e Knowledge graph (KG) uses the triples to describe the facts in the real world. It has been widely used in intelligent analysis and applications. However, possible noises and con icts are inevitably introduced in the process of constructing. And the KG based tasks or applications assume that the knowledge in the KG is completely correct and inevitably bring about potential deviations. In this paper, we establish a knowledge graph triple trustworthiness measurement model that quantify their semantic correctness and the true degree of the facts expressed. e model is a crisscrossing neural network structure. It synthesizes the internal semantic information in the triples and the global inference information of the KG to achieve the trustworthiness measurement and fusion in the three levels of entity level, relationship level, and KG global level. We analyzed the validity of the model output con dence values, and conducted experiments in the real-world dataset FB15K (from Freebase) for the knowledge graph error detection task. e experimental results showed that compared with other models, our model achieved signi cant and consistent improvements.
Shale
gas has become one of the primary energy resources during
the past few years, and its impact has been profound in many countries.
Hydraulic fracturing treatments are required for the development of
shale gas reservoirs, and the consequent hydraulic fractures usually
connect with the original small-scale natural fractures forming complex
fracture networks in these reservoirs. Therefore, a model for numerical
simulation, which is capable of accurately modeling naturally and
hydraulically fractured reservoirs, is essential in optimization and
management of such reservoirs. In this paper, we develop a comprehensive
model that couples embedded discrete fractures, multiple interacting
continua, and geomechanics to accurately simulate the fluid flow in
shale gas reservoirs with multiscale fractures. Large-scale hydraulic
fractures are described by an embedded discrete fracture method, while
middle-scale and small-scale natural fractures are modeled by a multiple
interacting continua method. Usually, the connection of matrix–natural
fractures–hydraulic fractures–wells is considered as
the main pathway for the gas flow from a reservoir to a production
well. However, geomechanics effects are significant in fractured reservoirs,
which may lead to the closure of fractures and a dramatic decrease
in gas conductivity in the fractures during the depletion of pressure.
When the permeability of fractures is close to that of matrix, the
gas production directly from the pathway of matrix–hydraulic
fractures–wells as well as the fluid flow in shale matrix cannot
be ignored. To accurately predict the fluid flow and well performance,
the geomechanics effects and all the possible connections between
different regimes must be taken into account. We implement this comprehensive
model in our in-house reservoir simulator and study its behavior by
numerical experiments. According to the numerical simulation results,
accurate and comprehensive production prediction is performed, and
reasonable physical phenomena is captured. Sensitivity studies are
also performed to show the impacts of different parameters on the
prediction of well performance.
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL). However, existing GANs in SSL have two problems: (1) the generator and the discriminator (i.e. the classifier) may not be optimal at the same time; and (2) the generator cannot control the semantics of the generated samples. The problems essentially arise from the two-player formulation, where a single discriminator shares incompatible roles of identifying fake samples and predicting labels and it only estimates the data without considering the labels. To address the problems, we present triple generative adversarial net (Triple-GAN), which consists of three players-a generator, a discriminator and a classifier. The generator and the classifier characterize the conditional distributions between images and labels, and the discriminator solely focuses on identifying fake image-label pairs. We design compatible utilities to ensure that the distributions characterized by the classifier and the generator both converge to the data distribution. Our results on various datasets demonstrate that Triple-GAN as a unified model can simultaneously (1) achieve the state-of-the-art classification results among deep generative models, and (2) disentangle the classes and styles of the input and transfer smoothly in the data space via interpolation in the latent space class-conditionally.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.