Urban areas feature complex and heterogeneous land covers which create challenging issues for tree species classification. The increased availability of high spatial resolution multispectral satellite imagery and LiDAR datasets combined with the recent evolution of deep learning within remote sensing for object detection and scene classification, provide promising opportunities to map individual tree species with greater accuracy and resolution. However, there are knowledge gaps that are related to the contribution of Worldview-3 SWIR bands, very high resolution PAN band and LiDAR data in detailed tree species mapping. Additionally, contemporary deep learning methods are hampered by lack of training samples and difficulties of preparing training data. The objective of this study was to examine the potential of a novel deep learning method, Dense Convolutional Network (DenseNet), to identify dominant individual tree species in a complex urban environment within a fused image of WorldView-2 VNIR, Worldview-3 SWIR and LiDAR datasets. DenseNet results were compared against two popular machine classifiers in remote sensing image analysis, Random Forest (RF) and Support Vector Machine (SVM). Our results demonstrated that: (1) utilizing a data fusion approach beginning with VNIR and adding SWIR, LiDAR, and panchromatic (PAN) bands increased the overall accuracy of the DenseNet classifier from 75.9% to 76.8%, 81.1% and 82.6%, respectively. (2) DenseNet significantly outperformed RF and SVM for the classification of eight dominant tree species with an overall accuracy of 82.6%, compared to 51.8% and 52% for SVM and RF classifiers, respectively. (3) DenseNet maintained superior performance over RF and SVM classifiers under restricted training sample quantities which is a major limiting factor for deep learning techniques. Overall, the study reveals that DenseNet is more effective for urban tree species classification as it outperforms the popular RF and SVM techniques when working with highly complex image scenes regardless of training sample size. Full article

Land cover change detection based on remote sensing has become increasingly important for protecting the ecological environment. Spatial features of images can be extracted by object-level methods. However, the computational complexity is high when using many features to detect land cover change. Meanwhile, single-constrained change detection (SCCD) methods produce non-objective and inaccurate results. Therefore, we proposed a land cover change detection method: the object-level double constrained change detection (ODCD) method. First, spectral and spatial features were calculated based on multi-scale segmentation results. Second, using the significant difference test (SDT), feature differences among all categories were calculated, and the features with more significant differences were considered as the optimal features. Third, the maximum Kappa coefficient was used as the criterion for determining the optimal change intensity and correlation coefficient. Finally, the ODCD was validated using GF-1 satellite images on March 2016 and February 2017 in north Beiqijia Town, Beijing. Using optimal feature selection, the dimension of features was reduced from 26 to 12. Compared with SCCD methods, the result of the ODCD was more reliable and accurate. Its overall accuracy was 10% higher, overall error was 27% lower, and the Kappa coefficient was 0.22 higher. In conclusion, the ODCD is effective for land cover change detection and can improve computational efficiency. Full article

There is limited research in land surface temperatures (LST) simulation using image fusion techniques, especially studies addressing the downscaling effect of LST image fusion. LST simulation and associated downscaling effect can potentially benefit the thermal studies requiring both high spatial and temporal resolutions. This study simulated LSTs based on observed Terra Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Terra Moderate Resolution Imaging Spectroradiometer (MODIS) LST imagery with Spatial and Temporal Adaptive Reflectance Fusion Model, and investigated the downscaling effect of LST image fusion at 15, 30, 60, 90, 120, 250, 500, and 1000 m spatial resolutions. The study area partially covered the City of Los Angeles, California, USA, and surrounding areas. The reference images (observed ASTER and MODIS LST imagery) were acquired on 04/03/2007 and 07/01/2007, with simulated LSTs produced for 4/28/2007. Three image resampling methods (Cubic Convolution, Bilinear Interpolation, and Nearest Neighbor) were used during the downscaling and upscaling processes, and the resulting LST simulations were compared. Results indicated that the observed ASTER LST and simulated ASTER LST images (date 04/28/2007, spatial resolution 90 m) had high agreement in terms of spatial variations and basic statistics based on a comparison between the observed and simulated ASTER LST maps. Urban developed lands possessed higher LSTs with lighter tones and mountainous areas showed dark tones with lower LSTs. The Cubic Convolution and Bilinear Interpolation resampling methods yielded better results over Nearest Neighbor resampling method across the scales from 15 to 1000 m. The simulated LSTs with image fusion can be used as valuable inputs in heat related studies that require frequent LST measurements with fine spatial resolutions, e.g., seasonal movements of urban heat islands, monthly energy budget assessment, and temperature-driven epidemiology. The observation of scale-independency of the proposed image fusion method can facilitate with image selections of LST studies at various locations. Full article

Urban land cover and land use mapping plays an important role in urban planning and management. In this paper, novel multi-scale deep learning models, namely ASPP-Unet and ResASPP-Unet are proposed for urban land cover classification based on very high resolution (VHR) satellite imagery. The proposed ASPP-Unet model consists of a contracting path which extracts the high-level features, and an expansive path, which up-samples the features to create a high-resolution output. The atrous spatial pyramid pooling (ASPP) technique is utilized in the bottom layer in order to incorporate multi-scale deep features into a discriminative feature. The ResASPP-Unet model further improves the architecture by replacing each layer with residual unit. The models were trained and tested based on WorldView-2 (WV2) and WorldView-3 (WV3) imageries over the city of Beijing. Model parameters including layer depth and the number of initial feature maps (IFMs) as well as the input image bands were evaluated in terms of their impact on the model performances. It is shown that the ResASPP-Unet model with 11 layers and 64 IFMs based on 8-band WV2 imagery produced the highest classification accuracy (87.1% for WV2 imagery and 84.0% for WV3 imagery). The ASPP-Unet model with the same parameter setting produced slightly lower accuracy, with overall accuracy of 85.2% for WV2 imagery and 83.2% for WV3 imagery. Overall, the proposed models outperformed the state-of-the-art models, e.g., U-Net, convolutional neural network (CNN) and Support Vector Machine (SVM) model over both WV2 and WV3 images, and yielded robust and efficient urban land cover classification results. Full article

