检索结果-内蒙古大学图书馆

DeepSSN: a deep convolutional neural network to assess spatial scene similarity

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Danhuai Ge, Shiyin Zhang, Shu Gao, Song Tao, Ran Wang, Yangang Spatio-Temporal Data Intelligence Lab College of Information Science and Technology Beijing University of Chemical Technology Beijing China Computer Network Information Center Chinese Academy of Sciences Beijing China Geospatial Data Science Lab Department of Geography University of Wisconsin-Madison WI United States School of Geosciences University of South Florida FL United States

Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries. However, traditional sketch-based spatial search methods perform insufficiently due to their inability to find hidden multi-scale map features from mental sketches. In this research, we propose a deep convolutional neural network, namely Deep Spatial Scene Network (DeepSSN), to better assess the spatial scene similarity. In DeepSSN, a triplet loss function is designed as a comprehensive distance metric to support the similarity assessment. A positive and negative example mining strategy using qualitative constraint networks in spatial reasoning is designed to ensure a consistently increasing distinction of triplets during the training process. Moreover, we develop a prototype spatial scene search system using the proposed DeepSSN, in which the users input spatial query via sketch maps and the system can automatically augment the sketch training data. The proposed model is validated using multi-source conflated map data including 131,300 labeled scene samples after data augmentation. The empirical results demonstrate that the DeepSSN outperforms baseline methods including k-nearest-neighbors, multilayer perceptron, AlexNet, DenseNet, and ResNet using mean reciprocal rank and precision metrics. This research advances geographic information retrieval studies by introducing a novel deep learning method tailored to spatial scene queries. © 2022, CC BY-NC-SA.

关键词： Deep neural networks

Late Mesozoic Tectonic Transfer in the Southern Great Xing'An Range, Ne China: Evidence from Geochronology, Geochemistry and Lu-Hf Isotopes of Magmatic Intrusions in Inner Mongolia

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhao, Zhixiong Dong, Guochen Santosh, M. Bao, Xiangping Ren, Yingwei Xie, Zhuolin School of Earth Science and Mineral Resources China University of Geosciences Beijing100083 China Ulanqab Key Laboratory of Geospatial Big Data Application and Environmental Monitoring Jining Normal University Ulanqab012000 China Department of Earth Science University of Adelaide Adelaide5005 Australia Yonsei Frontier Lab Yonsei University Seoul Korea Republic of

The geodynamic background of the Mesozoic magmatism in the Jarud region of Inner Mongolia remains debated. Here we present zircon U-Pb geochronology, geochemistry and Hf isotope data on the Late Jurassic diorite and Early Cretaceous quartz monzonite porphyry and granite porphyry from the Jarud area to constrain the petrogenesis and tectonic setting. Zircon U-Pb data suggest that the multiphase magmatism extended from the Late Jurassic to Early Cretaceous, i.e., 161.0 ± 1.0 Ma (diorite), 129.9 ± 1.4 Ma (quartz monzonite porphyry), and 125.8 ± 1.1 Ma and 126.8 ± 1.1 Ma (granite porphyry). These rocks are characterized by enrichment of light rare earth and large ion lithophile elements. Based on the geochemistry and Hf isotope data, the diorite with elevated crystallization temperatures (1061 to 1098 ℃), and moderate logfO2 (-22.80 to -7.53) is inferred to have formed by low degree partial melting of depleted mantle wedge metasomatized by fluids at a relatively shallow depth. The quartz monzonite porphyry with moderate crystallization temperatures (755 to 839 °C) and high logfO2 (-18.35 to -9.53) was generated by partial melting of lower crust triggered by depleted mantle-derived basaltic magma underplating, subsequent experienced the fractional crystallization of olivine, pyroxene, Fe-Ti oxides and apatite. The granite porphyry with low crystallization temperatures (643 to 821 °C) and logfO2 (-27.59 to -12.40), is classified as S-type granites, and was sourced from greywacke. The results presented in this study indicate that the Late Jurassic magmatism was related to the southward subduction of the Mongol- Okhotsk Ocean, while the Early Cretaceous magmatic rocks were formed in a post-collision extensional setting. © 2023, The Authors. All rights reserved.

