Xin Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xin Luo has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Peng Chi
School of Geosciences, China University of Petroleum (East China), Qingdao 266580, China
6 shared publications - Jianmeng Sun
School of Geosciences, China University of Petroleum (East China), Qingdao 266580, China
5 shared publications Ruikang Cui
3 shared publications- Gang Liu
Shandong Provincial Key Laboratory of Oil, Gas and New Energy Storage and Transportation Safety, China University of Petroleum (East China), Qingdao, Shandong, China
2 shared publications Jianmeng Sun
2 shared publicationsJiaxing Zou
Shandong Provincial Key Laboratory of Oil, Gas and New Energy Storage and Transportation Safety, China University of Petroleum (East China), Qingdao, Shandong, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- p. 1-13
Temperature Interface in Long-Distance Batch Pipelines: A Numerical Method for Suppressing Numerical Dissipation Combining Method of Characteristics and Akima Interpolation
Summary: During the sequential transportation of hot and cold fluids in long-distance pipelines, convective transport dominates the temperature evolution of the pipe fluid. Accurate numerical simulation provides crucial support for engineering operation and scheduling. Aiming at the severe numerical dissipation and resultant nonphysical broadening of temperature interfaces in the commercial software Stoner Pipeline Simulator (SPS) and the traditional method of characteristics (MOC) with linear interpolation (MOC-Linear), we propose a numerical computational framework that integrates the MOC with locally adaptive piecewise Akima interpolation. The framework discretizes the computational grid based on a characteristic velocity of 2.5 m/s, ensuring the Courant-Friedrichs-Lewy (CFL) number stays strictly below unity to satisfy the numerical stability criterion. Two typical operating conditions are designed for method validation: first, a step fluctuation of flow velocity (1.5 m/s→1.0 m/s) under a constant temperature field, for verifying numerical stability; second, a step change of temperature (45°C→35°C) under a constant flow velocity field, for evaluating antidissipation performance. An additional temperature step condition for large-diameter water transportation is included to verify the general applicability of the method across different fluid media and pipe diameters. The results show that under the flow velocity fluctuation condition, the temperature results from SPS, MOC-Linear, and MOC-Akima are fully consistent with no spurious oscillations, verifying the robustness of the proposed framework for smooth temperature fields. Under the temperature step condition, MOC-Akima effectively suppresses numerical dissipation: After 20 hours of simulation, the interface width is narrowed by approximately 70% compared with the 12.0 km yielded by MOC-Linear and by more than 90% compared with the 38.0 km yielded by SPS. Furthermore, MOC-Akima is insensitive to timestep variations and maintains a sharp temperature interface even with a relatively large timestep, striking a favorable balance between computational cost and accuracy. This numerical framework provides a reliable solution for temperature interface tracking in long-distance sequential transportation pipelines.
- 1 October 2026
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- p. 1-13
Temperature Interface in Long-Distance Batch Pipelines: A Numerical Method for Suppressing Numerical Dissipation Combining Method of Characteristics and Akima Interpolation
Summary: During the sequential transportation of hot and cold fluids in long-distance pipelines, convective transport dominates the temperature evolution of the pipe fluid. Accurate numerical simulation provides crucial support for engineering operation and scheduling. Aiming at the severe numerical dissipation and resultant nonphysical broadening of temperature interfaces in the commercial software Stoner Pipeline Simulator (SPS) and the traditional method of characteristics (MOC) with linear interpolation (MOC-Linear), we propose a numerical computational framework that integrates the MOC with locally adaptive piecewise Akima interpolation. The framework discretizes the computational grid based on a characteristic velocity of 2.5 m/s, ensuring the Courant-Friedrichs-Lewy (CFL) number stays strictly below unity to satisfy the numerical stability criterion. Two typical operating conditions are designed for method validation: first, a step fluctuation of flow velocity (1.5 m/s→1.0 m/s) under a constant temperature field, for verifying numerical stability; second, a step change of temperature (45°C→35°C) under a constant flow velocity field, for evaluating antidissipation performance. An additional temperature step condition for large-diameter water transportation is included to verify the general applicability of the method across different fluid media and pipe diameters. The results show that under the flow velocity fluctuation condition, the temperature results from SPS, MOC-Linear, and MOC-Akima are fully consistent with no spurious oscillations, verifying the robustness of the proposed framework for smooth temperature fields. Under the temperature step condition, MOC-Akima effectively suppresses numerical dissipation: After 20 hours of simulation, the interface width is narrowed by approximately 70% compared with the 12.0 km yielded by MOC-Linear and by more than 90% compared with the 38.0 km yielded by SPS. Furthermore, MOC-Akima is insensitive to timestep variations and maintains a sharp temperature interface even with a relatively large timestep, striking a favorable balance between computational cost and accuracy. This numerical framework provides a reliable solution for temperature interface tracking in long-distance sequential transportation pipelines.
