Search Results (68,662)

Coal mining in the Loess Plateau can very easily generate ground cracks, and these cracks can immediately result in ventilation trouble under the mine shaft, runoff disturbance, and vegetation destruction. Advanced UAV (Unmanned Aerial Vehicle) high-resolution mapping and DL (Deep Learning) are introduced as the key methods to quickly delineate coal mining ground surface cracks for disaster prevention. Firstly, the dataset named the Ground Cracks of Coal Mining Area Unmanned Aerial Vehicle (GCCMA-UAV) is built, with a ground resolution of 3 cm, which is suitable to make a 1:500 thematic map of the ground crack. This GCCMA-UAV dataset includes 6280 images of ground cracks, and the size of the imagery is 256 × 256 pixels. Secondly, the DRA-UNet model is built effectively for coal mining ground surface crack delineation. This DRA-UNet model is an improved UNet DL model, which mainly includes the DAM (Dual Dttention Dechanism) module, the RN (residual network) module, and the ASPP (Atrous Spatial Pyramid Pooling) module. The DRA-UNet model shows the highest recall rate of 77.29% when the DRA-UNet was compared with other similar DL models, such as DeepLabV3+, SegNet, PSPNet, and so on. DRA-UNet also has other relatively reliable indicators; the precision rate is 84.92% and the F1 score is 78.87%. Finally, DRA-UNet is applied to delineate cracks on a DOM (Digital Orthophoto Map) of 3 km² in the mining workface area, with a ground resolution of 3 cm. There were 4903 cracks that were delineated from the DOM in the Huojitu Coal Mine Shaft. This DRA-UNet model effectively improves the efficiency of crack delineation. Full article

The deep integration of communication and sensing technology in fiber-optic systems has been highly sought after in recent years, with the aim of rapid and cost-effective large-scale upgrading of existing communication cables in order to monitor ocean activities. As a proof-of-concept demonstration, a high-degree of compatibility was shown between forward-transmission distributed fiber-optic vibration sensing and an on–off keying (OOK)-based communication system. This type of deep integration allows distributed sensing to utilize the optical fiber communication cable, wavelength channel, optical signal and demodulation receiver. The addition of distributed sensing functionality does not have an impact on the communication performance, as sensing involves no hardware changes and does not occupy any bandwidth; instead, it non-intrusively analyzes inherent vibration-induced noise in the data transmitted. Likewise, the transmission of communication data does not affect the sensing performance. For data transmission, 150 Mb/s was demonstrated with a BER of 2.8 × 10⁻⁷ and a Q_dB of 14.1. For vibration sensing, the forward-transmission method offers distance, time, frequency, intensity and phase-resolved monitoring. The limit of detection (LoD) is 8.3 pε/Hz^1/2 at 1 kHz. The single-span sensing distance is 101.3 km (no optical amplification), with a spatial resolution of 0.08 m, and positioning accuracy can be as low as 10.1 m. No data averaging was performed during signal processing. The vibration frequency range tested is 10–1000 Hz. Full article

Image stitching aims to construct a wide field of view with high spatial resolution, which cannot be achieved in a single exposure. Typically, conventional image stitching techniques, other than deep learning, require complex computation and are thus computationally expensive, especially for stitching large raw images. In this study, inspired by the multiscale feature of fluid turbulence, we developed a fast feature point detection algorithm named local-peak scale-invariant feature transform (LP-SIFT), based on the multiscale local peaks and scale-invariant feature transform method. By combining LP-SIFT and RANSAC in image stitching, the stitching speed can be improved by orders compared with the original SIFT method. Benefiting from the adjustable size of the interrogation window, the LP-SIFT algorithm demonstrates comparable or even less stitching time than the other commonly used algorithms, while achieving comparable or even better stitching results. Nine large images (over 2600 × 1600 pixels), arranged randomly without prior knowledge, can be stitched within 158.94 s. The algorithm is highly practical for applications requiring a wide field of view in diverse application scenes, e.g., terrain mapping, biological analysis, and even criminal investigation. Full article

