Explore the vast range of titles available.

Obtaining high-spatial–high-temporal (HTHS) resolution remote sensing images from a single sensor remains a great challenge due to the cost and technical limitations. Spatiotemporal fusion (STF) technology breaks through the technical limitations of existing sensors and provides a convenient and economical solution for obtaining HTHS resolution images. At present, most STF methods use stacked convolutional layers to extract image features and then obtain fusion images by using a summation strategy. However, these convolution operations may lead to the loss of feature information, and the summation strategy results in poorly fused images due to a lack of consideration of global spatial feature information. To address these issues, this article proposes a STF network architecture based on multiscale and attention mechanisms (MANet). The multiscale mechanism module composed of dilated convolutions is used to extract the detailed features of low-spatial resolution remote sensing images at multiple scales. The channel attention mechanism adaptively adjusts the weights of the feature map channels to retain more temporal and spatial information in the upsampling process, while the non-local attention mechanism adjusts the initial fusion images to obtain more accurate predicted images by calculating the correlation between pixels. We use two datasets with different characteristics to conduct the experiments, and the results prove that the proposed MANet method with fewer parameters obtains better fusion results than the existing machine learning-based and deep learning-based fusion methods.

Extracting buildings from high-resolution remote sensing images is essential for many geospatial applications, such as building change detection, urban planning, and disaster emergency assessment. Due to the diversity of geometric shapes and the blurring of boundaries among buildings, it is still a challenging task to accurately generate building footprints from the complex scenes of remote sensing images. The rapid development of convolutional neural networks is presenting both new opportunities and challenges with respect to the extraction of buildings from high-resolution remote sensing images. To capture multilevel contextual information, most deep learning methods extract buildings by integrating multilevel features. However, the differential responses between such multilevel features are often ignored, leading to blurred contours in the extraction results. In this study, we propose an end-to-end multitask building extraction method to address these issues; this approach utilizes the rich contextual features of remote sensing images to assist with building segmentation while ensuring that the shape of the extraction results is preserved. By combining boundary classification and boundary distance regression, clear contour and distance transformation maps are generated to further improve the accuracy of building extraction. Subsequently, multiple refinement modules are used to refine each part of the network to minimize the loss of image feature information. Experimental comparisons conducted on the SpaceNet and Massachusetts building datasets show that the proposed method outperforms other deep learning methods in terms of building extraction results.

Fine particulate matter (PM2.5) threatens human health and the natural environment. Estimating the near-ground PM2.5 concentrations accurately is of great significance in air quality research. Statistical and deep-learning models are widely used for estimating PM2.5 concentration based on remotely sensed aerosol optical depth (AOD) products. Deep-learning models can effectively express the nonlinear relationship between AOD, parameters, and PM2.5. This study proposed a capsule network model (CapsNet) to address the spatial differences in PM2.5 concentration distribution by introducing a capsule structure and dynamic routing algorithm for the first time, which integrates AOD, surface PM2.5 measurements, and auxiliary variables (e.g., normalized difference vegetation index (NDVI) and meteorological parameters). Moreover, we examined the longitude and latitude of pixels as input parameters to reflect spatial location information, and the results showed that the introduction of longitude (LON) and latitude (LAT) parameters improved the model fitting accuracy. The coefficient of determination (R2) increased by 0.05 ± 0.01, and the root mean square error (RMSE), mean relative error (MRE), and mean absolute error (MAE) decreased by 3.30 ± 1.0 μg/m3, 8 ± 3%, and 1.40 ± 0.2 μg/m3, respectively. To verify the accuracy of our proposed CapsNet, the deep neural network (DNN) model was executed. The results indicated that the R2 values of the validation dataset using CapsNet improved by 4 ± 2%, and RMSE, MRE, and MAE decreased by 1.50 ± 0.4 μg/m3, ~5%, and 0.60 ± 0.2 μg/m3, respectively. Finally, the effects of seasons and spatial region on the fitting accuracy were examined separately from 2018 to 2020. With respect to seasons, the model performed more robustly in the cold season. In terms of spatial region, the R2 values exceeded 0.9 in the central-eastern region, while the accuracy was lower in the western and coastal regions. This study proposed the CapsNet model to estimate PM2.5 concentrations for the first time and achieved good accuracy, which could be used for the estimation of other air contaminants.

Fine particulate matter (PM2.5) has attracted extensive attention due to its harmful effects on humans and the environment. The sparse ground-based air monitoring stations limit their application for scientific research, while aerosol optical depth (AOD) by remote sensing satellite technology retrieval can reflect air quality on a large scale and thus compensate for the shortcomings of ground-based measurements. In this study, the elaborate vertical-humidity method was used to estimate PM2.5 with the spatial resolution 1 km and the temporal resolution 1 hour. For vertical correction, the scale height of aerosols (Ha) was introduced based on the relationship between the visibility data and extinction coefficient of meteorological observations to correct the AOD of the Advance Himawari Imager (AHI) onboard the Himawari-8 satellite. The hygroscopic growth factor (f(RH)) was fitted site-by-site and month by month (1–12 months). Meanwhile, the spatial distribution of the fitted coefficients can be obtained by interpolation assuming that the aerosol properties vary smoothly on a regional scale. The inverse distance weighted (IDW) method was performed to construct the hygroscopic correction factor grid for humidity correction so as to estimate the PM2.5 concentrations in Sichuan and Chongqing from 09:00 to 16:00 in 2017–2018. The results indicate that the correlation between “dry” extinction coefficient and PM2.5 is slightly improved compared to the correlation between AOD and PM2.5, with r coefficient values increasing from 0.12–0.45 to 0.32–0.69. The r of hour-by-hour verification is between 0.69 and 0.85, and the accuracy of the afternoon is higher than that of the morning. Due to the missing rate of AOD in the southwest is very high, this study utilized inverse variance weighting (IVW) gap-filling method combine satellite estimation PM2.5 and the nested air-quality prediction modeling system (NAQPMS) simulation data to obtain the full-coverage hourly PM2.5 concentration and analyze a pollution process in the fall and winter.

The evolution processes of complex systems carry key information in the systems’ functional properties. Applying machine learning algorithms, we demonstrate that the historical formation process of various networked complex systems can be extracted, including protein-protein interaction, ecology, and social network systems. The recovered evolution process has demonstrations of immense scientific values, such as interpreting the evolution of protein-protein interaction network, facilitating structure prediction, and particularly revealing the key co-evolution features of network structures such as preferential attachment, community structure, local clustering, degree-degree correlation that could not be explained collectively by previous theories. Intriguingly, we discover that for large networks, if the performance of the machine learning model is slightly better than a random guess on the pairwise order of links, reliable restoration of the overall network formation process can be achieved. This suggests that evolution history restoration is generally highly feasible on empirical networks. Evolution processes of complex networked systems in biology and social sciences, and their underlying mechanisms, still need better understanding. The authors propose a machine learning approach to reconstruct the evolution history of complex networks.

The evolution processes of complex systems carry key information in the systems' functional properties. Applying machine learning algorithms, we demonstrate that the historical formation process of various networked complex systems can be extracted, including protein-protein interaction, ecology, and social network systems. The recovered evolution process has demonstrations of immense scientific values, such as interpreting the evolution of protein-protein interaction network, facilitating structure prediction, and particularly revealing the key co-evolution features of network structures such as preferential attachment, community structure, local clustering, degree-degree correlation that could not be explained collectively by previous theories. Intriguingly, we discover that for large networks, if the performance of the machine learning model is slightly better than a random guess on the pairwise order of links, reliable restoration of the overall network formation process can be achieved. This suggests that evolution history restoration is generally highly feasible on empirical networks.