The urban heat island (UHI) refers to the phenomenon of higher atmospheric 21 and surface temperatures occurring in urban areas than in the surrounding rural areas. Mitigation 22 of the UHI effects via the configuration of green spaces and sustainable design of urban 23 *Manuscript Click here to download Manuscript: ISPRS_Manuscript_final_R1_2013_12_20_final.docx Click here to view linked References 2 environments has become an issue of increasing concern under changing climate. In this paper, 24 the effects of the composition and configuration of green space on land surface temperatures 25 (LST) were explored using landscape metrics including percentage of landscape (PLAND), edge 26 density (ED) and patch density (PD). An oasis city of Aksu in Northwestern China was used as a 27 case study. The metrics were calculated by moving window method based on a green space map 28 derived from Landsat Thematic Mapper (TM) imagery, and LST data were retrieved from 29 Landsat TM thermal band. Normalized mutual information measure was employed to investigate 30 the relationship between LST and the spatial pattern of green space. The results showed that 31 while the PLAND is the most important variable that elicits LST dynamics, spatial configuration 32 of green space also has significant effect on LST. Though, the highest normalized mutual 33 information measure was with the PLAND (0.71), it was found that ED and PD combination is 34 the most deterministic factors of LST than the unique effects of a single variable or the joint 35 effects of PLAND and PD or PLAND and ED. Normalized mutual information measure 36 estimations between LST and PLAND and ED, PLAND and PD and ED and PD were 0.7679, 37 0.7650 and 0.7832, respectively. A combination of the three factors PLAND, PD and ED 38 explained much of the variance of LST with a normalized mutual information measure of 39 0.8694. Results from this study can expand our understanding of the relationship between LST 40 and street trees and vegetation, and provide insights for sustainable urban planning and 41 management under changing climate. 42 43 44 Keywords-urban heat island, urban green space, landscape metrics, configuration, normalized 45 mutual information measure. 46 Remarkable proliferations of studies focusing on the relationship between LST and green space 79 composition has been reported over the last two decades (

Exploring changes in land use land cover (LULC) to understand the urban heat island (UHI) effect is valuable for both communities and local governments in cities in developing countries, where urbanization and industrialization often take place rapidly but where coherent planning and control policies have not been applied. This work aims at determining and analyzing the relationship between LULC change and land surface temperature (LST) patterns in the context of urbanization. We first explore the relationship between LST and vegetation, man-made features, and cropland using normalized vegetation, and built-up indices within each LULC type. Afterwards, we assess the impacts of LULC change and urbanization in UHI using hot spot analysis (Getis-Ord Gi* statistics) and urban landscape analysis. Finally, we propose a model applying non-parametric regression to estimate future urban climate patterns using predicted land cover and land use change. Results from this work provide an effective methodology for UHI characterization, showing that (a) LST depends on a nonlinear way of LULC types; (b) hotspot analysis using Getis Ord Gi* statistics allows to analyze the LST pattern change through time; (c) UHI is influenced by both urban landscape and urban development type; (d) LST pattern forecast and UHI effect examination can be done by the proposed model using nonlinear regression and simulated LULC change scenarios. We chose an inner city area of Hanoi as a case-study, a small and flat plain area where LULC change is significant due to urbanization and industrialization. The methodology presented in this paper can be broadly applied in other cities which exhibit a similar dynamic growth. Our findings can represent an useful tool for policy makers and the community awareness by providing a scientific basis for sustainable urban planning and management.

Convolutional neural networks (CNNs) exhibit good performance in image processing tasks, pointing themselves as the current state-of-the-art of deep learning methods. However, the intrinsic complexity of remotely sensed hyperspectral images (HSIs) still limits the perfor-This work has been supported by Ministerio de Educación (Res

Convolutional neural networks (CNNs) have recently exhibited excellent performance in hyperspectral image (HSI) classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when effectively exploiting the relationships between HSI features in the spectral-spatial domain, which is a key factor to deal with the high level of complexity present in remotely sensed HSI data. Despite the fact that deeper architectures try to mitigate these limitations, they also find challenges with the convergence of the network parameters, which eventually limit the classification performance under highly demanding scenarios. In this paper, we propose a new CNN architecture based on spectral-spatial capsule networks in order to achieve highly accurate classification of HSIs while significantly reducing the network design complexity. Specifically, based on Hinton's capsule networks, we develop a CNN model extension which re-defines the concept of capsule units to become spectral-spatial units specialized in classifying remotely sensed HSI data. The proposed model is composed by several building blocks, called spectral-spatial capsules, which are able to learn HSI spectral-spatial features considering their corresponding spatial positions in the scene, their associated spectral

No abstract

Super-resolution (SR) brings an excellent opportunity to improve a wide range of different remote sensing applications. SR techniques are concerned about increasing the image resolution while providing finer spatial details than those captured by the original acquisition This paper has been supported by Ministerio de Educación (Res

No abstract

Image acquisition technology is improving very fast from a performance point of view. However, there are physical restrictions that can only be solved using software processing strategies. This is particularly true in the case of super resolution methodologies. Super-resolution techniques have found a fertile application field in airborne and space optical acquisition platforms. Single-frame super resolution methods may be advantageous for some remote sensing platforms and acquisition time conditions. The contributions of this paper are basically two: (1) to present an overview of single-frame super resolution methods, making a comparative analysis of their performance in different and challenging remote sensing scenarios, and (2) to propose a new single-frame super-resolution taxonomy, and a common validation strategy. Finally, we should emphasize that, on the one hand, this is the first time, to the best of our knowledge, that such a review and analysis of single super resolution methods is made in the framework of remote sensing, and, on the other hand, that the new single-frame super-resolution taxonomy is aimed at shedding some light when classifying some types of single-frame super-resolution methods.