Traditional villages have reached milestones in developing a living culture, politics, economy, and society, among other aspects, while acting as important carriers of agricultural culture formed by long-term interactions between humans and nature. Unfortunately, traditional villages could disappear with the advent of urbanization. Therefore, this study enhances the accuracy of traditional village classification protection work by examining traditional villages in the Jinjiang River Basin in Quanzhou, China. A spatial pattern is extracted for the socio-ecological systems (SES) prototype of traditional villages, and an SES classification protection system is constructed based on a prototype analysis. Given the evaluation results, a K-means cluster analysis is applied to establish the SES sustainability levels for six types of traditional villages. After adjusting the types according to the principles of sustainability, equilibrium, and individual cases, six SES system types are identified: SES decay and shrinkage (Type 1), SES fusion and development (Type 2), SES ecological decline (Type 3), SES social decline (Type 4), SES ecological conservation (Type 5), and SES extensive development (Type 6). This system provides a quantitative analysis method to classify and protect concentrated and contiguous traditional villages. It also helps facilitate a better understanding of local rural society, economy, and culture, especially a deeper understanding of the interactions between humans and the rural environment. Full article

Metropolitan areas are important regions with a high concentration of population and public service facilities. The coupling coordination between public service facilities and population plays an important role in the sustainable development of economy and society. However, previous studies have focused on a few core cities, effectively identifying areas with weak coordination of public services and currently lacking corresponding information support and paradigms at the regional scale. Taking the Wuhan Metropolitan Area as an example, this paper strengthens the concern about the spatiality and locality of public service facilities in the region;, applies the improved CRITIC method and coupling coordination model to study the spatiotemporal distribution characteristics of public service facilities at the county and grid levels by using multisource data, and evaluates the intercity differences and dynamic changes of coupling coordination relationships between public service facilities and population. The findings are as follows: (1) Wuhan was the core of public service facilities in the metropolitan area, and a continuous high-level coordinated distribution was gradually developed on the east-west axis from 2016 to 2022; (2) there were differences in the coupling coordination degree of different types of facilities, among which the imbalance between the supply and demand of elderly care facilities was obvious; and (3) the coupling coordination degree of facilities in the Wu-E-Huang-Huang core development area was relatively high. Finally, we summarize the development stages of the coupling coordination between the facilities and population in the Wuhan Metropolitan Area and obtain the typical development characteristics. The research results could provide scientific support for planning decisions. Full article

To enhance the detection of pavement-sealed cracks and ensure the long-term stability of pavement performance, a novel approach called the shuffle attention-based pavement-sealed crack detection is proposed. This method consists of three essential components: the feature extraction network, the detection head, and the Wise Intersection over Union loss function. Within both the feature extraction network and the detection head, the shuffle attention module is integrated to capture the high-dimensional semantic information of pavement-sealed cracks by combining spatial and channel attention in parallel. The two-way detection head with multi-scale feature fusion efficiently combines contextual information for pavement-sealed crack detection. Additionally, the Wise Intersection over Union loss function dynamically adjusts the gradient gain, enhancing the accuracy of bounding box fitting and coverage area. Experimental results highlight the superiority of our proposed method, with higher [email protected] (98.02%), Recall (0.9768), and F1-score (0.9680) values compared to the one-stage state-of-the-art methods, showcasing improvements of 0.81%, 1.8%, and 2.79%, respectively. Full article

In recent years, China’s urbanization has accelerated, significantly impacting ecosystems and the carbon balance due to changes in urban land use. The spatial patterns of CO₂ emissions from urban land are essential for devising strategies to mitigate emissions, particularly in predicting future spatial distributions that guide urban development. Based on socioeconomic grid data, such as nighttime lights and the population, this study proposes a spatial prediction method for CO₂ emissions from urban land using a Long Short-Term Memory (LSTM) model with added fully connected layers. Additionally, the geographical detector method was applied to identify the factors driving the increase in CO₂ emissions due to urban land expansion. The results show that socioeconomic grid data can effectively predict the spatial distribution of CO₂ emissions. In the Yangtze River Economic Belt (YREB), emissions from urban land are projected to rise by 116.23% from 2020 to 2030. The analysis of driving factors indicates that economic development and population density significantly influence the increase in CO₂ emissions due to urban land expansion. In downstream cities, CO₂ emissions are influenced by both population density and economic development, whereas in midstream and upstream city clusters, they are primarily driven by economic development. Furthermore, technology investment can mitigate CO₂ emissions from upstream city clusters. In conclusion, this study provides a scientific basis for developing CO₂ mitigation strategies for urban land within the YREB. Full article

