Multi-scale Data Research Articles

APNet: Adaptive projection network for medical image denoising.

In clinical medicine, low-dose radiographic image noise reduces the quality of the detected image features and may have a negative impact on disease diagnosis. In this study, Adaptive Projection Network (APNet) is proposed to reduce noise from low-dose medical images. APNet is developed based on an architecture of the U-shaped network to capture multi-scale data and achieve end-to-end image denoising. To adaptively calibrate important features during information transmission, a residual block of the dual attention method throughout the encoding and decoding phases is integrated. A non-local attention module to separate the noise and texture of the image details by using image adaptive projection during the feature fusion. To verify the effectiveness of APNet, experiments on lung CT images with synthetic noise are performed, and the results demonstrate that the proposed approach outperforms recent methods in both quantitative index and visual quality. In addition, the denoising experiment on the dental CT image is also carried out and it verifies that the network has a certain generalization. The proposed APNet is an effective method that can reduce image noise and preserve the required image details in low-dose radiographic images.

Structural analysis, tectonic fracturing modeling, and kinematic evolution along the South Atlas Fault at the northern border of the Tinghir-Errachidia-Boudenib basin (Pre-African Trough, Morocco)

The structural evolution of the High Atlas orogenic belt is characterized by the formation of the thrust propagation folds. The exploration and understanding of the southern central-eastern High Atlas orogenic wedge system are still in their infancy. The significance of the growth of the Tinghir-Errachidia-Boudenib foreland basin (TEB) is underestimated due to limited constraints on surface structural styles and kinematics analysis, as well as insufficient surface data. This question is addressed by using several multi-sources and multi-scale data including a geological map constrained from fieldwork and kinematic analysis, combined with subsurface magnetic data. The integration and analysis of these data provided a comprehensive understanding tectonic fracturing model and reconstruct the kinematic evolution of the northern border of the TEB basin. Analysis of surface and subsurface data identify E−, ENE-to WNW- trending Jbel Tisdar and Jbel Rhouir anticlines interpreted as a fault-propagation fold. Magnetic investigations show a positive anomaly superposed on the hinge of the Jbel Tisdar and the Jbel Rhouir anticlines indicating a Triassic and/or Paleozoic uplifted magnetic materials. Along the southern Atlas margin, brittle tectonic is represented by E−to ENE-reverse faults with a small dextral strike-slip component and NNE-to NE-trending strike-slip faults with a reverse component and associated with NW- trending ones. Fracturing mechanism fault-propagation fold highlights three fracture sets: (i) syn-folding E−trending axial fractures; (ii) syn-folding NW- trending transverse fractures and (iii) late-folding NE-trending fractures. Fault kinematics analyses provide a transpressional tectonic regime, responsible for the structuring (folding, faulting, fracturing) of the Jbel Tisdar and the Jbel Rhouir fault-propagation fold, developed in response to Alpine compressional inversion of the central-eastern High Atlas belt.

Seismic resolution enhancement with variational modal-based fast-matching pursuit decomposition

Enhancing vertical resolution and signal-to-noise ratio (S/N) is a key objective in seismic data processing. Considering the underground medium is inhomogeneous and incompletely elastic, seismic wave energy attenuation occurs during underground propagation, which has a significant impact on seismic data resolution and S/N. Traditional fast-matching pursuit (FMP) algorithms make it difficult to separate valid signals and noise effectively while reconstructing the noisy signals. Therefore, an improved FMP algorithm that combines the variational-mode decomposition (VMD) strategy is developed. The VMD algorithm is used to obtain intrinsic mode functions with varying amplitudes, frequencies, and center times. It can achieve a multiscale decomposition of nonstationary seismic data. Based on the intrinsic mode functions of different scales, the FMP algorithm can reconstruct prior information of the amplitude, frequency, and center time of valid signals and noise signals in the mode functions. Thus, the high-resolution sparse representation of intrinsic mode functions is achieved. The numerical results indicate that our method not only separates the effective signal and noise but also preserves the valid signal as much as possible. In addition, the feasibility of the method is further verified by field exploration data. The results indicate that this strategy can enhance the resolution of seismic data while restoring the attenuated energy using multiscale seismic data.

