Accurate translation of aerial imagery to maps is a direction of great value and challenge in mapping, a method of generating maps that does not require using vector data as traditional mapping methods do. The tremendous progress made in recent years in image translation based on generative adversarial networks has led to rapid progress in aerial image-to-map translation. Still, the generated results could be better regarding quality, accuracy, and visual impact. This paper proposes a supervised model (SAM-GAN) based on generative adversarial networks (GAN) to improve the performance of aerial image-to-map translation. In the model, we introduce a new generator and multi-scale discriminator. The generator is a conditional GAN model that extracts the content and style space from aerial images and maps and learns to generalize the patterns of aerial image-to-map style transformation. We introduce image style loss and topological consistency loss to improve the model’s pixel-level accuracy and topological performance. Furthermore, using the Maps dataset, a comprehensive qualitative and quantitative comparison is made between the SAM-GAN model and previous methods used for aerial image-to-map translation in combination with excellent evaluation metrics. Experiments showed that SAM-GAN outperformed existing methods in both quantitative and qualitative results.

Forest fire regimes are changing as a function of increasing global weather extremes, socioeconomic development, and land use change. It is appropriate to use long-term time series satellite observations to better understand forest fire regimes. However, many studies that have analyzed the spatiotemporal characteristics of forest fires based on fire frequency have been inadequate. In this study, a set of metrics was derived from the VIIRS active fire data in China, from 2012 to 2021, through spatial extraction, spatiotemporal clustering, and spread reconstruction to obtain the frequency of forest fire spots (FFS), the frequency of forest fire events (FFE), the frequency of large forest fire events (LFFE), duration, burned area, and spread rate; these metrics were compared to explore the characteristics of forest fires at different spatiotemporal scales. The experimental results include 72.41 × 10⁴ forest fire spots, 7728 forest fire events, 1118 large forest fire events, and a burned area of 58.4 × 10⁴ ha. Forest fires present a significant spatiotemporal aggregation, with the most FFS and FFE in the Southern Region and the most severe LFFE and burned area in the Southwest Region. The FFS, FFE, and LFFE show a general decreasing trend on an annual scale, with occasional minor rebounds. However, the burned area had substantial rebounds in 2020. The high incidence of forest fires was concentrated from March to May. Additionally, 74.7% of the forest fire events had a duration of less than 5 days, while 25.3% of the forest fire events lasted more than 5 days. This helps us to understand the characteristics of more serious or higher risk forest fires. This study can provide more perspectives for exploring the characteristics of forest fires, and more data underpinning for forest fire prevention and management. This will contribute towards reasonable forest protection policies and a sustainable environment.

As a core task of computer vision perception, 3D scene understanding has received widespread attention. However, the current research mainly focuses on the semantic understanding task at the level of entity objects and often neglects the semantic relationships between objects in the scene. This paper proposes a 3D scene graph prediction model based on deep learning methods for scanned point cloud data of indoor scenes to predict the semantic graph about the class of entity objects and their relationships. The model uses a multi-scale pyramidal feature extraction network, MP-DGCNN, to fuse features with the learned category-related unbiased meta-embedding vectors, and the relationship inference of the scene graph uses an ENA-GNN network incorporating node and edge cross-attention; in addition, considering the long-tail distribution effect, a category grouping re-weighting scheme is used in the embedded prior knowledge and loss function. For the 3D scene graph prediction task, experiments on the indoor point cloud 3DSSG dataset show that the model proposed in this paper performs well compared with the latest baseline model, and the prediction effectiveness and accuracy are substantially improved.

This study proposes a two-dimensional analytical framework based on urban spatial form and spatial service perspectives, utilizing data on buildings and points of interest (POIs). It integrates fishnet analysis, kernel density analysis, the categorization of POI functionalities, and mixture calculations to enhance our understanding of urban spatial form and function. Taking the main urban area of Zhengzhou as an example, this study identifies image elements that can describe urban spatial characteristics through the results of two-dimensional analysis and enriches the city image in the form of a portrait. The experimental findings demonstrate that the elements of the annular layer, functional landmarks, ring line boundaries, and special districts can fully convey the spatial picture of Zhengzhou City. The performance of the four types of image elements has a high degree of matching with the content of the urban spatial planning of Zhengzhou City, which can effectively identify the urban multi-center structure and development pattern. This paper explores and tests the development status of the city from a new perspective, which can provide an effective reference for the future planning and sustainable development of the city.

The traditional model reference adaptive system (MRAS) has the problem of error accumulation and DC bias in the pure integration of flux observation. In order to solve this problem, this paper presents an improved model reference adaptive speed identification method. A high pass filter is added to the voltage model to eliminate the pure integral effect, and a high pass filter is added to the current model to balance the phase and amplitude errors. Thus, the influence of DC bias can be eliminated. On the other hand, when the flux is observed, the feedback quantity is added, and the error value is obtained by comparing the stator flux values obtained by the voltage model and the current model respectively. Then, the error value is corrected by the PI regulator, it can improve the accuracy of the observer. In the MATLAB/SIMULINK environment, the model reference adaptive algorithm is simulated. The results show that the model reference adaptive algorithm can realize the accurate estimation of the rotor speed and position without load start and load start, and realize the sensorless operation of the permanent magnet synchronous motor.

Improve power quality problems, the company introduced the "tag through 66kV Static dynamic reactive power compensation device (SVC)", which means water cooling valve parts, using the international advanced technology and light control thyristor, the real control cabinet and valve all-fiber connections between groups, no valve trigger circuit boards, etc., to ensure safe and reliable high-pressure environment. Light control while protecting 66kV more stable water-cooled manifold, also designed the various protection functions. Reactive power compensation device based on electrical design principle, the protection of the valve design principles, summarized the valve characteristic is a light-controlled thyristor trigger and pulse trigger laser fiber distribution device as one of the valve, the valve overcurrent analysis protection, undervoltage protection, return status display, RC protection, BOD protection, protection and cooling system valve structural protection, light control demonstrates the necessity of 66kV water cooling valve protection; through the reactive power compensation and benefits case situation the comparative analysis to verify the correctness of the application of SVC devices.