The distribution and development of rock mass discontinuities in 3D space control the deformation and failure characteristics of the rock mass, which in turn affect the strength, permeability, and stability of rock masses. Therefore, it is essential to accurately and efficiently characterize these discontinuities. Light Detection and Ranging (LiDAR) now allows for fast and precise 3D data collection, which supports the creation of new methods for characterizing rock mass discontinuities. However, uneven density distribution and local surface undulations can limit the accuracy of discontinuity characterization. To address this, we propose a method for characterizing complex rock mass discontinuities based on laser point cloud data. This method is capable of processing datasets with varying densities and can reduce over-segmentation in non-planar areas. The suggested approach involves a five-stage process that includes: (1) adaptive resampling of point cloud data based on density comparison; (2) normal vector calculation using Principal Component Analysis (PCA); (3) identifying non-planar areas using a watershed-like algorithm, and determine the main discontinuity sets using Multi-threshold Mean Shift (MTMS); (4) identify single discontinuity clusters using Density-Based Spatial Clustering of Applications with Noise (DBSCAN); (5) fitting discontinuity planes with Random Sample Consensus (RANSAC) and determining discontinuity orientations using analytic geometry. This method was applied to three rock slope datasets and compared with previous research results and manual measurement results. The results indicate that this method can effectively reduce over-segmentation and the characterization results have high accuracy. Full article

Due to the changing climate and human activity, more and more researchers started to focus on non-stationarity in hydrology. In the Wei River Basin, which is the largest tributary of the Yellow River, there is a significant reduction in the total amount of water resources which has been found in past decades. Additionally, the distribution of water resources within the basin is unbalanced, with the lower reaches and southern regions having relatively abundant water resources and other regions lacking these resources. Within this situation, it is important to consider the spatial aspect of water resource management. Four non-stationarity detection methods have been applied to investigate variation in seasonal discharge series. Two meteorological factors have also been analyzed. Based on test results and Köppen Geiger Climate classification, the water resource management has been investigated spatially. As for results, the Baojixia Channel has significant impact on the abrupt change of discharge, while the precipitation and temperature may have an impact on the discharge trend change. In addition, there was no clear evidence to prove that the climate zones impact spatially on the non-stationarity of discharge. Full article

The fragile environment of the Himalayan region is prone to natural hazards, which are intensified by climate change, leading to food and livelihood insecurity for inhabitants. Therefore, building resilience in the most dominant livelihood sector, i.e., the agricultural sector, has become a priority in development and planning. To assess the perils induced by climate change on the agriculture sector in the ecologically fragile region of Kashmir Valley, a study has been conducted to evaluate the risk using the Intergovernmental Panel on Climate Change (IPCC) framework. The risk index has been derived based on socioeconomic and ecological indicators for risk determinants, i.e., vulnerability, hazard, and exposure. Furthermore, the study also evaluated the future risk to the agriculture sector under changing climatic conditions using Shared Socioeconomic Pathways (SSPs) for SSP2-4.5 and SSP5-8.5 at mid- and late-century timescales. It was observed that districts such as Bandipora (0.59), Kulgam (0.56), Ganderbal (0.56), and Kupwara (0.54) are most vulnerable due to drivers like low per capita income, yield variability, and areas with >30% slope. Shopian and Srinagar were found to be the least vulnerable due to adaptive capacity factors like livelihood diversification, crop diversification, percentage of tree crops, and percentage of agriculture labor. In terms of the Risk index, the districts found to be at high risk are Baramulla (0.19), Pulwama (0.16), Kupwara (0.15), and Budgam (0.13). In addition, the findings suggested that the region would experience a higher risk of natural hazards by the mid- (MC) and end-century (EC) due to the projected increase in temperature with decreasing precipitation, which would have an impact on crop yields and the livelihoods of farmers in the region. Full article

Moran’s I is a spatial autocorrelation measure of univariate spatial data. Therefore, even if p spatial data exist, we can only obtain p values for Moran’s I. In other words, Moran’s I cannot measure the degree of spatial autocorrelation of multivariate spatial data as a single value. This paper addresses this issue. That is, we extend Moran’s I so that it can measure the degree of spatial autocorrelation of multivariate spatial data as a single value. In addition, since the local version of Moran’s I has the same problem, we extend it as well. Then, we establish their properties, which are fundamental for applied work. Numerical illustrations of the theoretical results obtained in the paper are also provided. Full article

