SE‐KGE: A location‐aware Knowledge Graph Embedding model for Geographic Question Answering and Spatial Semantic Lifting     

Gengchen Mai  Krzysztof Janowicz  Ling Cai  Rui Zhu  Blake Regalia  Bo Yan  Meilin Shi  Ni Lao 《Transactions in GIS》2020,24(3):623-655

Learning knowledge graph (KG) embeddings is an emerging technique for a variety of downstream tasks such as summarization, link prediction, information retrieval, and question answering. However, most existing KG embedding models neglect space and, therefore, do not perform well when applied to (geo)spatial data and tasks. Most models that do consider space primarily rely on some notions of distance. These models suffer from higher computational complexity during training while still losing information beyond the relative distance between entities. In this work, we propose a location‐aware KG embedding model called SE‐KGE. It directly encodes spatial information such as point coordinates or bounding boxes of geographic entities into the KG embedding space. The resulting model is capable of handling different types of spatial reasoning. We also construct a geographic knowledge graph as well as a set of geographic query–answer pairs called DBGeo to evaluate the performance of SE‐KGE in comparison to multiple baselines. Evaluation results show that SE‐KGE outperforms these baselines on the DBGeo data set for the geographic logic query answering task. This demonstrates the effectiveness of our spatially‐explicit model and the importance of considering the scale of different geographic entities. Finally, we introduce a novel downstream task called spatial semantic lifting which links an arbitrary location in the study area to entities in the KG via some relations. Evaluation on DBGeo shows that our model outperforms the baseline by a substantial margin.  相似文献   

Review of Image Quality Measures for Solar Imaging     

Adam Popowicz  Krystian Radlak  Krzysztof Bernacki  Valeri Orlov 《Solar physics》2017,292(12):187

Observations of the solar photosphere from the ground encounter significant problems caused by Earth’s turbulent atmosphere. Before image reconstruction techniques can be applied, the frames obtained in the most favorable atmospheric conditions (the so-called lucky frames) have to be carefully selected. However, estimating the quality of images containing complex photospheric structures is not a trivial task, and the standard routines applied in nighttime lucky imaging observations are not applicable. In this paper we evaluate 36 methods dedicated to the assessment of image quality, which were presented in the literature over the past 40 years. We compare their effectiveness on simulated solar observations of both active regions and granulation patches, using reference data obtained by the Solar Optical Telescope on the Hinode satellite. To create images that are affected by a known degree of atmospheric degradation, we employed the random wave vector method, which faithfully models all the seeing characteristics. The results provide useful information about the method performances, depending on the average seeing conditions expressed by the ratio of the telescope’s aperture to the Fried parameter, \(D/r_{0}\). The comparison identifies three methods for consideration by observers: Helmli and Scherer’s mean, the median filter gradient similarity, and the discrete cosine transform energy ratio. While the first method requires less computational effort and can be used effectively in virtually any atmospheric conditions, the second method shows its superiority at good seeing (\(D/r_{0}<4\)). The third method should mainly be considered for the post-processing of strongly blurred images.  相似文献   

Site formation processes in loess areas: A case study from moravany-žakovska,western slovakia     

Ladislav Bnesz  Josef Hromada  Janusz Kozlowski  Krzysztof Sobczyk  Maciej Pawlikowski 《Geoarchaeology》1995,10(4):237-255

The site of Moravany-Žakovska in western Slovakia is situated in a loessic terrain and is dated to the end of the Late Glacial Maximum. This article shows the importance of analyzing the 0.01-0.1 mm fraction to interpret the sedimentological environment and a number of measured anthropogenic indices, such as burnt quartz grains, charcoal, radiolarite chips, microflakes, and microfragments of bone. Analysis of the profile of the site through time reveals the relationship between occupational levels and phases of slope wash that occurred during wetter climatic episodes; these are separated by phases of aeolian sedimentation. At the same time, analysis of anthropogenic indices in this size fraction permitted the identification of occupational levels, including those not recorded by macrofinds. Analysis of anthropogenic indices in horizontal exposures enabled the identification of latent settlement structures such as hearths, areas of radiolarite processing, zones where mineral dyes were prepared, and other structures not recorded by macrofinds.  相似文献   

Balanced cross-section restoration in a complicated folded hinterland structure: Shilbilisaj profile,Talas ridge,Caledonian Tien Shan     

Fedor Yakovlev  Krzysztof Gaidzik  Viacheslav Voytenko  Natalia Frolova 《地学学报》2023,35(1):1-14

Conventional cross-section balancing techniques based on layer length measuring can be applied only for foreland structures. To analyse complicated hinterland structure with numerous small-scale folds, this balancing technique requires the reliable and detailed tracing of the morphology of any layer throughout the cross-section, which is unattainable. We present a special kinematic method of balancing cross sections based “on the geometry of the folded domain” which enables the structural restoration of hinterland regions. We apply the method to restore the detailed structural section along the Shilbilisaj River, having a length of 26 km. We divided this section into 40–60 so-called “domains” each including 2–7 folds. Our method uses the fold's morphology to determine the strain ellipsoid, which describes the deformation of each domain and is used to restore its pre-folded state. By combining the pre-folded states of the domains, we reconstruct the entire profile, and calculate shortening values as K = L₀/L₁ (initial to final length). The overall shortening value for the profile is 4.49, incrementally varying along the section from 3.79 to 5.53. The comparable results of two independently performed reconstructions emphasize the reliability of the applied balancing method.  相似文献