea breeze and urban heat island circulation contributed to a ∼10-ppb reduction in ozone concentrations. Hence, incorporating the latest land surface parameters improved the simulation of meteorological fields and influenced cross-border pollutant transportation. This study highlights the importance of considering underlying surface characteristics in regional modelling and provides insights for air pollutant management. • Latest land surface parameters are incorporated into WRF-CAMx for model improvement. • These updated inputs provide improved meteorological simulation, especially on wind speed. • The local circulations and intense updraft induced by UHI modulate the transportation of O 3. [ABSTRACT FROM AUTHOR]

He attended the signing ceremony of 'Deepening Cooperation between Guangdong, Hong Kong and Macao and Promoting the GBA Construction Framework Agreement' in Hong Kong on 1 July 2017. From a "World Factory" to China's Bay Area: A Review of the Outline of the Development Plan for the Guangdong-Hong Kong-Macao Greater Bay Area The Outline of the Development Plan (ODP) for the Guangdong-Hong Kong-Macao Greater Bay Area, (a region formerly know n as the Pearl River Delta - PRD - or the "world's factory") marks China's determination to transform traditional manufacturing and accomplish the Fourth Industrial Revolution. [Extracted from the article]

Geographically weighted regression model with a spatially autoregressive term of the response variable (GWR‐Lag model for short) is a useful tool to simultaneously model spatial autocorrelation in the response variable and spatial heterogeneity in the regression relationship. The profile maximum likelihood estimation has been developed to calibrate the model, where a single bandwidth is used for all of the spatially varying coefficients. However, due to different spatial scales at which the explanatory variables might operate, the coefficients may have different levels of spatial heterogeneity and cannot be effectively estimated by a single bandwidth. To deal with such multiscale problem, a backfitting method is proposed to calibrate the GWR‐Lag model, where the optimal bandwidth size is separately selected for each coefficient and the autoregressive parameter is estimated by maximizing the log‐likelihood function. A simulation study with a comparison of the GWR‐based profile maximum likelihood (GWR‐ML) estimation is conducted to assess the performance of the backfitting approach. The empirical results show that the backfitting method not only provides useful scale information for each explanatory variable, but also yields more accurate estimators of the coefficients. Furthermore, a real‐life data set is analyzed to demonstrate the effectiveness of the backfitting approach. [ABSTRACT FROM AUTHOR]

Identification and mapping of various habitats with sufficient spatial details are essential to support environmental planning and management. Considering the complexity of diverse habitat types in a heterogeneous landscape, a context-dependent mapping framework is expected to be superior to traditional classification techniques. With the aim to produce a territory-wide habitat map in Hong Kong, a three-stage mapping procedure was developed to identify 21 habitats by combining very-high-resolution satellite images, geographic information system (GIS) layers and knowledge-based modification rules. In stage 1, several classification methods were tested to produce initial results with 11 classes from a WorldView-2/3 image mosaic using a combination of spectral, textural, topographic and geometric variables. In stage 2, modification rules were applied to refine the classification results based on contextual properties and ancillary data layers. Evaluation of the classified maps showed that the highest overall accuracy was obtained from pixel-based random forest classification (84.0%) and the implementation of modification rules led to an average 8.8% increase in the accuracy. In stage 3, the classification scheme was expanded to all 21 habitats through the adoption of additional rules. The resulting habitat map achieved >80% accuracy for most of the evaluated classes and >70% accuracy for the mixed habitats when validated using field-collected points. The proposed mapping framework was able to utilize different information sources in a systematic and controllable workflow. While transitional mixed habitats were mapped using class membership probabilities and a soft classification method, the identification of other habitats benefited from the hybrid use of remote-sensing classification and ancillary data. Adaptive implementation of classification procedures, development of appropriate rules and combination with spatial data are recommended when producing an integrated and accurate map. [ABSTRACT FROM AUTHOR]