The desertification of the China–Mongolia–Russia Economic Corridor (CMREC), one of the six major economic corridors in the Belt and Road Initiative, has posed a great challenge to the ecological environment protection and sustainable economic development of the region. In this work, two categories of feature space models based on point–point mode and point–line mode were constructed. The optimal feature space model was used to establish the spatial–temporal change patterns of desertification in the CMREC from 2001 to 2020, and then the dominant driving factors were quantitatively determined. The conclusions demonstrated the following: (1) the monitoring accuracy of the Albedo–MSAVI desertification model based on point–point mode was the highest, at 86.47%, followed by that of the TGSI–MSAVI model based on point–line mode, at 85.71%; (2) from 2001 to 2020, the spatial distribution of desertification in the China–Mongolia–Russia Economic Corridor region showed a decreasing trend radiating outwards from the Inner Mongolia Plateau and Gobi Desert; (3) the gravity center of desertification in Chinese parts in the CMREC migrated toward the northeast, while the Mongolia and Russia parts migrated toward the southwest and southeast, respectively; and (4) from 2001 to 2020, precipitation and land use change had the greatest impacts on the evolution patterns of desertification in China and Mongolia, while topography and land use contributed greatly to the change process of desertification in Russia. The research results could provide data support for desertification control in the CMREC. Full article

Rivers represent naturally dynamic ecosystems that require diligent preservation efforts to maintain ecological balance and biodiversity. Understanding the evolutionary movements of rivers is crucial for effective conservation and management strategies. Geographic information systems (GISs) have emerged as indispensable tools in this domain and provide detailed spatial analysis and visualization capabilities. This paper explores the development and application of a specific set of GIS tools called RiverMetrics, which was designed to monitor and analyze rivers’ changes over time. By leveraging these advanced tools, researchers and environmental managers can gain deeper insights into river dynamics, enabling informed decision-making to safeguard these vital ecosystems. This paper details the functionalities and benefits of these GIS tools and demonstrates their critical role in river conservation efforts. The Paglia River in Central Italy serves as a case study for demonstrating the validity of RiverMetrics tools in monitoring long-term trends. The tools offer significant advantages for monitoring and calculating various indexes such as the sinuosity, braiding index, and profile trend. They also provide researchers with a simple way to process spatial data with precision and efficiency, increasing their ability to perform correct environmental monitoring. Full article

Many major diseases can cause changes in the morphology of blood vessels, and the segmentation of retinal blood vessels is of great significance for preventing these diseases. Obtaining complete, continuous, and high-resolution segmentation results is very challenging due to the diverse structures of retinal tissues, the complex spatial structures of blood vessels, and the presence of many small ships. In recent years, deep learning networks like UNet have been widely used in medical image processing. However, the continuous down-sampling operations in UNet can result in the loss of a significant amount of information. Although skip connections between the encoder and decoder can help address this issue, the encoder features still contain a large amount of irrelevant information that cannot be efficiently utilized by the decoder. To alleviate the irrelevant information, this paper proposes a feature selection module between the decoder and encoder that utilizes the self-attention mechanism of transformers to accurately and efficiently select the relevant encoder features for the decoder. Additionally, a lightweight Residual Global Context module is proposed to obtain dense global contextual information and establish dependencies between pixels, which can effectively preserve vascular details and segment small vessels accurately and continuously. Experimental results on three publicly available color fundus image datasets (DRIVE, CHASE, and STARE) demonstrate that the proposed algorithm outperforms existing methods in terms of both performance metrics and visual quality. Full article

Traditional deep learning methods employing 2D images can only classify healthy and unhealthy seedlings; consequently, this study proposes a method by which to further classify healthy seedlings into primary seedlings and secondary seedlings and finally to differentiate three classes of seedling through a 3D point cloud for the detection of useful eggplant seedling transplants. Initially, RGB images of three types of substrate-cultivated eggplant seedlings (primary, secondary, and unhealthy) were collected, and healthy and unhealthy seedlings were classified using ResNet50, VGG16, and MobilNetV2. Subsequently, a 3D point cloud was generated for the three seedling types, and a series of filtering processes (fast Euclidean clustering, point cloud filtering, and voxel filtering) were employed to remove noise. Parameters (number of leaves, plant height, and stem diameter) extracted from the point cloud were found to be highly correlated with the manually measured values. The box plot shows that the primary and secondary seedlings were clearly differentiated for the extracted parameters. The point clouds of the three seedling types were ultimately classified directly using the 3D classification models PointNet++, dynamic graph convolutional neural network (DGCNN), and PointConv, in addition to the point cloud complementary operation for plants with missing leaves. The PointConv model demonstrated the best performance, with an average accuracy, precision, and recall of 95.83, 95.83, and 95.88%, respectively, and a model loss of 0.01. This method employs spatial feature information to analyse different seedling categories more effectively than two-dimensional (2D) image classification and three-dimensional (3D) feature extraction methods. However, there is a paucity of studies applying 3D classification methods to predict useful eggplant seedling transplants. Consequently, this method has the potential to identify different eggplant seedling types with high accuracy. Furthermore, it enables the quality inspection of seedlings during agricultural production. Full article