关键词： Quartz

Context-aware knowledge graph framework for traffic speed forecasting using graph neural network

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yatao Wang, Yi Gao, Song Raubal, Martin Future Resilient Systems Singapore-ETH Centre ETH Zurich Singapore138602 Singapore Institute of Cartography and Geoinformation ETH Zurich Zurich8093 Switzerland Civil and Natural Resources Engineering Department University of Canterbury Christchurch8041 New Zealand Geospatial Data Science Lab Department of Geography University of Wisconsin-Madison MadisonWI53706 United States

Human mobility is intricately influenced by urban contexts spatially and temporally, constituting essential domain knowledge in understanding traffic systems. While existing traffic forecasting models primarily rely on raw traffic data and advanced deep learning techniques, incorporating contextual information remains underexplored due to insufficient integration frameworks and the complexity of urban contexts. This study proposes a novel context-aware knowledge graph (CKG) framework to enhance traffic speed forecasting by effectively modeling spatial and temporal contexts. Employing a relation-dependent integration strategy, the framework generates context-aware representations from the spatial and temporal units of CKG to capture spatiotemporal dependencies of urban contexts. A CKG-GNN model, combining the CKG, dual-view multi-head self-attention (MHSA), and graph neural network (GNN), is then designed to predict traffic speed utilizing these context-aware representations. Our experiments demonstrate that CKG’s configuration significantly influences embedding performance, with ComplEx and KG2E emerging as optimal for embedding spatial and temporal units, respectively. The CKG-GNN model establishes a benchmark for 10-120 min predictions, achieving average MAE, MAPE, and RMSE of 3.46±0.01, 14.76±0.09%, and 5.08±0.01, respectively. Compared to the baseline DCRNN model, integrating the spatial unit improves the MAE by 0.04 and the temporal unit by 0.13, while integrating both units further reduces it by 0.18. The dual-view MHSA analysis reveals the crucial role of relation-dependent features from the context-based view and the model’s ability to prioritize recent time slots in prediction from the sequence-based view. Overall, this study underscores the importance of merging context-aware knowledge graphs with graph neural networks to improve traffic forecasting. © 2024, CC BY-NC-SA.

关键词： Knowledge graph

FLEE-GNN: A Federated Learning System for Edge-Enhanced Graph Neural Network in Analyzing geospatial Resilience of Multicommodity Food Flows

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qu, Yuxiao Rao, Jinmeng Gao, Song Zhang, Qianheng Chao, Wei-Lun Su, Yu Miller, Michelle Morales, Alfonso Huber, Patrick R. Department of Computer Science Carnegie Mellon University United States Geospatial Data Science lab University of Wisconsin Madison United States Department of Computer Science and Engineering Ohio State University United States Center for Integrated Agricultural Systems University of Wisconsin Madison United States Department of Planning and Landscape Architecture University of Wisconsin Madison United States Institute of the Environment University of California Davis United States

Understanding and measuring the resilience of food supply networks is a global imperative to tackle increasing food insecurity. However, the complexity of these networks, with their multidimensional interactions and decisions, presents significant challenges. This paper proposes FLEE-GNN, a novel Federated Learning System for Edge-Enhanced Graph Neural Network, designed to overcome these challenges and enhance the analysis of geospatial resilience of multicommodity food flow network, which is one type of spatial networks. FLEE-GNN addresses the limitations of current methodologies, such as entropy-based methods, in terms of generalizability, scalability, and data privacy. It combines the robustness and adaptability of graph neural networks with the privacy-conscious and decentralized aspects of federated learning on food supply network resilience analysis across geographical regions. This paper also discusses FLEE-GNN’s innovative data generation techniques, experimental designs, and future directions for improvement. The results show the advancements of this approach to quantifying the resilience of multicommodity food flow networks, contributing to efforts towards ensuring global food security using AI methods. The developed FLEE-GNN has the potential to be applied in other spatial networks with spatially heterogeneous sub-network distributions. © 2023, CC BY.