Land degradation is a widespread environmental issue and an important factor in limiting sustainability. In this study, we aimed to improve the accuracy of monitoring human-induced land degradation by using phenological signal detection and residual trend analysis (RESTREND). We proposed an improved model for assessing land degradation named phenology-based RESTREND (P-RESTREND). This method quantifies the influence of precipitation on normalized difference vegetation index (NDVI) variation by using the bivariate linear regression between NDVI and precipitation in pre-growing season and growing season. The performances of RESTREND and P-RESTREND for discriminating land degradation caused by climate and human activities were compared based on vegetation-precipitation relationship. The test area is in Western Songnen Plain, Northeast China. It is a typical region with a large area of degraded drylands. The MODIS 8-day composite reflectance product and daily precipitation data during 2000–2015 were used. Our results showed that P-RESTREND was more effective in distinguishing different drivers of land degradation than the RESTREND. Degraded areas in the Songnen grasslands can be effectively detected by P-RESTREND. Therefore, this modified model can be regarded as a practical method for assessing human-induced land degradation. Full article

In this paper, we propose a new method of land use and land cover classification for polarimetric SAR data. This algorithm consists of three parts. First, the multiple-component model-based scattering decomposition technique is improved and the decomposed scattering powers can be used to support the classification of PolSAR data. With this decomposition, the volume scattering of vegetated areas is enhanced while their double-bounce scattering is reduced. Furthermore, the double-bounce scattering of urban areas is enhanced and their volume scattering is decreased, which leads to an improvement in the classification accuracy especially for the urban areas. Second, this classification strategy is carried out on the superpixel level, which can decrease the influence of speckle noise and speed up the classification. Moreover, the contexture and spatial features extracted from these superpixels are utilized to improve classification accuracy. Lastly, we introduce the supervised locally linear embedding approach to map the high dimensional features into the low dimensional features as the inputs of classifiers. The classification is completed using the nearest neighbor classifier. The effectiveness of our proposed method is demonstrated using the AIRSAR C-band PolSAR data set, which is compared with the original MCSM-SVM and newly published LE-IF PolSAR classification methods. Further investigation is also carried out on the individual contribution of the three parts to LULC classification using AIRSAR C-band data. It indicates that all three components have important contributions to the final classification result. Full article

The huge quantity of information and the high spectral resolution of hyperspectral imagery present a challenge when performing traditional processing techniques such as classification. Dimensionality and noise reduction improves both efficiency and accuracy, while retaining essential information. Among the many dimensionality reduction methods, Independent Component Analysis (ICA) is one of the most popular techniques. However, ICA is computationally costly, and given the absence of specific criteria for component selection, constrains its application in high-dimension data analysis. To overcome this limitation, we propose a novel approach that applies Discrete Cosine Transform (DCT) as preprocessing for ICA. Our method exploits the unique capacity of DCT to pack signal energy in few low-frequency coefficients, thus reducing noise and computation time. Subsequently, ICA is applied on this reduced data to make the output components as independent as possible for subsequent hyperspectral classification. To evaluate this novel approach, the reduced data using (1) ICA without preprocessing; (2) ICA with the commonly used preprocessing techniques which is Principal Component Analysis (PCA); and (3) ICA with DCT preprocessing are tested with Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) classifiers on two real hyperspectral datasets. Experimental results in both instances indicate that data after our proposed DCT preprocessing method combined with ICA yields superior hyperspectral classification accuracy. Full article

Landslides that take place in mountain cities tend to cause huge casualties and economic losses, and a precise survey of landslide areas is a critical task for disaster emergency. However, because of the complicated appearance of the nature, it is difficult to find a spatial regularity that only relates to landslides, thus landslides detection based on only spatial information or artificial features usually performs poorly. In this paper, an automated landslides detection approach that is aiming at mountain cities has been proposed based on pre- and post-event remote sensing images, it mainly utilizes the knowledge of landslide-related surface covering changes, and makes full use of the temporal and spatial information. A change detection method using Deep Convolution Neural Network (DCNN) was introduced to extract the areas where drastic alterations have taken place; then, focusing on the changed areas, the Spatial Temporal Context Learning (STCL) was conducted to identify the landslides areas; finally, we use slope degree which is derived from digital elevation model (DEM) to make the result more reliable, and the change of DEM is used for making the detected areas more complete. The approach was applied to detecting the landslides in Shenzhen, Zhouqu County and Beichuan County in China, and a quantitative accuracy assessment has been taken. The assessment indicates that this approach can guarantee less commission error of landslide areal extent which is below 17.6% and achieves a quality percentage above 61.1%, and for landslide areas, the detection percentage is also competitive, the experimental results proves the feasibility and accuracy of the proposed approach for the detection landslides in mountain cities. Full article