Detecting changes using bitemporal remote sensing imagery is vital to understand the dynamics of the land surface. Existing change detection models based on deep learning suffer from the problem of scale variation and pseudochange due to their insufficient multilevel aggregation and inadequate capability of feature representation, which limits the accuracy. This study proposes a densely attentive refinement network (DARNet) to improve change detection on bitemporal very-high-resolution remote sensing images. DARNet is based on the U-shape encoder–decoder architecture with the Siamese network as a feature extractor. The dense skip connection module (DSCM) is employed between the decoder and the encoder to aggregate multilevel feature maps. The hybrid attention module (HAM) is integrated to exploit contextual information and generate discriminative features. The recurrent refinement module (RRM) is exploited to progressively refine the predicted change maps during the decoding process. Experiments on testing the model performance were conducted on three benchmark datasets: the season-varying change detection (SVCD) dataset, the Sun Yat-sen University change detection (SYSU-CD) dataset, and the Learning Vision and Remote Sensing Laboratory building change detection (LEVIR-CD) dataset. The experimental results demonstrate that DARNet outperforms state-of-the-art models with kappa of 96.58%, 75.35%, and 90.69% for the SVCD, SYSU-CD, and LEVIR-CD datasets, respectively.
Vegetation phenology plays a key role in influencing ecosystem processes and biosphere-atmosphere feedbacks. Digital cameras such as PhenoCam that monitor vegetation canopies in near real-time provide continuous images that record phenological and environmental changes. There is a need to develop methods for automated and effective detection of vegetation dynamics from PhenoCam images. Here we developed a method to predict leaf phenology of deciduous broadleaf forests from individual PhenoCam images using deep learning approaches. We tested four convolutional neural network regression (CNNR) networks on their ability to predict vegetation growing dates based on PhenoCam images at 56 sites in North America. In the one-site experiment, the predicted phenology dated to after the leaf-out events agree well with the observed data, with a coefficient of determination (R2) of nearly 0.999, a root mean square error (RMSE) of up to 3.7 days, and a mean absolute error (MAE) of up to 2.1 days. The method developed achieved lower accuracies in the all-site experiment than in the one-site experiment, and the achieved R2 was 0.843, RMSE was 25.2 days, and MAE was 9.3 days in the all-site experiment. The model accuracy increased when the deep networks used the region of interest images rather than the entire images as inputs. Compared to the existing methods that rely on time series of PhenoCam images for studying leaf phenology, we found that the deep learning method is a feasible solution to identify leaf phenology of deciduous broadleaf forests from individual PhenoCam images.
Accurate building footprint polygons provide essential data for a wide range of urban applications. While deep learning models have been proposed to extract pixel-based building areas from remote sensing imagery, the direct vectorization of pixel-based building maps often leads to building footprint polygons with irregular shapes that are inconsistent with real building boundaries, making it difficult to use them in geospatial analysis. In this study, we proposed a novel deep learning-based framework for automated extraction of building footprint polygons (DLEBFP) from very high-resolution aerial imagery by combining deep learning models for different tasks. Our approach uses the U-Net, Cascade R-CNN, and Cascade CNN deep learning models to obtain building segmentation maps, building bounding boxes, and building corners, respectively, from very high-resolution remote sensing images. We used Delaunay triangulation to construct building footprint polygons based on the detected building corners with the constraints of building bounding boxes and building segmentation maps. Experiments on the Wuhan University building dataset and ISPRS Vaihingen dataset indicate that DLEBFP can perform well in extracting high-quality building footprint polygons. Compared with the other semantic segmentation models and the vector map generalization method, DLEBFP is able to achieve comparable mapping accuracies with semantic segmentation models on a pixel basis and generate building footprint polygons with concise edges and vertices with regular shapes that are close to the reference data. The promising performance indicates that our method has the potential to extract accurate building footprint polygons from remote sensing images for applications in geospatial analysis.
1 January 2021 in Aerosol and Air Quality Research
The vertical thermal and dynamic structures in synoptic and local scale that contribute to the haze formation are investigated in three-dimensional view. In synoptic scale, heavy haze corresponds to significant horizontal transport by southerly winds or strong vertical stability with descending motion in the layer below ~1500–3000 m. Average meteorological elements below ~1500 m are better indicators of pollutant transport and dispersion than on-surface measurements. The dynamic changes are characterized by ascending motion accompanied by enhanced southerly winds from the surface to above ~1500 m, can transport pollutants from surrounding areas to Beijing, resulting in a rapid increase of PM2.5 within a few or several hours, even when the surface wind remains weak. This explained the debatable question on regional transport under surface stagnant condition and partially approved the important role of regional transport in haze formation. In addition, local mountain–plain breeze circulation is prominent during stable stage of haze episodes. The plain wind in daytime pushes the pollutants to areas along the mountains and then to Beijing, resulting in a day-by-day increase of pollutants. This is different from observation in winter haze events that local pollution accumulation is the main cause for haze worsening in stable meteorological conditions. The coupling effect of easterly winds and local topography can cause special dissipation and formation processes of haze. The orographic effect can uplift haze to higher layers, where PM2.5 is transported to the southeast. Then the polluted plume aloft is carried back to Beijing along the mountain front with southerly winds, merges with surface pollutants by vertical mixing, and finally enhances the next haze episode.