Semantic segmentation of urban land classes using a multi-scale dataset

ABSTRACT The use of remote sensing imagery for land cover and land use classification has made significant advancements in recent years. However, it becomes particularly challenging to enhance the semantic representation of high-resolution networks while dealing with uneven land categories and merging multi-scale data without compromising the accuracy of semantic segmentation. To tackle this challenge, this paper presents a novel method for classifying high-resolution remote sensing images based on a deep neural network that performs semantic segmentation of urban construction lands into five categories: vegetation, water, buildings, roads, and bare soil. The network incorporates a U-shaped high-resolution neural network and the advanced high-resolution network (HRNet) framework. The parallel storage of feature maps with different resolutions enables the exchange of information between them. The data pre-processing module addresses the issue of data imbalance in the semantic segmentation of urban construction lands, resulting in an increase in Intersection over Union (IoU) values for different land types by 3.75%-12.01%. Additionally, a target context representation module is introduced to enhance the feature representation of pixels by calculating the relationship between pixels and multiple target regions. Moreover, a polarization attention mechanism is proposed to extract the characteristics of geographical objects in all directions and achieve a stronger semantic representation. This method provides a novel approach to accurately and effectively extract information on construction lands and advance the development of monitoring algorithms for urban construction lands. To validate the proposed U-HRNet-OCR+PSA network, a comparative analysis was conducted with six classical networks, including DeepLabv3+, PSPNet, U-Net, U-Net++, HRNet, and HRNet-OCR, as well as the relatively new ViT-adapter-L, Oneformer and InternImage-H. The experiments demonstrate that the U-HRNet-OCR+PSA network achieves higher accuracy compared to the aforementioned networks. Specifically, the corresponding IoU values for the buildings, roads, vegetation, bare soil, and water in the multi-scale dataset are 89.79%, 90.05%, 94.89%, 85.91%, and 88.36%, respectively.

Optimal scale selection approach for classification based on generalized multi-scale formal context

The classification of multi-scale data is an important research topic in granular computing. Its research goal is to determine the most appropriate scale and achieve better classification performance. However, determining the optimal scale is often a difficult problem due to lacking better metrics and optimization methods. In order to solve this problem, this paper proposes the optimal scale selection criteria for generalized multi-scale formal contexts. That is, the optimal scale uses the coarsest conditional attributes and finest decision attributes to optimize the combination of granularities of attributes. We combine these criteria with multi-objective optimization methods for developing an algorithm to fast compute the optimal scale. Experiments show that for the selected 14 data sets and 11 comparative classification methods, there are 9 classification methods with higher classification accuracies on more than 9 data sets. Therefore, the optimal scale selection method proposed in this paper is feasible and can effectively improve the performance of the classification method.

Hyperspectral mapping of magmatic-hydrothermal sericite, Battle Mountain mining district, Nevada

We demonstrate the utility of multi-scale imaging spectroscopy data (hyperspectral data) to differentiate magmatic-hydrothermal sericite from other white micas based on grain size, in a case study of the Battle Mountain mining district in Humboldt and Lander Counties, Nevada. The Battle Mountain mining district contains porphyry, skarn, and distal disseminated deposits that formed in magmatic-hydrothermal systems, as well as sedimentary-rock hosted gold deposits of less certain origin. We generated spectral-based mineral maps of the Battle Mountain mining district to examine the spatial distribution of spectrally dominant minerals such as kaolinite, montmorillonite, and white micas (muscovite, sericite, and illite). We then used spectral-based mineral mapping to characterize the grain size and composition of white micas, enabling us to differentiate igneous muscovite from magmatic-hydrothermal sericite. By integrating our spectral-based maps with geologic mapping, airborne aeromagnetic data, and prior studies on mines and deposits in Battle Mountain, we determined that finer grained, higher Al sericite spatially correlated with the footprints of known magmatic-hydrothermal systems and is interpreted as forming from magmatic-hydrothermal alteration. Larger grained, lower Al muscovites are distal from known magmatic-hydrothermal systems and are interpreted as being igneous derived siliciclastic sediments that became constituents of the host sedimentary rocks. Techniques described in this contribution can be applied to any appropriate hyperspectral data, regardless of sensor type used to collect the data.

