Xin Ju

Projection-based low-dimensional parameterization method for three-dimensional discrete fracture networks through generative adversarial network

Zheng Teng, Hui Wu, Kezhan Zhang, J Junyi Zhang et autres

Fracture network characterization is an important yet intractable task in many subsurface applications related to energy recovery, storage, and waste disposal. A major challenge is the lack of advanced methods for parameterizing complex fracture networks within low-dimensional parameter spaces to address the …

cn, hk, us (code pays fourni par la source)

Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage

Xin Ju, Jiachen Yao, Anima Anandkumar, Sally M. Benson et autres

Accurate characterization of subsurface flow is critical for Carbon Capture and Storage (CCS) but remains challenged by the ill-posed nature of inverse problems with sparse observations. We present Function-space Decoupled Diffusion Posterior Sampling (Fun-DDPS), a generative framework that combines function-space diffusion models …

Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage

Xin Ju, Jiachen Yao, Anima Anandkumar, Sally M. Benson et autres

Accurate characterization of subsurface flow is critical for Carbon Capture and Storage (CCS) but remains challenged by the ill-posed nature of inverse problems with sparse observations. We present Function-space Decoupled Diffusion Posterior Sampling (Fun-DDPS), a generative framework that combines function-space diffusion models …

Distribution and evolution of distress in embankment-bridge transition sections of the Gonghe–Yushu Expressway in degrading permafrost regions

Bingyan Li, Liang Zhang, Yanhu Mu, Jing Luo et autres

cn (code pays fourni par la source)

Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction

Mingda Jia, Weiliang Meng, Zheng Qing Fu, Yiheng Li et autres

Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi-task architectures to achieve competitive performance. However, these pipelines rely on implicit modeling that uses frame-level or fragmented video …

Generating high-fidelity discrete fracture networks from low-dimensional latent spaces using generative adversarial network

Zheng Teng, Hui Wu, Jize Zhang, Xin Ju et autres

Characterization of discrete fracture networks (DFNs) in the shallow crust is essential for understanding subsurface flow and transport processes and guiding reservoir exploitation such as water/oil/gas/geothermal/mineral recovery and nuclear waste/CO 2 storage. However, characterizing the geometry of subsurface DFNs is extremely difficult, …

cn, hk, us (code pays fourni par la source)

Prediction of sandstone freeze-thaw damage in the Changdu of the Qinghai-Tibet plateau based on CT radiomics method

Xin Ju, Fujun Niu, Minghao Liu, Lu Ren et autres

cn (code pays fourni par la source)

Temperature-Dependent Mechanical Characteristics of Frozen Sandstone: Experiments and Multi-scale Constitutive Model

Lu Ren, Fujun Niu, Tannong Chen, Jianwei Xiao et autres

cn, sg (code pays fourni par la source)

Enhancing Los Angeles’ resilient energy systems amid wildfires

Alexis Pengfei Zhao, Mohannad Alhazmi, Shuangqi Li, Jiarong Li et autres

Wildfires pose a significant threat to urban regions, with cities like Los Angeles facing increasing challenges due to their vulnerability to frequent and severe wildfire events. This study proposes a novel framework for optimizing fire rescue vehicle scheduling and energy system operations …

us, sa, hk, cn (code pays fourni par la source)

Learning From Each Other: Exploring A Novel Mutual Learning Paradigm for Enhancing Code Generation Performance

Xin Ju, Ye Zhang, Xiabing Zhou, Min Zhang

Large language model progress drives code generation research. Most works enhance performance via problem decomposition and knowledge distillation. However, they predominantly adopt a unidirectional approach to knowledge learning. Inspired by the mutually beneficial learning patterns observed in humans, this paper explores a …

cn (code pays fourni par la source)

Enhancing Los Angeles’ Resilient Energy Systems Amid Wildfires

Pengfei Zhao, Mohannad Alhazmi, Shuangqi Li, Jiarong Li et autres

us, sa, hk, cn (code pays fourni par la source)

Enhancing resilience in Los Angeles energy systems

Pengfei Zhao, Chenghong Gu, Shuangqi Li, Xin Ju et autres

Wildfires, exacerbated by climate change, pose significant challenges to the resilience and operational stability of energy systems, particularly in regions like Los Angeles (LA). These extreme events disrupt critical infrastructure, hinder renewable energy generation, and amplify uncertainties in energy supply and demand. …

us, gb, hk, sa (code pays fourni par la source)