The mapping of urban areas at regional to global scales is a crucial task due to its value for environmental monitoring, habitat and biodiversity conservation, and decision-making. In most current applications, two techniques (i.e., supervised classification and data fusion) are widely applied in large-scale urban mapping. However, the costly training sample collection, inadequate data-source descriptions, and diverse urban characteristics (e.g., shape, size, socioeconomic status, and physical environment) are challenging problems for the urban mapping approaches. In this context, aiming at effectively deriving accurate urban areas at a large scale, we propose a novel ensemble support vector machine (SVM) method which consists of three steps: 1) the automatic generation of training data to reduce labor costs; 2) the construction of an ensemble SVM model to effectively combine the multisource data (including remote sensing and socioeconomic data); and 3) an adaptive patch-based thresholding technique to tackle the diverse urban characteristics. The proposed method is employed to map urban areas of China in 2005 and 2010, and the resulting maps are compared with the existing urban maps for 287 prefecture-level cities. It is found that our results present a satisfactory superiority, especially in challenging small cities, with a significant improvement in median Kappa (0.174 for 2005 and 0.203 for 2010). When incorporating moderate-resolution imaging spectroradiometer multispectral data as an additional source, the Kappa coefficient can be further raised by 0.028 for 2010. In general, the proposed method shows great potential for accurately mapping urban areas at regional, continental, or even global scales in a cost-effective manner.

Land-cover mapping over urban areas using Landsat imagery has attracted considerable attention in recent years as it can promptly and accurately reflect the biophysical composition status of the urban landscape and allow further applications such as urban planning and risk management. However, due to the large diversity across different urban landscapes, adequate training sample collection for urban area mapping is both challenging and time-consuming. In this paper, we propose a novel unsupervised sample collection method for mapping urban areas using Landsat imagery. Specifically, the idea is to select reliable, representative, and diverse training samples from the images in a two-stage and iterative manner, based on a set of spectral indices (vegetation, impervious surface, soil, water). To validate the effectiveness and robustness of the proposed method, a synthetic data set was designed and a series of Landsat images over 39 representative cities from different biomes across the world was employed. The effectiveness of the proposed algorithm was quantitatively validated by assessing the quality of the automatically collected samples and the accuracy of the mapping results. In terms of the mapping performance, the proposed automatic approach can achieve a comparable mapping accuracy to supervised classification with manually collected samples. On the basis of the freely accessed Landsat data, the proposed approach demonstrates a promising potential for automatic large-scale (i.e., global) mapping over urban areas.

Accurate cloud detection is essential for subsequent optical remote sensing imagery processing. Although many deep learning-based cloud detection methods have been proposed, the accurate detection of thin clouds still remains a challenge. To solve this issue, this paper introduces a thin cloud aware network (TANet). TANet tackles the problem from the aspects of color, texture, spatial distribution, and feature, by constructing unique strategies to enhance the sensitivity of the network to thin cloud regions, thereby improving the overall accuracy of cloud detection. On the one hand, the TANet utilizes a color prior guidance module (CPGM) to incorporate robust dehaze priors, guiding the network to pay more attention to thin cloud areas. On the other hand, the global information aggregation module (GIAM) is employed to deeply extract long distance dependence between pixels, mining potential correlations between thin and thick clouds, addressing the challenge of recognizing thin clouds in a local perspective. Additionally, we construct a plug-and-play cloud feature difference (CFD) loss, encouraging the network to learn more distinctive features between pixels of thin clouds and cloud-free regions, thereby strengthening the network’s ability to distinguish highly similar samples of different classes. The experimental results substantiate that our proposed method attains the lowest omission error and the highest detection accuracy. This affirms the superior capability of TANet in thin cloud detection, thereby yielding more dependable cloud detection results.