Wind turbine gearbox multi-scale condition monitoring through operational data

Since wind is expected to play a crucial role on the worldwide electricity production scenario, the reliability of the turbines is attracting attention of both industry and academia. New techniques for efficient condition monitoring of key components can be fundamental to optimising the performance and maintenance of a large fleet of turbines. The gearbox and bearings are the most critical mechanical components as they are responsible for a large proportion of the downtime of a wind turbine over its lifetime. However, the monitoring of wind turbine gearboxes is challenging due to the non-stationary nature of the operation and the lack of noise-free vibration measurements. In the present work, a new approach for efficient long to short term monitoring of wind turbine gearboxes has been developed based on real data. An turbine drivetrain failure was used as a test case to develop a new approach based on the use of multi-scale data sources. On the one hand, SCADA (Supervisory Control And Data Acquisition) data were used for general monitoring of the condition of the machine component on long to medium term time scales, while on the other hand, high resolution, triggered event data collected by a CMS (Condition Monitoring System) were used to refine the diagnosis and prognosis of the fault on a shorter time scale. Even though triggered spot events are very difficult to manage, the results show that the use of multi-scale high resolution CMS data can be fast and useful in fault diagnosis to classify a target machine with a healthy reference one. In the present work, the one-class SVM (Support Vector Method) was used for novelty detection. The approach, when applied to all available time scales, can be very precise in detecting the faulty machine and can therefore be proposed as a fast detection approach requiring less data compared to the classical data-driven regression normal behaviour model developed with continuously available SCADA data.

Determining the optimal generalization operators for building footprints using an improved graph neural network model

Determining the optimal generalization operators of city buildings is a crucial step during the building generalization process and an important aspect of realizing cross-scale updating of map data. It is a decision-making behavior of the cartographer that can be learned and simulated using artificial intelligence algorithms. Multi-scale data can provide rich generalization samples to train the determination process. However, previous studies have focused primarily on the intelligent use of each generalization operator separately, neglecting the intelligent scheduling issue between multiple operators when they are used simultaneously. Herein, we propose an improved graph neural network (GNN) called self-neighborhood merged GNN (SNGNN) that selects the optimal generalization operators for different buildings. In SNGNN, node and edge information are passed with different weights through two modules to simulate the effects of a building on itself and the neighborhood on either side. SNGNN has been experimentally validated using sample datasets for Ningbo, China, at 1:10,000 and 1:25,000. The F1-score of the testing dataset was 94.19%, and the classification precision of each operator was ≥87%. Compared with other popular intelligent algorithms, the experimental results for SNGNN revealed better performance in determining the optimal generalization operators.

A Temporal Variable-Scale Clustering Method on Feature Identification for Policy Public-Opinion Management

The development of various digital social network platforms has caused public opinion to play an increasingly important role in the policy making process. However, due to the fact that public opinion hotspots usually change rapidly (such as the phenomenon of public opinion inversion), both the behaviour feature and demand feature of netizens included in the public opinion often vary over time. Therefore, this paper focuses on the feature identification problem of public opinion simultaneously considering the multiple observation time intervals and key time points, in order to support the management of policy-focused online public opinion. According to the variable-scale data analysis theory, the temporal scale space model is established to describe candidate temporal observation scales, which are organized following the time points of relevant policy promulgation (policy time points). After proposing the multi-scale temporal data model, a temporal variable-scale clustering method (T-VSC) is put forward. Compared to the traditional numerical variable-scale clustering method, the proposed T-VSC enables to combine the subjective attention of decision-makers and objective timeliness of public opinion data together during the scale transformation process. The case study collects 48552 raw public opinion data on the double-reduction education policy from Sina Weibo platform during Jan 2023 to Nov 2023. Experimental results indicate that the proposed T-VSC method could divide netizens that participate in the dissemination of policy-focused public opinion into clusters with low behavioural granularity deviation on the satisfied observation time scales, and identify the differentiated demand feature of each netizen cluster at policy time points, which could be applied to build the timely and efficient digital public dialogue mechanism.