关键词： Geographical regions

Measuring Network Resilience via geospatial Knowledge Graph: a Case Study of the US Multi-Commodity Flow Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rao, Jinmeng Gao, Song Miller, Michelle Morales, Alfonso Geospatial Data Science Lab University of Wisconsin-Madison Madison United States Center for Integrated Agricultural Systems University of Wisconsin-Madison Madison United States Department of Planning and Landscape Architecture University of Wisconsin-Madison Madison United States

Quantifying the resilience in the food system is important for food security issues. In this work, we present a geospatial knowledge graph (GeoKG)-based method for measuring the resilience of a multi-commodity flow network. Specifically, we develop a CFS-GeoKG ontology to describe geospatial semantics of a multi-commodity flow network comprehensively, and design resilience metrics that measure the node-level and network-level dependence of single-sourcing, distant, or non-adjacent suppliers/customers in food supply chains. We conduct a case study of the US state-level agricultural multi-commodity flow network with hierarchical commodity types. The results indicate that, by leveraging GeoKG, our method supports measuring both node-level and network-level resilience across space and over time and also helps discover concentration patterns of agricultural resources in the spatial network at different geographic scales. © 2022, CC BY.

关键词： Semantics

On the Opportunities and Challenges of Foundation Models for geospatial Artificial Intelligence

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mai, Gengchen Huang, Weiming Sun, Jin Song, Suhang Mishra, Deepak Liu, Ninghao Gao, Song Liu, Tianming Cong, Gao Hu, Yingjie Cundy, Chris Li, Ziyuan Zhu, Rui Lao, Ni SEAI Lab Department of Geography University of Georgia United States School of Computer Science and Engineering Nanyang Technological University Singapore School of Computing University of Georgia United States College of Public Health University of Georgia United States Department of Geography University of Georgia United States Geospatial Data Science Lab Department of Geography University of Wisconsin-Madison United States GeoAI Lab Department of Geography University at Buffalo United States Department of Computer Science Stanford University United States School of Business University of Connecticut United States School of Geographical Sciences University of Bristol United Kingdom Google United States

Large pre-trained models, also known as foundation models (FMs), are trained in a task-agnostic manner on large-scale data and can be adapted to a wide range of downstream tasks by fine-tuning, few-shot, or even zero-shot learning. Despite their successes in language and vision tasks, we have yet seen an attempt to develop foundation models for geospatial artificial intelligence (GeoAI). In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI. We first investigate the potential of many existing FMs by testing their performances on seven tasks across multiple geospatial subdomains including geospatial Semantics, Health Geography, Urban Geography, and Remote Sensing. Our results indicate that on several geospatial tasks that only involve text modality such as toponym recognition, location description recognition, and US state-level/county-level dementia time series forecasting, these task-agnostic LLMs can outperform task-specific fully-supervised models in a zero-shot or few-shot learning setting. However, on other geospatial tasks, especially tasks that involve multiple data modalities (e.g., POI-based urban function classification, street view image-based urban noise intensity classification, and remote sensing image scene classification), existing foundation models still underperform task-specific models. Based on these observations, we propose that one of the major challenges of developing a FM for GeoAI is to address the multimodality nature of geospatial tasks. After discussing the distinct challenges of each geospatial data modality, we suggest the possibility of a multimodal foundation model which can reason over various types of geospatial data through geospatial alignments. We conclude this paper by discussing the unique risks and challenges to develop such a model for GeoAI. © 2023, CC0.

关键词： Semantics

Spatio-Temporal Stratified Associations between Urban Human Activities and Crime Patterns: A Case Study in San Francisco Around the Covid-19 Stay-at-Home Mandate

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Chen, Tongxin Bowers, Kate Zhu, Di Gao, Xiaowei Cheng, Tao Space Time Lab for Big Data Analytics Department of Civil Environmental and Geomatic Engineering University College London LondonWC1E 6BT United Kingdom Department of Security and Crime Science University College London LondonWC1H 9EZ United Kingdom Geospatial Data Intelligence Lab Department of Geography Environment and Society University of Minnesota Twin Cities Minneapolis55455 United States

Crime changes have been reported as a result of human routine activity shifting due to containment policies, such as stay-at-home (SAH) mandates during the COVID-19 pandemic. However, the way in which the manifestation of crime in both space and time is affected by dynamic human activities in urban areas has not been explored in depth in empirical studies hitherto. Here, we aim to quantitatively measure the spatio-temporal associations between crime patterns and human activities in the context of an unstable period of the ever-changing socio-demographic backcloth. We propose an analytical framework to detect the dynamic stratified associations between the spatial distributions of human activities and crimes. The results of a case study in San Francisco, United States reveal that the spatial patterns of most crime types are statistically significantly associated with that of human activities zones. Property crime exhibits higher stratified association than violent crime across all temporal scales. Further, the strongest association is obtained with the eight-week time span centered around the SAH order. These findings not only enhance our understanding of the relationships between urban crime and human activities, but also offer insights that tailored crime intervention strategies need to consider human activity variables. © 2022, The Authors. All rights reserved.

