The real-time, accurate, and refined monitoring of urban green space status information is of great significance in the construction of urban ecological environment and the improvement of urban ecological benefits. The high-resolution technology can provide abundant information of ground objects, which makes the information of urban green surface more complicated. The existing classification methods are challenging to meet the classification accuracy and automation requirements of high-resolution images. This paper proposed a deep learning classification method for urban green space based on phenological features constraints in order to make full use of the spectral and spatial information of green space provided by high-resolution remote sensing images (GaoFen-2) in different periods. The vegetation phenological features were added as auxiliary bands to the deep learning network for training and classification. We used the HRNet (High-Resolution Network) as our model and introduced the Focal Tversky Loss function to solve the sample imbalance problem. The experimental results show that the introduction of phenological features into HRNet model training can effectively improve urban green space classification accuracy by solving the problem of misclassification of evergreen and deciduous trees. The improvement rate of F1-Score of deciduous trees, evergreen trees, and grassland were 0.48%, 4.77%, and 3.93%, respectively, which proved that the combination of vegetation phenology and high-resolution remote sensing image can improve the results of deep learning urban green space classification.

Evaluating and exploring regional eco-environmental quality (EEQ), economic development equality (EDE) and the coupling coordination degree (CCD) at multiple scales is important for realizing regional sustainable development goals. The CCD can reflect both the development level and the interaction relationship of two or more systems. However, relevant previous studies have ignored non-statistical data, lacked multiscale analyses, misused the coupling coordination degree model or have not sufficiently considered economic development equality. In response to these problems, this study integrated multisource remote sensing datasets to calculate and analyse the remote sensing ecological index (RSEI) and then used nighttime light data and population density data to calculate the proposed nighttime difference index (NTDI). Next, a modified coupling coordination degree (MCCD) index was proposed to analyse the MCCD between EEQ and EDE. Then, spatiotemporal and multiscale analyses at the county, city, province, urban agglomeration and country levels were performed. Global and local spatial autocorrelation and trend analyses were performed to evaluate the spatial aggregation degree and change trends from 2001 to 2020. The main conclusions are as follows: (1) The EEQ of China displayed a fluctuating upwards trend (0.0048 a⁻¹), with average RSEI values of 0.5950, 0.6277, 0.6164, 0.6311 and 0.6173; the EDE of China showed an upwards trend (0.0298 a⁻¹), with average NTDI values of 0.1271, 0.1635, 0.1642, 0.2181 and 0.2490; and China’s MCCD indicated an upwards trend (0.0220 a⁻¹), with values of 0.4614, 0.5027, 0.4978, 0.5401 and 0.5525. (2) The highest global Moran’s I of NTDI and MCCD was achieved at the city scale, while the highest RSEI was achieved at the county scale. From 2001 to 2020, the spatial agglomeration effect of the RSEI decreased, while that of the NTDI and MCCD increased. (3) A power function relationship occurred between NTDI and MCCD at different scales. Furthermore, the NTDI had a higher contribution to improving the MCCD than the RSEI and the R² of the fitted curve at different scales ranged from 0.8183 to 0.9915.

The ship detection task using optical remote sensing images is important for in maritime safety, port management and ship rescue. With the wide application of deep learning to remote sensing, a series of target detection algorithms, such as faster regions with convolution neural network feature (R-CNN) and You Only Look Once (YOLO), have been developed to detect ships in remote sensing images. These detection algorithms use fully connected layer direct regression to obtain coordinate points. Although training and forward speed are fast, they lack spatial generalization ability. To avoid the over-fitting problem that may arise from the fully connected layer, we propose a fully convolutional neural network, SDGH-Net, based on Gaussian heatmap regression. SDGH-Net uses an encoder–decoder structure to obtain the ship area feature map by direct regression. After simple post-processing, the ship polygon annotation can be obtained without non-maximum suppression (NMS) processing. To speed up model training, we added a batch normalization (BN) processing layer. To increase the receptive field while controlling the number of learning parameters, we introduced dilated convolution and added it at different rates to fuse the features of different scales. We tested the performance of our proposed method using a public ship dataset HRSC2016. The experimental results show that this method improves the recall rate of ships, and the F-measure is 85.05%, which surpasses all other methods we used for comparison.