Spatiotemporal analysis of seasonal trends in land surface temperature within the distribution range of Moringa peregrina (Forssk.) in Southern and Southeastern Iran.

Temperature fluctuations and related factors are among the main causes of climate change. Understanding the temporal and spatial variations in temperature can shed light on how species respond to climate change. Plants generally persist in suitable microclimates in response to environmental change; however, examining long-term temperature variations within a species' range can be challenging using field observations. Thermal remote sensing, on the other hand, provides multi-scale time-series data with good coverage and regularity to overcome the challenges associated with field observations in environmental monitoring. Although changes in land surface temperature (LST) affect climate, hydrological processes, land-atmosphere interactions, and ecological activities, this metric has not received much research attention. This study aimed to analyze changes in habitat suitability and microclimatic conditions for Moringa peregrina. Seasonal changes in LST within the distribution range of the species were also investigated. To this aim, mean seasonal LST was computed in Google Earth Engine using the daily MODIS/006/MYD13A2 product from 2003 to 2023. Subsequently, a binary habitat suitability map was created based on the true skill statistic (TSS). The Mann-Kendall test was used to analyze seasonal LST trends. Major trends in LST were quantified based on the z-score, and compatibility with habitat suitability was evaluated via GAP analysis and the Kappa index. Seasonal temperature trends were evaluated by comparing each season with the following season using binary comparison. Landforms at presence points were regarded as microclimates and the sensitivity of microclimates to LST was evaluated using two methods: Principal component analysis (PCA) was used to quantify seasonal LST heterogeneity and the random forest (RF) approach was used to evaluate the effect of environmental parameters on habitat suitability within microclimates. The Kappa index revealed a weak overlapping between suitable / unsuitable habitat and the surfaces affected by the trend of changes. Moreover, the suitable habitat of Moringa peregrina in spring, autumn and winter is spatially overlapped by areas that have shown an increasing LST trend, and the presence points have not experienced an increasing temperature trend only in the summer. The findings show that the analysis of seasonal trends in LST provides insights into the effect of LST on habitat suitability and the condition of vegetation. The current study clearly shows that seasonal changes have had a significant impact on the distribution and habitat suitability of M. peregrina, particularly during summer and winter. Improved habitat suitability and range expansion were observed throughout the year. The study also highlights the role of landforms in regulating temperature. Landforms such as local ridges with minimal temperature fluctuations and regions near the Oman Sea were identified as potential future habitats due to favorable humidity conditions.

A sustainable monitoring approach to manage complex archaeological sites – The example of Pompeii

The management of archaeological sites has always been a particularly complex issue, especially in the context of significant natural and man-made hazards. Among these, climate change is becoming increasingly significant. Over the past few decades, the analysis of the evolution of the condition of archaeological sites has revealed a trend of decay that is significantly influenced by extreme and/or rapid weather changes. While short-term solutions may not always be available to prevent disasters, proactive maintenance can help to control the impact caused by rapid changes and mitigate their extreme effects. Therefore, reliable knowledge and prediction of the evolution of decay are key to the design of a successful maintenance plan.In this context, an innovative approach to monitoring has been developed and applied in the Archaeological Park of Pompeii (Southern Italy). The methodology adopts both multi-scale (data and time resolution) and multi-level (assessment accuracy) approaches compatible with the master data and the information system already developed and implemented in the Park. This paper outlines the overall monitoring framework, which is structured on three assessment levels: Local (LA), General (GA) and Detailed (DA). Additionally, some application examples are also described.

