生态红线区是维护国家或区域生态安全的关键区域,基于遥感技术建立生态红线区长时间动态监测与定量评价体系对区域生态系统演变研究具有重要意义.以1988-2017年8期Landsat TM/OLI影像为数据源,以遥感生态指数(RSEI)为评价指标,结合时序分析方法对南京市陆地生态红线区近30 a的生态环境时空格局和变化趋势进行了研究.结果表明:①生态红线区生态环境质量总体呈振荡上升趋势,RSEI均值由1988年的0.611上升到2017年的0.696;但各类型的生态红线区增长速率与幅度各异,森林公园增长最快,生态公益林次之,风景名胜区与自然保护区相对较慢,变化幅度较大的是森林公园与生态公益林,最小的是自然保护区.②生态红线区面积占比74.24％的区域呈现环境质量上升(改善)趋势,其中极显著增加、显著增加区域占比达到4.00％和3.86％;各类型生态红线区中环境改善面积占比最高的是自然保护区,达到93.65％;森林公园变化的显著性水平最高,有4.48％的区域表现为极显著增加,4.12％的区域表现为显著增加,自然保护区变化最不显著.

Most machine learning tasks can be categorized into classification or regression problems. Regression and classification models are normally used to extract useful geographic information from observed or measured spatial data, such as land cover classification, spatial interpolation, and quantitative parameter retrieval. This paper reviews the progress of four advanced machine learning methods for spatial data handling, namely, support vector machine (SVM)-based kernel learning, semi-supervised and active learning, ensemble learning, and deep learning. These four machine learning modes are representative because they improve learning performances from different views, for example, feature space transform and decision function (SVM), optimized uses of samples (semi-supervised and active learning), and enhanced learning models and capabilities (ensemble learning and deep learning). For spatial data handling via machine learning that can be improved by the four machine learning models, three key elements are learning algorithms, training samples, and input features. To apply machine learning methods to spatial data handling successfully, a four-level strategy is suggested: experimenting and evaluating the applicability, extending the algorithms by embedding spatial properties, optimizing the parameters for better performance, and enhancing the algorithm by multiple means. Firstly, the advances of SVM are reviewed to demonstrate the merits of novel machine learning methods for spatial data, running the line from direct use and comparison with traditional classifiers, and then targeted improvements to address multiple class problems, to optimize parameters of SVM, and to use spatial and spectral features. To overcome the limits of small-size training samples, semi-supervised learning and active learning methods are then utilized to deal with insufficient labeled samples, showing the potential of learning from small-size training samples. Furthermore, considering the poor generalization capacity and instability of machine learning algorithms, ensemble learning is introduced to integrate the advantages of multiple learners and to enhance the generalization capacity. The typical research lines, including the combination of multiple classifiers, advanced ensemble classifiers, and spatial interpolation, are presented. Finally, deep learning, one of the most popular branches of machine learning, is reviewed with specific examples for scene classification and urban structural type recognition from high-resolution remote sensing images. By this review, it can be concluded that machine learning methods are very effective for spatial data handling and have wide application potential in the big data era.

This study investigates the thermal behavior of local climate zones (LCZs) together with seasonal divergence. Firstly, LCZs were distinguished by combining satellite imagery and LiDAR data. Trees accounted for the highest proportion among the land cover type LCZs, whereas open mid-rise was the predominant zone in the built-up types. According to the comparison of mean LSTs, the results found that the warmest/coolest zones varied with seasons. However, large low-rise buildings acquired the highest mean LST among built-up type LCZs in all seasons. LCZ types with lower mean LSTs than that of the city, were limited to land cover type LCZs in spring and summer, but both land cover type LCZs and built-up type LCZs in autumn and winter. Building height had substantial impacts on LST, and LSTs in all seasons tended to increase as the building height decreased. However, LST demonstrated a decreased trend with the decrease of built-up area in summer, but the effect of built-up area almost disappeared for the other seasons. Another important finding was that, regardless of seasons, average LSTs exhibited significant differences among LCZs. LCZs were differentiated better in summer regarding LST than in other seasons, and trees were the most distinguishable zone in all seasons.

Effective features derived from an original hyperspectral image (HSI) are quite important to improve the classification performance. An improved feature set, namely HGFM, is constructed by integrating harmonic analysis (HA) optimized by a multiscale guided filter (GF) with morphological operation for HSI classification. To establish HGFM, HA is first adopted to convert the HSI from spectral space to the frequency domain represented by amplitude, phase, and residual. With the first component of minimum noise fraction obtained from the original HSI as the guidance image, the harmonic components are then processed by the multiscale GF. Finally, the obtained results are then operated via morphological opening by reconstruction and closing by reconstruction to generate an improved feature set for classification. The HGFM features are input to an ensemble learning (EL) based on classification framework, in which EL plays an auxiliary role to enhance the classification stability and reliability. Three commonly used HSIs are used for experiments, and different feature sets are evaluated by comparing EL and rotation forest, support vector machine optimized by particle swarm optimization, random forest, and others. Compared with benchmark feature sets, the proposed HGFM feature set can better depict the details of objects easily, and the experimental results confirm the effectiveness in terms of classification accuracy and generalization ability.