Landslide susceptibility mapping (LSM) is significant for disaster prevention and mitigation, land use management, and as a reference for decision-making. Convolutional neural networks (CNNs) in deep learning have been successfully applied to LSM studies and have been shown to improve the accuracy of LSM. Although optimizing the quality of negative samples at the input step of a deep learning model can improve the accuracy of the model, the risk of model overfitting may increase. In this study, an LSM method based on the Gaussian heatmap sampling technique and a CNN was developed from the perspective of LSM dataset sampling. A Gaussian heatmap sampling technique was used to enrich the variety of landslide inventory at the input step of the deep learning model to improve the accuracy of the LSM results. This sampling technique involved the construction of a landslide susceptibility Gaussian heatmap neural network model, LSGH-Net, by combining a CNN. A series of optimization strategies such as attention mechanism, dropout, etc., were applied to improve the model structure and training process. The results demonstrated that the proposed approach outperformed the benchmark CNN-based algorithm in terms of metrics (Accuracy = 95.30%, F1 score = 95.13%, and Sensitivity = 91.79%). The Gaussian heatmap sampling technique effectively improved the accuracy of frequency histograms of the landslide susceptibility index, which provided finer-grained mapping details and more reasonable landslide density. By analyzing Gaussian heatmap at different scales, the approach proposed in this paper is an important reference for different regions and other disaster susceptibility studies as well.

Quickly and accurately extracting buildings from remote sensing images is essential for urban planning, change detection, and disaster management applications. In particular, extracting buildings that cannot be sheltered in emergency shelters can help establish and improve a city’s overall disaster prevention system. However, small building extraction often involves problems, such as integrity, missed and false detection, and blurred boundaries. In this study, EfficientUNet+, an improved building extraction method from remote sensing images based on the UNet model, is proposed. This method uses EfficientNet-b0 as the encoder and embeds the spatial and channel squeeze and excitation (scSE) in the decoder to realize forward correction of features and improve the accuracy and speed of model extraction. Next, for the problem of blurred boundaries, we propose a joint loss function of building boundary-weighted cross-entropy and Dice loss to enforce constraints on building boundaries. Finally, model pretraining is performed using the WHU aerial building dataset with a large amount of data. The transfer learning method is used to complete the high-precision extraction of buildings with few training samples in specific scenarios. We created a Google building image dataset of emergency shelters within the Fifth Ring Road of Beijing and conducted experiments to verify the effectiveness of the method in this study. The proposed method is compared with the state-of-the-art methods, namely, DeepLabv3+, PSPNet, ResUNet, and HRNet. The results show that the EfficientUNet+ method is superior in terms of Precision, Recall, F1-Score, and mean intersection over union (mIoU). The accuracy of the EfficientUNet+ method for each index is the highest, reaching 93.01%, 89.17%, 91.05%, and 90.97%, respectively. This indicates that the method proposed in this study can effectively extract buildings in emergency shelters and has an important reference value for guiding urban emergency evacuation.

Under the background of intensified human activities and global climate warming, the frequency and intensity of flood disasters have increased, causing many casualties and economic losses every year. Given the difficulty of mountain shadow removal from large-scale watershed flood monitoring based on Sentinel-1 SAR images and the Google Earth Engine (GEE) cloud platform, this paper first adopted the Support Vector Machine (SVM) to extract the water body information during flooding. Then, a function model was proposed based on the mountain shadow samples to remove the mountain shadows from the flood maps. Finally, this paper analyzed the flood disasters in the middle and lower basin of the Yangtze River (MLB) in 2020. The main results showed that: (1) compared with the other two methods, the SVM model had the highest accuracy. The accuracy and kappa coefficients of the trained SVM model in the testing dataset were 97.77% and 0.9521, respectively. (2) The function model proposed based on the samples achieved the best effect compared with other shadow removal methods with a shadow recognition rate of 75.46%, and it alleviated the interference of mountain shadows for flood monitoring in a large basin. (3) The flood inundated area was 8526 km², among which, cropland was severely affected (6160 km²). This study could provide effective suggestions for relevant stakeholders in policy making.