APest-YOLO: A Multi-Scale Agricultural Pest Detection Model Based on Deep Learning

HighlightsWe propose a APest-YOLO model, an innovative agricultural pest detection model founded on a lightweight approach, thus improving the efficiency of pest detection while also reducing the model’s dimensions.The model incorporates a novel grouping atrous spatial pyramid pooling fast module with four convolution layers to enhance multi-scale pest feature representation, aiming for improved detection accuracy. Additionally, it utilizes a convolutional block attention module to reduce noise and complexity in background images, facilitating the extraction of more refined and smoother pest features for accurate detection.We conducted experiments on agricultural pest detection using a comprehensive multi-pest dataset. The APest-YOLO model surpasses existing detection models in terms of mAP0.5, mAP0.5:0.95.Abstract. Crop pests and diseases pose a significant threat to smart agriculture, making pest detection a critical component in agricultural applications. However, current detection methods often struggle to effectively identify multi-scale pest data. In response, we present a novel agricultural pest detection model (APest-YOLO) based on a lightweight approach. The APest-YOLO model enhances pest detection efficiency while reducing model size, which is different from the baseline models. Our model features an original grouping atrous spatial pyramid pooling fast module, comprising four convolution layers with varying rates to capture multi-scale and multi-level pest characteristics. Additionally, we incorporate a convolutional block attention module to extract smoother features from pest images with noisy and complex backgrounds. We evaluated the APest-YOLO model on a large-scale multi-pest dataset encompassing 37 pest species. Furthermore, the APest-YOLO model achieved 99.3% mAP0.5 and found that it outperforms baseline models, demonstrating effective pest species detection capabilities. Keywords: Attention mechanism, Convolutional neural network, Intelligent agriculture, Pest detection, YOLO.

Partitioning building groups at multiple scales based on image segmentation

The partitioning of building groups is a prerequisite for map generalization. Existing methods center on the spatial relationships between individual buildings, neglecting the interrelations among building groups. As such, these methods prove suitable only for identifying building groups at a single scale. In this research, we introduce a novel methodology for partitioning building groups across multiple scales by employing image segmentation, thus enabling the simultaneous recognition of building groups of all scales within a recognition unit. First, image segmentation and merging approaches were employed to extract merged image regions, representing the spatial relationships of building groups. Then, the process commenced with the construction of a graphical representation encompassing buildings and merged regions, wherein the edges were assigned weights indicative of the closeness between groups of buildings. Finally, the graph underwent a progressive segmentation process, and a scale set of building groups was established. Based on the experimental findings, the proposed approach can proficiently partition building groups across various scales. This is demonstrated by the accuracy rate surpassing 90% in the complex experimental area. One can effortlessly derive building groups from the scale set by using a predetermined scale parameter. These findings may serve as a fundamental basis for the implementation of multiscale map generalization and the linkage updating of multiscale spatial data.

ECW-EGNet: Exploring Cross-ModalWeighting and edge-guided decoder network for RGB-D salient object detection

Existing RGB-D salient object detection (SOD) techniques concentrate on combining data from multiple modalities (e.g., depth and RGB) and extracting multi-scale data for improved saliency reasoning. However, they frequently perform poorly as a factor of the drawbacks of low-quality depth maps and the lack of correlation between the extracted multi-scale data. In this paper, we propose a Exploring Cross-ModalWeighting and Edge-Guided Decoder Network (ECW-EGNet) for RGB-D SOD, which includes three prominent components. Firstly, we deploy a Cross-Modality Weighting Fusion (CMWF) module that utilizes Channel-Spatial Attention Feature Enhancement (CSAE) mechanism and Depth-Quality Assessment (DQA) mechanism to achieve the cross-modal feature interaction. The former parallels channel attention and spatial attention enhances the features of extracted RGB streams and depth streams while the latter assesses the depth-quality reduces the detrimental influence of the low-quality depth maps during the cross-modal fusion. Then, in order to effectively integrate multi-scale features for high-level and produce salient objects with precise locations, we construct a Bi-directional Scale- Correlation Convolution (BSCC) module in a bi-directional structure. Finally, we construct an Edge-Guided (EG) decoder that uses the edge detection operator to obtain edge masks to guide the enhancement of salient map edge details. The comprehensive experiments on five benchmark RGB-D SOD datasets demonstrate that the proposed ECW-EGNet outperforms 21 state-of-the-art (SOTA) saliency detectors in four widely used evaluation metrics.