Automated extraction of buildings from earth observation (EO) data has long been a fundamental but challenging research topic. Combining data from different modalities (e.g., high-resolution imagery (HRI) and light detection and ranging (LiDAR) data) has shown great potential in building extraction. Recent studies have examined the role that deep learning (DL) could play in both multimodal data fusion and urban object extraction. However, DL-based multimodal fusion networks may encounter the following limitations: (1) the individual modal and cross-modal features, which we consider both useful and important for final prediction, cannot be sufficiently learned and utilized and (2) the multimodal features are fused by a simple summation or concatenation, which appears ambiguous in selecting cross-modal complementary information. In this paper, we address these two limitations by proposing a hybrid attention-aware fusion network (HAFNet) for building extraction. It consists of RGB-specific, digital surface model (DSM)-specific, and cross-modal streams to sufficiently learn and utilize both individual modal and cross-modal features. Furthermore, an attention-aware multimodal fusion block (Att-MFBlock) was introduced to overcome the fusion problem by adaptively selecting and combining complementary features from each modality. Extensive experiments conducted on two publicly available datasets demonstrated the effectiveness of the proposed HAFNet for building extraction.

Good knowledge of inland water dynamics is of great significance for water management, preserving ecological balance and supporting industrial and agricultural development. However, the existing water cover products and water extraction methods cannot meet the present needs of monitoring water distribution and dynamic changes accurately and timely, particularly in the areas frequently disturbed by human activities, such as the Taihu Lake region. This article proposed an expert knowledge system to detect annual stable water and separate aquaculture water from natural water, and a frequency-based approach is used to generate stable water map within a year. All available Landsat Level-2 images were used to generate annual 30-m resolution stable water products from 1984 to 2018, and analyze the historical spatial-temporal changes of the water body in the Taihu Lake region. Furthermore, we related each important graph change with a reality event at that time. The results suggest that human activities have an obviously stronger influence on surface water than climate fluctuations in the Taihu Lake region, and confirm the effectiveness of ecological protection policy in maintaining the stability of the total amount of natural water in the past few decades. The spatial-temporal disturbance of aquaculture also provided another perspective and a reliable evidence of previous studies on the influence of human activities on the eutrophication process of Taihu Lake.

As an essential ecological parameter, soil moisture is important for understanding the water exchange between the land surface and the atmosphere, especially in the Loess Plateau (China). Although Synthetic Aperture Radar (SAR) images can be used for soil moisture retrieval, it is still a challenge to mitigate the impacts of complex terrain over hilly areas. Therefore, the objective of this paper is to propose an improved approach for soil moisture estimation in gully fields based on the joint use of the Advanced Integral Equation Model (AIEM) and the Incidence Angle Correction Model (IACM) from Sentinel-1A observations. AIEM is utilized to build a simulation database of microwave backscattering coefficients from various radar parameters and surface parameters, which is the data basis for the retrieval modeling. IACM is proposed to correct the deviation between the local incidence angle at the scatterer and the radar viewing angle. The study area is located in the Loess Plateau of China, where the main land cover is mostly bare land and the terrain is complex. The Sentinel-1A SAR data in C-band with dual polarization acquired on October 19th, 2017 was adopted to extract the VV&VH polarimetric backscattering coefficients. The in situ measurements of soil moisture were collected on the same day of the SAR acquisition, for evaluating the accuracy of the SAR-derived soil moisture. The results showed that, firstly, the estimated soil moisture with volumetric content between 0% and 20% was in the majority. Subsequently, both the RMSE of estimation values (0.963%) and the standard deviation of absolute errors (0.957%) demonstrated a good accuracy of the improved approach. Moreover, the evaluation of IACM confirmed that the improved approach coupling IACM and AIEM was more efficient than employing AIEM solely. In conclusion, the proposed approach has a strong ability to estimate the soil moisture in the gully fields of the Loess Plateau from Sentinel-1A data.

Background: Centenarians represent an intriguing model for healthy aging. They appear to have adapted well to their lives and are likely to be influenced by previous lifestyle habits, and their life satisfaction is influenced by mental and psychological health. Objective: The aim of this study is to explore centenarians' lifestyles by sex and their potential contribution to life satisfaction. Method: In order to examine the common characteristics of centenarians in Hainan and the potential differences between men and women, a cross-sectional survey was conducted with 223 cognitively-intact Chinese centenarians. We also explored the association between life satisfaction and other physical factors using binary logistic regression and principal component analysis. Results: The results provided supplementary evidence indicating that women tended to live longer than men. However, the difference in life satisfaction observed between the sexes was not obvious (p = 0.659). The proportion of physical factors between each sex showed a similar trend in distribution. Most centenarians' lifestyles were similar, in that they followed a light diet and did not smoke or drink alcohol. Centenarians in better physical condition and with higher self-assessment, as well as those with "alcohol and tobacco habits," were more satisfied with their life. Of the factors examined in the binary logistic regression, sleep satisfaction was the only factor significantly positively correlated with life satisfaction (p < .01). Conclusion: The research findings elucidated physiological and psychological health in centenarians and provided a model of healthy aging strategies for reference purposes.

The contextual-based multi-source time-series remote sensing and proposed Comprehensive Heritage Area Threats Index (CHATI) index are used to analyze the spatiotemporal land use/land cover (LULC) and threats to the Mount Wutai World Heritage Area. The results show disturbances, such as forest coverage, vegetation conditions, mining area, and built-up area, in the research area changed dramatically. According to the CHATI, although different disturbances have positive or negative influences on environment, as an integrated system it kept stable from 1987 to 2018. Finally, this research uses linear regression and the F-test to mark the remarkable spatial-temporal variation. In consequence, the threats on Mount Wutai be addressed from the macro level and the micro level. Although there still have some drawbacks, the effectiveness of threat identification has been tested using field validation and the results are a reliable tool to raise the public awareness of WHA protection and governance.

Multi-temporal remote sensing dataset allows for cost-and time-efficient monitoring of land-cover vital to the conservation of ecosystems and biodiversity. The Very High Resolution (VHR) images provide the needed spatial resolution which is important for government management and decision-making. In this paper, we propose a workflow for detecting artificial surface expansion in ecological redline zones based on object-based image analysis and transfer matrix. The new increased artificial surface regions are further obtained by rule optimization in the preliminary results. Finally, 854 new artificial surface patches with a total area of more than 1.93 square kilometers were detected. The proposed approach quantifies the effects of human activities without high cost and time-consuming process, which is of great significance for the protection and management of ecological redline zones.

Detailed land use and land cover (LULC) information is one of the important information for land use surveys and applications related to the earth sciences. Therefore, LULC classification using very-high resolution remotely sensed imagery has been a hot issue in the remote sensing community. However, it remains a challenge to successfully extract LULC information from very-high resolution remotely sensed imagery, due to the difficulties in describing the individual characteristics of various LULC categories using single level features. The traditional pixel-wise or spectral-spatial based methods pay more attention to low-level feature representations of target LULC categories. In addition, deep convolutional neural networks offer great potential to extract high-level features to describe objects and have been successfully applied to scene understanding or classification. However, existing studies has paid little attention to constructing multi-level feature representations to better understand each category. In this paper, a multi-level feature representation framework is first designed to extract more robust feature representations for the complex LULC classification task using very-high resolution remotely sensed imagery. To this end, spectral reflection and morphological and morphological attribute profiles are used to describe the pixel-level and neighborhood-level information. Furthermore, a novel object-based convolutional neural networks (CNN) is proposed to extract scene-level information. The object-based CNN method combines advantages of object-based method and CNN method and can perform multi-scale analysis at the scene level. Then, the random forest method is employed to carry out the final classification using the multi-level features. The proposed method was validated on three challenging remotely sensed imageries including a hyperspectral image and two multispectral images with very-high spatial resolution, and achieved excellent classification performances.

Convolutional neural networks (CNN) have attracted tremendous attention in the remote sensing community due to its excellent performance in different domains. Especially for remote sensing scene classification, the CNN-based methods have brought a great breakthrough. However, it is not feasible to fully design and train a new CNN model for remote sensing scene classification, as this usually requires a large number of training samples and high computational costs. To alleviate these limitations of fully training a new model, some work attempts to use the pretrained CNN models as feature extractors to build feature representation of scene images for classification and has achieved impressive results. In this scheme, how to construct feature representation of scene image via the pretrained CNN model becomes the key process. Existing studies paid a little attention to build more discriminative feature representation by exploring the potential benefits of multilayer features from a single CNN model and different feature representations from multiple CNN models. To this end, this paper presents a fusion strategy to build the feature representation of the scene images by integrating multilayer features of a single pretrained CNN model, and extends it to a framework of multiple CNN models. For these purposes, a multiscale improved Fisher kernel coding method is used to build feature representation of the scene images on convolutional layers, and a feature fusion approach based on two feature subspace learning methods [principal component analysis (PCA)/spectral regression kernel discriminant analysis and PCA/spectral regression kernel locality preserving projection] is proposed to construct final fused features for scene classification. For validation and comparison purposes, the proposed approaches are evaluated with two challenging high-resolution remote sensing datasets and shows the competitive performance compared with existing state-of-the-art baselines such as fully trained CNN models, fine tuning CNN models, and other related works.

Urban remote sensing is a significant field of remote sensing applications.Under the processing of new-type urbanization in China,remote sensing will not only play an irreplaceable role in many areas such as urban eco-logical construction,land and space development,resource and environment carrying capacity monitoring,but also provide data source for urban planning management.Based on the researches of urban remote sensing,this paper mainly analyzes the development of several important directions of urban remote sensing.Moreover,a framework of urban remote sensing based on geographical perspective is constructed.Combined with typical examples,aspects in-cluding structure and pattern,elements and interactions,change and processes,functions and responses are further explored to demonstrate the development of urban remote sensing research.Finally,combined with the national de-mands and technological development,the future development of urban remote sensing is prospected from aspects of data sources,research objects,application topics,research objectives and technical methods.