Remote sensing images are primary data sources for land use classification. High spatial resolution images enable more accurate analysis and identification of land cover types. However, a higher spatial resolution also brings new challenges to the existing classification methods. In the low-level feature spaces of remote sensing images, it is difficult to improve classification performance by modifying classifiers. Probabilistic topic models can connect low-level features and high-level semantics of remote sensing images. Latent Dirichlet allocation (LDA) models are representatives of probabilistic topic models. However, at present, probabilistic topic models are mainly adopted for scene classification and image retrieval in remote sensing image analysis only. In this study, multiscale segmentation was employed to construct bag-of-words (BoW) representations of high-resolution images. The segmented patches were then utilized as “image documents.” A structural topic model was used with an LDA model to import spatial information from the image documents at two levels: topical prevalence and topical content in the form of covariates. In this way, latent topic features in image documents can be more accurately deduced. The proposed method showed more satisfactory classification performance than standard LDA models and demonstrated a certain degree of robustness against the changes in the segmentation scale.

Towards fully exploring multidisciplinary research topics under global warming, the spatiotemporal discontinuities of land surface temperature (LST) products due to cloud contamination still challenge such research topics. Data fusion that seeks the best compromise between multiple data sources plays a key role in providing gapless LST data. However, most models only use information about the variation of LST at different times or the difference between different LST products without effectively combining the two pieces of information. With the rapid development of deep learning methods, powerful modeling capabilities can solve this problem. This article proposes a novel multi-information fusion network (MIFN) based on convolutional neural networks (CNNs) and attention mechanisms to map gapless all-sky LST, taking temporal-changing (TC) and data-differentiated (DD) information into consideration. Temporal normalization is used as a pre-processing step to match the time of Moderate Resolution Imaging Spectroradiometer (MODIS) and European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis fifth Generation (ERA5) LSTs. The MIFN extracts multiscale multi-temporal TC and DD features by network constraints. Then, the weights of the target LST features reconstructed by TC and DD features are assigned through an attention mechanism to fuse them reasonably. Finally, we design a loss function that combines TC, DD, and LST reconstruction to improve the accuracy of LST prediction further. We performed comprehensive data experiments to validate the performance of the new method. Our technique is more advantageous in generating MODIS-like LSTs than four state-of-the-art methods and two CNN models using a single piece of information.

The spatial allocation rationality of the service facilities of residential areas, which is affected by the scope of the population and the capacity of service facilities, is meaningful for harmonious urban development. The growth of the internet, especially Internet map and location-based service (LBS) data, provides micro-scale knowledge about residential areas. The purpose is to characterize the spatial allocation rationality of the service facilities of residential areas from Internet map and LBS data. An Internet map provides exact geographical data (e.g., points of interests (POI)) and stronger route planning analysis capability through an application programming interface (API) (e.g., route planning API). Meanwhile, LBS data collected from mobile equipment afford detailed population distribution values. Firstly, we defined the category system of service facilities and calculated the available service facilities capacity of residential areas (ASFC-RA) through a scrappy algorithm integrated with the modified cumulative opportunity measure model. Secondly, we used Thiessen polygon spatial subdivision to gain the population distribution capacity of residential areas (PDC-RA) from Tencent LBS data at the representative moment. Thirdly, we measured the spatial allocation rationality of service facilities of residential areas (SARSF-RA) by combining ASFC-RA and PDC-RA. In this case, a trial strip census, consisting of serval urban residential areas from Wuxi City, Jiangsu Province, is selected as research area. Residential areas have been grouped within several ranges according to their SARSF-RA values. Different residential areas belong to different groups, even if they are spatially contiguous. Spatial locations and other investigation information coordinate with these differences. Those results show that the method that we proposed can express the micro-spatial allocation rationality of different residential areas dramatically, which provide a new data lens for various researchers and applications, such as urban residential areas planning and service facilities allocation.

Effectively monitoring the size of a city in real time enables the scientific planning of urban development. Models that utilize the distribution and variations in city size generally use population data as inputs, which cannot be obtained in a timely and rapid manner. However, night-time light (NTL) remote sensing may be an alternative method. A case study was carried out on the Yangtze River Delta (YRD) in China, and the rank–size rule, the law of primate cities, and the Gini coefficient were employed to monitor the variation in city size in the study area. The urban areas extracted based on NTL remote sensing were utilized instead of the traditionally used population data to evaluate the variations in city size from 2012 to 2017. Considering the empiricism and subjectivity of the thresholding method, urban areas were extracted from NTL data combined with the normalized differential vegetation index and land-surface temperature data based on the artificial neural network algorithm. Based on the results, the YRD did not fit the distribution of the primate cities from 2012 to 2017. However, this region satisfied the rank–size rule well, which indicated that the development of medium–small cities was more prominent than that of larger cities, and the dispersed force was larger than the concentrated force. Notably, the city size reached a relatively balanced level in the study area. Further, sensitivity analysis revealed that the relatively low extraction accuracy of urban areas of few small cities had little effect on the results of city size variations. Moreover, the validation of city size computed from statistical population data and its comparison with results calculated based on the statistical data of urban areas aligned with the results of this study, which indicates the rationality and applicability of monitoring the variations in city size using the urban areas extracted from NTL remote sensing instead of population data.

The marine gravity field recovery close to land/island is challenging owing to the scarcity of measured gravimetric observations and sorely contaminated satellite radar altimeter-derived data. The satellite missions that carried the synthetic aperture radar (SAR) altimeters supplied data with improved quality compared to that retrieved from the conventional radar altimeters. In this study, we combine the satellite altimeter-derived gravity data for marine gravity field augmentation over island areas; in particular, the feasibility for regional augmentation by incorporating the SAR altimeter-derived gravity data is investigated. The gravity field modeling results over the Spratly Islands demonstrate that the marine gravity field is augmented by the incorporation of newly published satellite altimeter-derived gravity data. By merging the gravity models computed with the Sentinel-3A/B SAR altimetry data, the quasi-geoid and mean dynamic topography are dramatically improved, by a magnitude larger than 4 cm around areas close to islands, in comparison with the results directly derived from a combined global geopotential model alone. Further comparison of regional solutions computed from heterogeneous gravity models shows that the ones modeled from the SAR-based gravity models have better performances, the errors of which are reduced by a magnitude of 2~4 cm over the regions close to islands, in comparison with the solutions modeled with the gravity models developed without SAR altimetry data. These results highlight the superiority of using the SAR-based gravity data in marine gravity field recovery, especially over the regions close to land/island.