Trend detection is model-dependent. We analyze this for auto-correlated temperature time series. By the comparison of two different models which both describe the same stochastic process, we can introduce the distinction between the observed trend and the intrinsic trend. We transform a model with correlated noise into the lagged dependent variable (LDV) model with white noise. Although the commonly used climate dynamical model usually contains the LDV, existing trend studies barely consider it. For the LDV model, the auto-correlation effect on trend detection not only induces the stochastic trend, but also leads to an additional trend by accumulating the intrinsic trend. The intrinsic trend exclusive of the auto-correlation effect should be more likely related to the external forcing like anthropogenic factors, which is actually the trend of main interest. By applying the LDV model to the monthly mean anomalies at the Potsdam, Hamburg, and Frankfurt stations, it is found that 87%, 78%, and 75%, respectively, of the observed trends are the intrinsic trend, which may be more relevant to anthropogenic factors; and the rest should be due to auto-correlation. Analysis of two additional Chinese stations, namely the Guangzhou and Turpan stations, demonstrates the general applicability of the LDV model for different climate zones. Our study refreshes the current understanding of the observed trend and the auto-correlation effect, which is expected to be beneficial in the exploration of the underlying mechanism of global warming. [ABSTRACT FROM AUTHOR]

Air pollution has been an environmental problem exerting serious impact on human health. An accurate prediction of air pollutant concentrations in space and time is essential to the mitigation and minimization of exposure to air pollution, particularly in cities. To take advantage of data collected at monitoring stations and the effect of secondary information such as meteorological factors, this paper proposes a flexible hierarchical Bayesian model (HBM) which can predict air pollutant concentrations in space and time. Within the framework, spatial temporal Kriging (STK) is employed for interpolation and the obtained results are used as priors. Because of the undesirable performance of the STK, the likelihood in the form of a nonlinear regression (NLR) with skewed normal residuals is employed to take into account the effect of meteorological factors to derive the posterior distribution of air pollutant concentrations. Due to high dimensionality and complexity, the formulation of the posterior distribution is non-analytic. We thus need to draw samples from the estimated parameters of the posterior distribution with Markov chain Monte Carlo (MCMC) method, and approximate the population characteristics with the sample characteristics. We evaluate the HBM with the concentrations of air pollutants and the meteorological variables from Northern China. For all pollutants, in the cross-validation (CV) experiments, the HBM reduces the root mean square error (RMSE) of NLR and STK by at least 0.08 and 0.4, and R 2 by at least 0.02 and 0.4. The empirical results show that the proposed HBM generally outperforms the NLR and STK in terms of efficiency, accuracy and robustness. The proposed framework is general enough for the analysis of spatial-temporal data of all kinds. [ABSTRACT FROM AUTHOR]

Understanding species distribution and canopy structure of mangrove forests is imperative for flora and fauna conservation in mangrove habitats. However, most mangrove studies focused on the top canopy layer without exploring the vertical structure of mangroves. This paper presents multi-layered mangrove mapping which considered both overstory and understory detection and species classification using multispectral WorldView-3 (WV-3) data, airborne hyperspectral images (HSI), and LiDAR point cloud. First, LiDAR returns were stratified into the overstory and understory by analyzing the profile of return height, which helped understand the vertical structure of the mangrove stands. Second, three classification algorithms Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) were compared by applying WV-3, HSI, LiDAR data, and their combinations to map seven vegetative species. Feature selection was conducted to identify important features and the optimal feature size prior to classification tasks. The measured and estimated understory canopy heights reached a high correlation coefficient of 0.71, which demonstrated the effectiveness of using LiDAR data and the proposed procedure to stratify multi-layered canopies. The combined HSI and LiDAR data produced satisfactory results by the three classifiers with overall accuracy (OA) varying from 0.86 to 0.88. And the species was also accurately mapped by integrating WV-3 and LiDAR data using both RF and SVM algorithms with OA attaining between 0.84 and 0.86. The results of this study highlight that (1) LiDAR data provided superior information to map the vertical structure of multi-layered mangroves, which provided valuable information to classify single-layered and dual-layered Kandelia obovata with understory beneath; (2) the combination of spectral and LiDAR features improved mangrove species classification; (3) and species mapping results derived from combined datasets appeared to be more influential by LiDAR features when using RF and SVM, but spectral features played a more important role in CNN. • The overstory and understory of mangroves were correctly stratified by LiDAR data. • Four types of vertical structure in the mangrove stand were classified. • The canopy stratification result contributed to mangrove species identification. • Multiple sources of data and classifiers were compared for species mapping. • Combining optical and LiDAR data improved the species prediction accuracy. [ABSTRACT FROM AUTHOR]

Because of the limitations of hardware devices, such as the sensors, processing capacity, and high accuracy altitude control equipment, traditional optical remote sensing (RS) imageries capture information regarding the same scene from mostly one single angle or a very small number of angles. Nowadays, with video satellites coming into service, obtaining imageries of the same scene from a more-or-less continuous array of angles has become a reality. In this paper, we analyze the differences between the traditional RS data and continuous multi-angle remote sensing (CMARS) data, and unravel the characteristics of the CMARS data. We study the advantages of using CMARS data for classification and try to capitalize on the complementarity of multi-angle information and, at the same time, to reduce the embedded redundancy. Our arguments are substantiated by real-life experiments on the employment of CMARS data in order to classify urban land covers while using a support vector machine (SVM) classifier. They show the superiority of CMARS data over the traditional data for classification. The overall accuracy may increase up to about 9% with CMARS data. Furthermore, we investigate the advantages and disadvantages of directly using the CMARS data, and how such data can be better utilized through the extraction of key features that characterize the variations of spectral reflectance along the entire angular array. This research lay the foundation for the use of CMARS data in future research and applications. [ABSTRACT FROM AUTHOR]

Mangroves have significant social, economic, environmental, and ecological values but they are under threat due to human activities. An accurate map of mangrove species distribution is required to effectively conserve mangrove ecosystem. This study evaluates the synergy of WorldView-3 (WV-3) spectral bands and high return density LiDAR-derived elevation metrics for classifying seven species in mangrove habitat in Mai Po Nature Reserve in Hong Kong, China. A recursive feature elimination algorithm was carried out to identify important spectral bands and LiDAR (Airborne Light Detection and Ranging) metrics whilst appropriate spatial resolution for pixel-based classification was investigated for discriminating different mangrove species. Two classifiers, support vector machine (SVM) and random forest (RF) were compared. The results indicated that the combination of 2 m resolution WV-3 and LiDAR data yielded the best overall accuracy of 0.88 by SVM classifier comparing with WV-3 (0.72) and LiDAR (0.79). Important features were identified as green (510–581 nm), red edge (705–745 nm), red (630–690 nm), yellow (585–625 nm), NIR (770–895 nm) bands of WV-3, and LiDAR metrics relevant to canopy height (e.g., canopy height model), canopy shape (e.g., canopy relief ratio), and the variation of height (e.g., variation and standard deviation of height). LiDAR features contributed more information than spectral features. The significance of this study is that a mangrove species distribution map with satisfactory accuracy can be acquired by the proposed classification scheme. Meanwhile, with LiDAR data, vertical stratification of mangrove forests in Mai Po was firstly mapped, which is significant to bio-parameter estimation and ecosystem service evaluation in future studies. [ABSTRACT FROM AUTHOR]

Studies of land surface dynamics in heterogeneous landscapes often require satellite images with a high resolution, both in time and space. However, the design of satellite sensors often inherently limits the availability of such images. Images with high spatial resolution tend to have relatively low temporal resolution, and vice versa. Therefore, fusion of the two types of images provides a useful way to generate data high in both spatial and temporal resolutions. A Bayesian data fusion framework can produce the target high-resolution image based on a rigorous statistical foundation. However, existing Bayesian data fusion algorithms, such as STBDF (spatio-temporal Bayesian data fusion) -I and -II, do not fully incorporate the mixed information contained in low-spatial-resolution pixels, which in turn might limit their fusion ability in heterogeneous landscapes. To enhance the capability of existing STBDF models in handling heterogeneous areas, this study proposes two improved Bayesian data fusion approaches, coined ISTBDF-I and ISTBDF-II, which incorporate an unmixing-based algorithm into the existing STBDF framework. The performance of the proposed algorithms is visually and quantitatively compared with STBDF-II using simulated data and real satellite images. Experimental results show that the proposed algorithms generate improved spatio-temporal-resolution images over STBDF-II, especially in heterogeneous areas. They shed light on the way to further enhance our fusion capability. [ABSTRACT FROM AUTHOR]

Air pollution has become a serious environmental problem causing severe consequences in our ecology, climate, health, and urban development. Effective and efficient monitoring and mitigation of air pollution require a comprehensive understanding of the air pollution process through a reliable database carrying important information about the spatiotemporal variations of air pollutant concentrations at various spatial and temporal scales. Traditional analysis suffers from the severe insufficiency of data collected by only a few stations. In this study, we propose a rigorous framework for the integration of air pollutant concentration data coming from the ground-based stations, which are spatially sparse but temporally dense, and mobile sensors, which are spatially dense but temporally sparse. Based on the integrated database which is relatively dense in space and time, we then estimate air pollutant concentrations for given location and time by applying a two-step local regression model to the data. This study advances the frontier of basic research in air pollution monitoring via the integration of station and mobile sensors and sets up the stage for further research on other spatiotemporal problems involving multi-source and multi-scale information. [ABSTRACT FROM AUTHOR]