Integrating multiscale data for digital twin-enhanced manufacturing systems: A conceptual and case demonstration

This paper explores the integration of data within digital twin-driven multiscale manufacturing systems, examining the core characteristics of data flows in digital twin (DT) environments tailored to manufacturing. In DT frameworks, data are inherently bidirectional, automated, and real-time, which are critical for maintaining the operational integrity of interconnected manufacturing subsystems. Different scales (from machine tool focus to supply chains) and timelines (from operations events to long term planning) make manufacturing system operation complex. This in turn means data integration across these scales and timelines is inherently complex. This study focuses on the dynamics of data flows in DT-driven manufacturing systems that support both forward and backward communication across DT modules and the central DT platform. The overall DT data scheme manages the supervision and cataloging of actions, which includes technical data related to machinery, processes, resources, and rules, alongside performance metrics across various scales and levels over time. A case study of a DT-driven manufacturing unit illustrates the data flow and interdependency in DT data framework. It highlights how data integration across multiple manufacturing stages can improve operational efficiency, fault diagnosis, and resource optimisation. This study lays the groundwork for the implementation of DT in complex, multiscale manufacturing systems by providing an extendible structured framework.

CL-Informer: Long time series prediction model based on continuous wavelet transform.

Time series, a type of data that measures how things change over time, remains challenging to predict. In order to improve the accuracy of time series prediction, a deep learning model CL-Informer is proposed. In the Informer model, an embedding layer based on continuous wavelet transform is added so that the model can capture the characteristics of multi-scale data, and the LSTM layer is used to capture the data dependency further and process the redundant information in continuous wavelet transform. To demonstrate the reliability of the proposed CL-Informer model, it is compared with mainstream forecasting models such as Informer, Informer+, and Reformer on five datasets. Experimental results demonstrate that the CL-Informer model achieves an average reduction of 30.64% in MSE across various univariate prediction horizons and a reduction of 10.70% in MSE across different multivariate prediction horizons, thereby improving the accuracy of Informer in long sequence prediction and enhancing the model's precision.

Quantifying the spatial water salinity threshold of saline water irrigation by applying distributed WAVES model

CONTEXTSaline water irrigation presents a viable solution to alleviate freshwater scarcity. However, it's crucial to consider the threshold of salinity, as excessive levels can adversely affect crop yield, crop productivity and soil sustainability. Additionally, due to varying surface conditions and management practices at the regional level, a distributed approach to saline water irrigation management is necessary. OBJECTIVEThe primary goal of this research was to develop a regional agro-hydrological crop model. The validated regional model was then employed to identify the spatial water salinity threshold for saline water irrigation. METHODSIn this research, we utilized the WAVES (WAter Vegetation Energy and Solute model), which was adapted for mulching environment and validated in severely arid and saline fields. To account for spatial variations, we applied a distributed method to upscale the WAVES to the regional level. Multisource and multiscale data were used for regional model validation. Different scenarios of salinity levels for saline water irrigation were simulated, and a comprehensive criterion to determine water salinity threshold was proposed considering cotton yield, water productivity and soil salt accumulation. RESULTS AND CONCLUSIONSModel evaluation indicated a high level of accuracy for the developed regional model. The comparison between simulated and measured values for soil salt content, soil water content, cotton leaf area index, measured lint yield, and statistical yield resulted in indices of agreement of 0.90, 0.71, 0.93, 0.58, and 0.70, respectively. The validated regional model was employed to simulate various saline water irrigation scenarios. The findings revealed that under identical irrigation water salinity, cotton cultivation on sandy loam soil is more productive but has a larger yield reduction percentage compared to silty loam soil. Moreover, the research indicates a groundwater depth of 1.5 m is associated with higher cotton production. Additionally, a spatial pattern of the irrigation water salinity threshold for saline water irrigation was determined, suggesting that the water salinity in most areas of the Tarim Irrigation District should not exceed 6 g L−1. Notably, in the current practice of pumping groundwater in situ for irrigation, approximately 46% of the areas are at risk, indicating that it's not suitable for saline water irrigation. SIGNIFICANCEThis study developed a distributed model under a typical irrigation district characterized by mulching, severe drought and salinization and defined the distributed spatial threshold for saline water irrigation. These research results hold significant implications for guiding regional-scale saline water irrigation and groundwater extraction.

