Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries.

Impervious surface area (ISA) has been recognized as a significant indicator for evaluating levels of urbanization and the quality of urban ecological environments. ISA extraction methods based on supervised classification usually rely on a large number of manually labeled samples, the production of which is a time-consuming and labor-intensive task. Furthermore, in arid areas, man-made objects are easily confused with bare land due to similar spectral responses. To tackle these issues, a self-trained deep-forest (STDF)-based ISA extraction method is proposed which exploits the complementary information contained in multispectral and polarimetric synthetic aperture radar (PolSAR) images using limited numbers of samples. In detail, this method consists of three major steps. First, multi-features, including spectral, spatial and polarimetric features, are extracted from Sentinel-2 multispectral and Chinese GaoFen-3 (GF-3) PolSAR images; secondly, a deep forest (DF) model is trained in a self-training manner using a limited number of samples for ISA extraction; finally, ISAs (in this case, in three major cities located in Central Asia) are extracted and comparatively evaluated. The experimental results from the study areas of Bishkek, Tashkent and Nursultan demonstrate the effectiveness of the proposed method, with an overall accuracy (OA) above 95% and a Kappa coefficient above 0.90.

Habitat selection and prediction of the spatial distribution of the Chinese horseshoe bat (R. sinicus) in the Wuling Mountains.

Habitat selection by the Chinese horseshoe bat (Rhinolophus sinicus) in the Wuling Mountains was studied in this paper. Global positioning system (GPS), remote sensing (RS) and geographic information system (GIS) technologies were used to obtain ground survey data and analyse the habitat factors driving the distribution of R. sinicus. Based on these basic data, a binary logistic regression method was used to establish habitat selection models of R. sinicus. Then, the corrected Akaike information criterion (AICC) was used to screen an optimal model, and the Hosmer-Lemeshow test indicated that the optimal model has suitable goodness of fit. Finally, the optimal model was used to predict the spatial distribution of R. sinicus in the Wuling Mountains. Verification analysis showed that the overall accuracy of the model was 72.7% and that the area under the curve (AUC) value was 0.947, which indicated that the model was effective for predicting suitable habitat for R. sinicus. The model results also showed that the main factors that influenced habitat selection were slope, annual mean temperature and distances from roads, rivers and residential land. R. sinicus preferred areas far from roads and residential land and areas near rivers. Generally, higher values of slope and annual mean temperature were associated with a greater likelihood of R. sinicus presence. Therefore, the protection of the water bodies surrounding R. sinicus habitats and fully addressing the impacts of human activities on R. sinicus habitats are recommended to protect the survival and reproduction of the population.

Ensemble of ERDTs for Spectral-Spatial Classification of Hyperspectral Images Using MRS Object-Guided Morphological Profiles.

In spectral-spatial classification of hyperspectral image tasks, the performance of conventional morphological profiles (MPs) that use a sequence of structural elements (SEs) with predefined sizes and shapes could be limited by mismatching all the sizes and shapes of real-world objects in an image. To overcome such limitation, this paper proposes the use of object-guided morphological profiles (OMPs) by adopting multiresolution segmentation (MRS)-based objects as SEs for morphological closing and opening by geodesic reconstruction. Additionally, the ExtraTrees, bagging, adaptive boosting (AdaBoost), and MultiBoost ensemble versions of the extremely randomized decision trees (ERDTs) are introduced and comparatively investigated for spectral-spatial classification of hyperspectral images. Two hyperspectral benchmark images are used to validate the proposed approaches in terms of classification accuracy. The experimental results confirm the effectiveness of the proposed spatial feature extractors and ensemble classifiers.