Disturbances such as tropical cyclones and insect pests in mangroves can cause defoliation, tree mortality, and other changes in ecosystem processes. Understanding the resistance and resilience of mangroves to disturbance is critical to developing strategies for conservation. However, most studies apply multi-temporal optical data which have limited power to detect structural changes, especially for forests with complex architectures. We combined multispectral Sentinel-2 (S2) images and airborne LiDAR Scanning (ALS) datasets to assemble a comprehensive view of the effects of two disturbance events (a moth pest and a super-typhoon) on mangroves in Mai Po, Hong Kong. A series of normalized difference vegetation index (NDVI) estimates derived from S2 data indicated changes in greenness before and after the moth pest and typhoon events. An object-based stratification method was applied with ALS data to separate the overstory and understory to distinguish stratum changes. The results showed that moth larvae were more likely to encroach leafy mangroves of Avicennia marina. Double-layered and single-layered short mangroves have better resistance to typhoons than younger tall mangroves without understory beneath. NDVI recovered rapidly after three to six months post-disturbance but significant changes in canopy structures were found from the ALS data. Canopy gaps increased both in size and quantity in mature overstory areas, likely benefitting the growth of the understories beneath. Finally, the understory area grew resulting in a transition from single-layered to double-layered structures. The combination of multi-temporal LiDAR and multispectral data used here highlights the power of complementary remote sensing products in documenting mangrove ecosystem processes. • The study provides a comprehensive view of disturbance processes in mangroves. • NDVI recovered rapidly after three to six months post-disturbances. • LiDAR data reveals the canopy structures in both overstory and understory. • Double-layered or short mangroves have better resistance to typhoons. • Disturbances may facilitate a transition from single to double-layered structures. [ABSTRACT FROM AUTHOR]

Abstract: Geodesic distance estimation for data lying on a manifold is an important issue in many applications of nonlinear dimensionality reduction. In this paper, a method aiming at improving the precision of geodesic distance estimation is proposed. The method is constructed on the basic principle, locally linear assumption, underlying the manifold data. It presumes that the locally linear patch, expressed as a convex combination of neighbors of a vertex, approximately resides on the manifold, as well as the local neighborhood edge does. The proposed method essentially extends the search area from local edges, employed by existing methods, to local patches. This naturally leads to a more accurate geodesic distance estimation. An efficient algorithm for the method is constructed, and its computational complexity is also analyzed. Experiment results also show that the proposed method outperforms the existing methods in geodesic distance estimation. [Copyright &y& Elsevier]

Air pollution exerts serious impacts on human health and sustainable development. The accurate forecasting of air quality can guide the formulation of mitigation strategies and reduce exposure to air pollution. It is beneficial to explicitly consider both spatial and temporal information of multiple factors, e.g., the meteorological data, in the forecasting of air pollutant concentrations. The temporal information of relevant factors collected at a location should be considered for forecasting. In addition, these factors recorded at other locations may also provide useful information. Existing methods utilizing the spatio-temporal information of these relevant factors are usually based on some very complicated frameworks. In this study, we propose a novel and simple spatial attention-based long short-term memory (SA-LSTM) that combines LSTM and a spatial attention mechanism to adaptively utilize the spatio-temporal information of multiple factors for forecasting air pollutant concentrations. Specifically, the SA-LSTM employs gated recurrent connections to extract temporal information of multiple factors at individual locations, and the spatial attention mechanism to spatially fuse the temporal information extracted at these locations. This method is effective and applicable to forecast any air pollutant concentrations when spatio-temporal information of relevant factors has to be utilized. To validate the effectiveness of the proposed SA-LSTM, we apply it to forecast the daily air quality in Hong Kong, a high density city with peculiar cityscapes, by using the air quality and meteorological data. Empirical results demonstrate that the proposed SA-LSTM outperforms the conventional models with respect to one-day forecast accuracy, especially for extreme values. Moreover, the attention weights learned by the SA-LSTM can identify hotspots of the air pollution process for reducing computational complexity of forecasting and provide a better understanding of the underlying mechanism of air pollution. Unlabelled Image • A unified method adaptively utilizes spatio-temporal information of multiple factors. • The proposed model combines long short-term memory and a spatial attention mechanism. • The model can automatically identify hotspots of the air pollution process. • The proposed model performs well in forecasting air quality of Hong Kong. [ABSTRACT FROM AUTHOR]