A Seismic Inversion Method Based on Multi-Scale Super-Asymmetric Cycle-JNet Network

In order to improve the resolution and accuracy of seismic inversion, this study constructs a multi-scale super-asymmetric network (Cycle-JNet). In this model, wavelet analysis is used to capture the multi-scale data characteristics of well-seismic data, thereby improving the machine’s ability to learn details. Using the UNet neural network from Convolutional Neural Network (CNN), we modified the network structure by adding several convolution kernel layers at the output end to expand generated data, solving the problem of mismatched resolutions in well-seismic data, thus improving the resolution of seismic inversion and achieving the purpose of accurately identifying thin sandstone layers. Meanwhile, a cycle structure of Recurrent Neural Network (RNN) was designed for the secondary learning of the seismic data generated by JNet. By comparing the data transformed through inverse wavelet transform with the original data again, the accuracy of machine learning can be improved. After optimization, the Cycle-JNet model significantly outperforms traditional seismic inversion methods in terms of resolution and accuracy. This indicates that this method can provide more precise inversion results in more complex data environments, providing stronger support for seismic analysis.

Graph neural network-based identification of ditch matching patterns across multi-scale geospatial data

Ditches are vital to water system data. To ease the task of matching multi-scale ditch data and enhance accuracy (Acc), it is essential to discern ditch data matching patterns. Despite its importance, limited research has been conducted on ditch matching patterns, and the primary reasons for variations in multi-scale geographical entities’ matching patterns remain underexplored. Here, we introduce a supervised graph neural network (GNN) method, targeting the direct analysis of 1:10,000 ditch characteristics to identify the matching patterns between 1:10,000 and 1:25,000 datasets. The ditch network is depicted as a graph structure, with nodes representing ditch segments and edges indicating their connections. Subsequently, each ditch segment’s geometric, semantic, and topological attributes are computed as node attributes, and their matching patterns with the 1:25,000 dataset are labeled as node annotations. Ditch segment matching patterns are then categorized using supervised learning. Experiments using Overijssel, Netherlands’ ditch data reveal that this method achieves a 97.3% classification Acc, outperforming other GNN methods by 25.6–26.3% and traditional machine learning methods by 33%. These findings underscore the efficacy and superiority of the proposed supervised GNN approach in pinpointing ditch matching patterns.

First Observation of Kinetic Alfvén Waves behind Reconnection Front in Terrestrial Magnetotail

Reconnection fronts, also known as dipolarization fronts (DFs), and kinetic Alfvén waves (KAWs) are two of the widely observed structures and waves in the terrestrial magnetotail, but their correlation remains elusive in previous spacecraft measurements. Using high-resolution Magnetospheric Multiscale data, here we provide the first observational identification of KAWs behind the DF. These low-frequency dispersive KAWs propagate quasi-perpendicular to the magnetic field at phase speeds slower than local Alfvén speed, and are highly correlated with high-frequency whistlers propagating obliquely to the magnetic field. Specifically, whistlers appear at local magnetic field minima (wave troughs of KAWs) and disappear at local magnetic field maxima (wave crests of KAWs), highly consistent with the source region of whistler waves previously reported near equator and dayside magnetopause. Our study also suggests that the KAWs behind DFs could originate from the diffusion region of magnetic reconnection. These findings improve our understanding of the relationship between DFs, KAWs, and whistler waves in terrestrial magnetotail.