关键词： Crime

A gravity-inspired model integrating geospatial and socioeconomic distances for truck origin–destination flows prediction

学校读者我要写书评

暂无评论

International Journal of Applied Earth Observation and Geoinformation 2025年 136卷

作者： Zhao, Yibo Cheng, Shifen Gao, Song Lu, Feng State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research CAS Beijing 100101 China University of Chinese Academy of Sciences Beijing 100049 China Geospatial Data Science Lab Department of Geography University of Wisconsin-Madison Madison 53706 WI United States The Academy of Digital China Fuzhou University Fuzhou 350002 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023 China

Accurately predicting truck origin–destination (OD) flows is essential for optimizing logistics systems and promoting coordinated regional development. Existing methods typically assume a monotonic decrease in truck OD flows with increasing geospatial distance, which oversimplifies the complex non-monotonic distribution patterns observed in practice. Moreover, these methods overlook interregional socioeconomic distances and their interaction with geospatial distances, thereby limiting the prediction accuracy and reliability. This study introduces a gravity-inspired model that integrates both geospatial and socioeconomic distances (GSD-DG) to explicitly represent their combined influence on truck OD flows. Specifically, we 1) develop a geospatial distance relation graph using the Weibull function to model the complex spatial distribution patterns of truck OD flows with varying geospatial distances;2) propose a gravity-inspired representation learning method based on graph attention mechanism to quantify the influence of socioeconomic distance on truck OD flows;and 3) construct a deep gravity model that integrates these distances and their interactions to capture their non-linear relationship with truck OD flows. Extensive experiments on four datasets with varying spatial scale and economic development levels demonstrate that the GSD-DG model improves the robustness and prediction accuracy across diverse spatial distribution patterns, reducing RMSE by 14.2%–85.8% and MSE by 23.5%–92.5% compared to the six baseline models. Incorporating socioeconomic distance and its interaction with geospatial distance further reduces RMSE by 8.5%–36.0%. Additionally, explainable artificial intelligence techniques highlight how these distances affect truck OD flows, providing valuable policy insights for logistics planning and coordinated regional development. © 2024 The Authors

关键词： geospatial distance Gravity-inspired model Heavy trucks Origin–destination flows Socioeconomic distance Spatial interaction

Cross-City Matters: A Multimodal Remote Sensing Benchmark dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hong, Danfeng Zhang, Bing Li, Hao Li, Yuxuan Yao, Jing Li, Chenyu Werner, Martin Chanussot, Jocelyn Zipf, Alexander Zhu, Xiao Xiang Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China College of Resources and Environment University of Chinese Academy of Sciences Beijing100049 China Big Geospatial Data Management Technical University of Munich Munich85521 Germany School of Mathematics Southeast University Nanjing210096 China Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab Grenoble38000 France GIScience Chair Institute of Geography Heidelberg University Heidelberg69120 Germany Data Science in Earth Observation Technical University of Munich Munich80333 Germany

Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e.g., single cities or regions). Yet these AI models tend to meet the performance bottleneck in the case studies across cities or regions, due to the lack of diverse RS information and cutting-edge solutions with high generalization ability. To this end, we build a new set of multimodal remote sensing benchmark datasets (including hyperspectral, multispectral, SAR) for the study purpose of the cross-city semantic segmentation task (called C2Seg dataset), which consists of two cross-city scenes, i.e., Berlin-Augsburg (in Germany) and Beijing-Wuhan (in China). Beyond the single city, we propose a high-resolution domain adaptation network, HighDAN for short, to promote the AI model’s generalization ability from the multi-city environments. HighDAN is capable of retaining the spatially topological structure of the studied urban scene well in a parallel high-to-low resolution fusion fashion but also closing the gap derived from enormous differences of RS image representations between different cities by means of adversarial learning. In addition, the Dice loss is considered in HighDAN to alleviate the class imbalance issue caused by factors across cities. Extensive experiments conducted on the C2Seg dataset show the superiority of our HighDAN in terms of segmentation performance and generalization ability, compared to state-of-the-art competitors. The C2Seg dataset and the semantic segmentation toolbox (involving the proposed HighDAN) will be available publicly at https://***/danfenghong. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing