Impervious surface (IS) and urban heat island (UHI) effects are always the research hotspots. However, the existing researches either ignore the impacts of IS material on UHI or fail to monitor the seasonal temporal variations of UHI. To this end, we explore the impacts of impervious surface materials on land surface temperature (LST) by analyzing their correlation and seasonal temporal variations. The results show that the mean LST for different impervious surface materials is statistically different from each other. Additionally, the contribution of IS to LST is affected by the material. Finally, the effect of impervious surface materials on LST has seasonal differences. These findings may help decision-makers develop more effective strategies to alleviate the urban heat island phenomenon.

This study presents a spectral–spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel to be classified. Specifically, it has two subnetworks. The spatial subnetwork introduces the proposed spatial self-attention module to exploit rich patch-based contextual information related to the center pixel. The spectral subnetwork introduces the proposed spectral self-attention module to exploit the long-range spectral correlation over local spectral features. The extracted spectral and spatial features are then adaptively fused for HSI classification. Experiments conducted on four HSI datasets demonstrate that the proposed network outperforms several state-of-the-art methods.

Integration of spectral and spatial information is extremely important for the classification of high-resolution hyperspectral images (HSIs). Gravitation describes interaction among celestial bodies which can be applied to measure similarity between data for image classification. However, gravitation is hard to combine with spatial information and rarely been applied in HSI classification. This paper proposes a Bayesian Gravitation based Classification (BGC) to integrate the spectral and spatial information of local neighbors and training samples. In the BGC method, each testing pixel is first assumed as a massive object with unit volume and a particular density, where the density is taken as the data mass in BGC. Specifically, the data mass is formulated as an exponential function of the spectral distribution of its neighbors and the spatial prior distribution of its surrounding training samples based on the Bayesian theorem. Then, a joint data gravitation model is developed as the classification measure, in which the data mass is taken to weigh the contribution of different neighbors in a local region. Four benchmark HSI datasets, i.e. the Indian Pines, Pavia University, Salinas, and Grss_dfc_2014, are tested to verify the BGC method. The experimental results are compared with that of several well-known HSI classification methods, including the support vector machines, sparse representation, and other eight state-of-the-art HSI classification methods. The BGC shows apparent superiority in the classification of high-resolution HSIs and also flexibility for HSIs with limited samples.

Synergetic use of both Synthetic Aperture Radar (SAR) and optical data has been applied for mapping impervious surface (IS) in recent years. However, researchers use only descending or ascending SAR to cooperate with optical data, which cannot avoid the problems caused by side looking of SAR, including layover and SAR shadow. This research explored and analyzed the impact of mapping IS by cooperating descending, ascending SAR and both of them with optical data respectively. To obtain a credible result, support vector machine (SVM) is employed to conduct the classification. The results indicated that the combined use of both descending and ascending SAR with optical data achieved the highest accuracy on IS mapping.

As the source of urban ecology, urban green space (UGS) has always been the focus of urban ecological research. The complex urban surface structure causes great interference to UGS extraction. In areas with high vegetation density, the vegetation index becomes rapidly saturated. Existing vegetation indices are not effective for the two problems due to that these indices do not make full use of the rich spectral information contained in hyperspectral image. To remedy these issues, a hyperspectral image based vegetation index (HSVI) is proposed. In the formulation of the HSVI numerator, we chose four new bands combination sensitive to vegetation to improve the identification of vegetation. We opt the sum of the red edge and green bands as the HSVI denominator and reconstruct the easily saturable band (760nm) in the form of exponential function to weaken the saturation problem. We use the hyperspectral image from Shanghai Theatre Academy and University of Houston with different geomorphological features to verify the effect of HSVI. The performance of HSVI is compared with three widely adopted vegetation indices, i.e., the normalized difference vegetation index (NDVI), the optimized soil-adjusted vegetation index (OSVAI) and the wide-dynamic-range vegetation index (WDRVI). The results show that the UGS extraction accuracy of HSVI is more than 90%, which is significantly better than the other indices. Meanwhile, HSVI can also solve the problem of vegetation index saturation. It can be proved that HSVI can fulfill the requirements of urban ecological research on a fine scale.

Singular spectrum analysis (SSA) and its 2-D variation (2D-SSA) have been successfully applied for effective feature extraction in hyperspectral imaging (HSI). However, they both cannot effectively use the spectral-spatial information, leading to a limited accuracy in classification. To tackle this problem, a novel 2D-SSA based multiscale feature fusion method, combining with segmented principal component analysis (SPCA), is proposed in this paper. The SPCA method is used for dimension reduction and spectral feature extraction, while multiscale 2D-SSA can extract abundant spatial features at different scales. In addition, a postprocessing via SPCA is applied on fused features to enhance the spectral discriminability. Experiments on two widely used datasets show that the proposed method outperforms two conventional SSA methods and other spectral-spatial classification methods in terms of the classification accuracy and computational cost.

Monitoring crop phenology is essential for analyzing the impacts of climate change and agronomic management on agricultural production. In this study, we proposed a new framework to monitor the phonological response of winter wheat using time series of Sentinel-1A as well as rainfall and temperature data, and ground phenological observations. The results showed that the radar backscatter coefficient ratio of VH to VV polarization showed the obvious seasonality that was related to vegetation phenology. Furthermore, the results showed that we can extract the phenology of winter wheat from the backscatter. Overall, this study clearly shows the strong response of Sentinel-1A data to winter wheat phenology and the potential for monitoring winter wheat phenology.

At present, remote sensing images are mutually restricted in temporal and spatial resolution. A single satellite sensor cannot obtain remote sensing images with both high spatial resolution and high temporal resolution. Spatiotemporal fusion of remote sensing images is a promising method to solve this issue. The spatial and temporal adaptive reflectance fusion model (STARFM) is a widely-accepted method for spatiotemporal fusion. However, STARFM selects similar pixels in a regular rectangular window. This neighborhood window has many different land cover types, which leads to wrong selection of similar pixels. Therefore, we develop a novel spatial and temporal adaptive reflectance fusion model based on superpixel, denote by S-STARFM. In the proposed method, the target pixels to be predicted are divided into two categories, including changed pixels and unchanged pixels. Then the superpixels are used to improve the selection of similar pixels. To verify the effectiveness of S-STARFM, the moderate resolution imaging spectrometer (MODIS) and Landsat Enhanced Thematic Mapper Plus (ETM+) data are used to generate high spatiotemporal resolution images. The prediction image accuracy shows that the proposed method outperforms the STARFM.

Feature extraction is of significance for hyperspectral image (HSI) classification. Compared with conventional handcrafted feature extraction methods, convolutional neural network (CNN) can automatically learn hierarchical features with discriminative information. However, two issues exist in applying CNN to HSI classification. One issue is how to represent the land covers at multiscale, the other is how to solve the “salt and pepper” noises caused by pixel-based CNN classification. To solve these issues, in this paper, a multiscale CNN is proposed to extract multiscale features for HSI classification, and then a region-based max voting scheme is applied to the classification map to solve the “salt and pepper” noises. Experiments on two classical data sets demonstrate that the proposed method is effective for HSI classification, especially for images with large scale changes.

The spatial-spectral classification for hyperspectral image (HSI) has been widely concerned. However, the traditional spatial-spectral classification methods are often easily affected by the noisy and heterogeneous pixel in the local region, leading to misclassification. Joint data gravitation classification (JDGC) shows that gravitation can suppress the interference of noisy pixel in the local region, but its flexibility is limited by high local heterogeneity. In this paper, a novel HSI classification method based on the local correlation of pixels and data gravitation (LC-DGC) is proposed. In LC-DGC, each pixel is assigned as an object with local mass, which is defined according to the correlation between each pixel and the central pixel in the local region. The pixels with small correlation contribute less to the local mass, which can decrease the interference of noisy and heterogeneous pixels effectively. Experimental results on two HSI datasets verify the superior classification performance of LC-DGC.

While change of lakes in the Tibetan Plateau (TP) is generally attributed to change of natural conditions, it is also important to evaluate the influence of human activities on lakes with the rapid increase of population in the plateau. Using a total of 786 clear-sky images of Landsat, we try to study the trend of lakes' area and shape in the TP and investigate the role human activities play. During the past 25 years, the area of lakes in the TP has experienced a rapid increase, and reservoirs and salt lakes also appeared to expand, but the shape and area of the lakes close to cities and roads have little change. In general, total 43 lakes affected by human activities increased 841.3 km2in the surface area, and all of them located in the northeast or southwest of the Tibetan Plateau.

Fractional vegetation cover (FVC) is widely relevant for land surface process. In this paper, an algorithm is addressed on FVC retrieval, with the combination of MODIS and Huan Jing satellite (HJ), which is a newly launched constellation by China. In the developed model, we considered angular effect and utilized spatial and temporal information to a great extent. MODIS and HJ surface reflectance products provide data supply for the algorithm and play cooperative roles. A vegetation growth model was introduced to constrain the uncertainty of HJ data in a temporal scale. The uncertainty of using this algorithm was assessed by error propagation theory and field experiments. Retrieved FVC became more reasonable after consideration of the correlation among time series observations and the introduction of more observational data. A priori information is necessary to constrain the inversion process.

Soil is an important parameter on water quality, and plays a key role in water quality evaluation, especially for inland water. Many remote-sensing methods have now been developed to reverse soil concentration. However, in natural water, the existence of chlorophyll-a affects the soil concentration reverse precision. In order to remove the effect of chlorophyll-a, an experiment is designed in this work to study the water spectra with different soil concentrations and one chlorophyll-a concentration. A reverse method is developed through analyzing shifts and changes of characteristic spectral positions. It is based on special spectral positions where the influence of algae is the least.

The domestic interior water body was monitored Based on an HJ-1 satellite multi-spectrum data. Chlorophyll a density is inverted from the empirical model based on the different area and different season. Suspension density inversion is based on the photobiology model of near-infrared waveband method. Based on chlorophyll a and the suspension density, the interior water body trophic level index is monitored using remote sensing data. There was a synchronized observation experiment in Lake Chaohu in June, 2009. The measurement data confirms the water quality parameter inversion algorithm. The results indicated that the chlorophyll a density inversion precision is inferior to the suspension density, but both inversion precision meets the water environmental monitoring service demand.

This paper described an approach used HJ-1 CCD data to monitor algal blooms in Lake Dianchi, China. After the radiometric calibration, atmospheric correction and geometric correction, HJ-1CCD reflectance data were obtained and NDVI threshold values were chosen to separate the bloom and nonbloom water. 148 HJ-1 CCD images were used in which 66 effective images were chosen to monitor algal blooms of Lake Dianchi. 39 times of algal blooms occurred in 2009 and only one time algal bloom area is greater than 15 square kilometers. The algal bloom annual frequency and bloom initial date were analyzed. The paper summarized that the bloom areas in Lake Dianchi are mainly located in northern lake and Caohai, the bloom began on March and ended on December, the most frequency bloom region is northern lake, and the most serious bloom month is September and October.

The Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) is a critical input parameter to many climate and ecological models. Its calculation accuracy from remote sensing images directly influences the estimation of net primary productivity (NPP) and carbon cycle. This paper presents a hybrid model combining the characteristics of geometric optic model and radiation transfer model. It considers the illuminated and shadow area of the canopy and soil, as well as the multiple scattering between the canopy and soil. The Monte Carlo simulations of canopy FAPAR are also conducted and the results are compared with model results. In addition, we did the simulation of FAPAR daily change by the model and MC method, and compare the results with field measured daily data of FAPAR. All the results prove the model effective.

The high spatial and high temporal satellite data is necessary in the operational agricultural applications of remote sensing. But till now the advantages of high spatial and high temporal resolution still can not be realized in single sensor. The PSP method (Patch Spectral Purification Method) is capable of retrieving field patch average information from high temporal but moderate spatial resolution satellite data, which meets the requirement of high spatial and high temporal resolution information in the real monitoring applications. In this paper a PSP-based methodology is proposed to retrieve the high spatial and high temporal resolution information for the growth and drought monitoring using multiple satellite data. An application demonstration was made in Xinjiang, China to monitor the cotton growth and drought with MODIS and Landsat/TM data. And the processing software-AgRsis (Agricultural Remote Sensing Inversion System) was realized to generate the daily crop parameters standard maps(e.g. NDVI, TVDI) for the crop growth and drought monitoring.

It is suitable for remote sensing monitoring and precision agricultural for Xinjiang cotton for its unique natural and ecological condition and growing and cultivating characteristic. However, precise monitoring is weak in Xinjiang cotton. We took the farm land of Xinjiang Production and Construction Corps as an example and made the cotton leaf area index (LAI) inversion. It is befitting to invert cotton LAI for Mini-satellite of Beijing-1' wide scope (600 kilometer), middle spatial resolution (32 meter) and high temporal resolution (2-3 days). The LAI is inverted for Beijing-1 mini-satellite data based on the physical canopy reflectance model and lookup-table inversion method. The LAI is also inverted for TM data considering scaling problems. It is feasible to invert LAI for Beijing-1 through the comparison between the inverted LAI and the LAI from the experiment.

Row planted crop is the transitional crop type with the discrete structure and continuous structure. There are different canopy structures for different growth stages. The canopy structure will transfer from row structure to continuous structure around the elongth growth stages. Furthermore, the elongth growth stage is key growth stages for the crop. For parameter inversion, it is significant to propose the key growth stages to simplify the model selection and to improve the parameters inversion accuracy. We put the object on one row period for the similar structure of the row planted crop. For each period, four components (sunlit vegetation and soil; viewed vegetation and soil) can be computed based on the bidirectional gap probability model, and structure parameters (W (row width), H (row height), S (row spacing), etc.) and view and solar zenith/azimuth angles. At the same time, the equivalent radiance for vegetation and soil from direct illuminated light and from the diffused and multi-scatted light will be computed. The key growth stages model (KGSM) is the sum of the four component radiance which is the product of each component area and the corresponding equivalent radiance. Through the validation based on the RGM and SAILH model, the canopy bidirectional reflectance can be simulated based the KGSM. The model validation is also done for experiment measurement.

More and more wide-view angle or multi-angular sensors provide the possibility to retrieve vegetation parameters. It is an important issue to access the accuracy and uncertainty of the products retrieved from different view angle observations. This paper presents an approach to evaluate the information content of the multi-angular remote sensing data. The proposed method is based on information theory. By using the entropy difference between all unknown parameters and non-target parameters for the remote sensing data, the information content is quantified. The presented methodology revealed the information content in the remote sensing data. The accuracy of the vegetation parameters retrieved from canopy reflectance depends mainly on the information about target parameter contained within observations. The relationship between information content and the LAI inversion accuracy is listed in this paper.

It is feasible to retrieve LAI over large area from remote sensing data with physical models;however,it is quite difficult to get accurate LAI and thus limit the remote sensing application without enough prior knowledge due to the underdetermined parameters in the physical inversion models.A spectrum database system of typical objects in China(SpecLib) has been set up recently,which may provide a priori knowledge of typical land cover for LAI inversion.MODIS data is used to retrieve LAI after atmosphere correction,geometrical correction and cloud identification.The SAIL(Scattering by Arbitrarily Inclined Layers) model is applied for the inversion of LAI for MODIS data.The vegetation coverage of the mixed pixels of the MODIS data are calculated based on the TM data sets.The LAIs of pure pixels(computed from the retrieved LAIs and vegetation coverage) are compared with the field measurement data in Luancheng,Heibei Province,China.Meanwhile,the LAIs of pure pixels are also compared with the MODIS LAI data products.The inversion results show that the!SpecLib effectively improved the accuracy of leaf area index inversion.

The Spectrum Knowledge Base System (SKBS) for Typical Object in China, built up by taking advantage of J2EE technology, is capable of providing the functionalities in spectrum analysis, query and comparison. More importantly, the spectrum scale effect, especially the scale extension, can be achieved in SKBS, which is based on the model-driven theory with the support of the prior knowledge.

The mineral environment of the DeXing Copper, in JiangXi Province in China, is monitored and analyzed by making use of the field spectral data and remote sensing images, TM data as well as ETM data, in different mineral developmental period. The location of the mine tailings is identified and its change in area and volume versus the time is calculated as well. A method to use DEM (Digital Elevation Model) for analyzing the change of the volume for the pollution source and its impact to the local environment is proposed in this paper. It provides the quantitative description for the mineral environmental pollution. This method can be used to monitor the open mineral environment, which has the same environmental problem like DeXing Copper Mine. It's beneficial for the local government to supervise the mineral environmental changes and be aware of the pollution status dynamically and lively.

Leaf area index (LAI) is an important parameter for describing vegetation canopy structure in the terrestrial ecosystem. LAI is closely related to plant transpiration, sunlight intercept, photosynthesis and Net Primary Productivity. Multiangular remote sensing is capable of providing more three-dimension information of vegetation, and it is powerful in solving the problem of the same object with different spectrum or vice versa. As a result, multiangular remote sensing and Bidirectional Reflectance Distribution Function (BRDF) model based inversion may be more suitable for Leaf Area index (LAI) retrieval over row crop canopies. However, it's still difficult to get LAI without enough a priori knowledge due to the underdetermined problems in inversion. We use the multispectral information to get the a priori estimation of LAI, and then perform BRDF model inversion. Different from the general one channel based BRDF model inversion methods, our new methods use the muiltiangular and multispectral data sets together to increase the available information in inversion, i.e., it is a synthetic method. From the inversion results we found that the new synthetic method is more effective in LAI inversion.

Many attempts have been made to retrieve soil surface parameters, such as soil moisture (SM), surface roughness parameters, by regressions or other statistical methods and some other techniques like neural networks (NNs) and genetic algorithms. The NN is proved to be an effective method for retrieval problems; much effort has been devoted to it. In this study, our goal is to estimate the bare surface soil moisture and surface roughness at Advanced Microwave Scanning Radiometer (AMSR/E) frequencies. First, a preliminary analysis was conducted based on a sensitivity analysis of surface parameters by simulating AMSR/E emissivity data of V, H polarizations, which were generated by the Integral Equation Model (IEM) for AMSR/E viewing angle of 55 degrees. We employed NNs to be first trained with part of the sensitive data determined by the above sensitivity analysis, then the trained NNs were used to retrieve the parameters that we need, especially soil moisture, from the simulated data. Analysis of the difference between the retrieved parameters and the simulated ones is presented. In addition, because the retrieval accuracy of NNs is supposed to be extremely sensitive to "noise" - the difference between the model and measurements, we introduced random noise to the simulated data. At the same time, we carried out a sensitive analysis of the input noise. We also selected the most sensitive frequencies, 6.9 and 10.7 GHz, to soil moisture in our retrieval scheme. This study demonstrates the great potential of NNs in estimating soil surface parameters from passive microwave remotely sensed data again.