- 30 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (03) , 1425-1444
Research on a Rapid Calculation Method for External Unsteady Temperature Field of Long-Distance Buried Pipelines
Summary: During the transportation process of long-distance buried pipelines, the medium inside the pipeline and the semi-infinite soil space outside form a 3D unsteady heat transfer system. When simulating dynamic operational processes, the pipeline is modeled as a 1D system, thereby rendering the calculation of the external 3D unsteady soil temperature field the primary computational effort in overall simulations. Traditional analytical methods are unable to characterize the complex problem of 3D unsteady temperature fields, while numerical calculation methods have the problem of slow calculation speed. In this paper, we propose a rapid calculation method for unsteady temperature fields. Using the superposition principle and the Duhamel principle, the boundary conditions are decomposed to obtain the auxiliary problem. A proxy solution is constructed to represent the auxiliary problem, and the unsteady temperature field is rapidly solved by superimposing the proxy solution with the original boundary conditions. Compared with numerical methods, the new method improves the calculation speed of the global temperature field outside a single pipeline by 21 times. For the critical temperature field near the pipeline, which directly affects the overall heat transfer coefficient, the calculation speed is improved by 120 times, with a maximum temperature error of no more than 0.15°C across the entire domain and period. The method also applies to more complex scenarios, such as parallel double pipelines. This approach provides an accurate and efficient solution for calculating the external unsteady temperature field of long-distance buried pipelines, offering significant engineering application value.
- 30 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (03) , 1425-1444
Research on a Rapid Calculation Method for External Unsteady Temperature Field of Long-Distance Buried Pipelines
Summary: During the transportation process of long-distance buried pipelines, the medium inside the pipeline and the semi-infinite soil space outside form a 3D unsteady heat transfer system. When simulating dynamic operational processes, the pipeline is modeled as a 1D system, thereby rendering the calculation of the external 3D unsteady soil temperature field the primary computational effort in overall simulations. Traditional analytical methods are unable to characterize the complex problem of 3D unsteady temperature fields, while numerical calculation methods have the problem of slow calculation speed. In this paper, we propose a rapid calculation method for unsteady temperature fields. Using the superposition principle and the Duhamel principle, the boundary conditions are decomposed to obtain the auxiliary problem. A proxy solution is constructed to represent the auxiliary problem, and the unsteady temperature field is rapidly solved by superimposing the proxy solution with the original boundary conditions. Compared with numerical methods, the new method improves the calculation speed of the global temperature field outside a single pipeline by 21 times. For the critical temperature field near the pipeline, which directly affects the overall heat transfer coefficient, the calculation speed is improved by 120 times, with a maximum temperature error of no more than 0.15°C across the entire domain and period. The method also applies to more complex scenarios, such as parallel double pipelines. This approach provides an accurate and efficient solution for calculating the external unsteady temperature field of long-distance buried pipelines, offering significant engineering application value.
- Open Access
- 1 December 2025
- Published by KEAI Publishing in Petroleum Science
- Vol. 22 (12) , 5020-5033
ThinGPT: describing sedimentary rock thin section images with a multimodal large language model
- 1 December 2025
- Published by KEAI Publishing in Petroleum Science
- Vol. 22 (12) , 5020-5033
Open AccessThinGPT: describing sedimentary rock thin section images with a multimodal large language model
- 11 September 2025
- Published by Elsevier in Marine and Petroleum Geology
- Vol. 182
Enhancing reservoir parameter prediction workflows via advanced core data augmentation
- 11 September 2025
- Published by Elsevier in Marine and Petroleum Geology
- Vol. 182
Enhancing reservoir parameter prediction workflows via advanced core data augmentation
- Open Access
- 1 July 2025
- Published by KEAI Publishing in Petroleum Science
- Vol. 22 (7) , 2777-2793
Multidimensional data-driven porous media reconstruction: Inversion from 1D/2D pore parameters to 3D real pores
- 1 July 2025
- Published by KEAI Publishing in Petroleum Science
- Vol. 22 (7) , 2777-2793
Open AccessMultidimensional data-driven porous media reconstruction: Inversion from 1D/2D pore parameters to 3D real pores
- 23 March 2024
- Published by Springer Nature in Computational Geosciences
- Vol. 28 (3) , 491-502
A new method based on multiresolution graph-based clustering for lithofacies analysis of well logging
- 23 March 2024
- Published by Springer Nature in Computational Geosciences
- Vol. 28 (3) , 491-502
A new method based on multiresolution graph-based clustering for lithofacies analysis of well logging
- Top Cited Papers
- 18 January 2024
- Published by Elsevier in Computers & Geosciences
- Vol. 184
A multi-condition denoising diffusion probabilistic model controls the reconstruction of 3D digital rocks
- 18 January 2024
- Published by Elsevier in Computers & Geosciences
- Vol. 184
Top Cited PapersA multi-condition denoising diffusion probabilistic model controls the reconstruction of 3D digital rocks
- 9 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (5) , MR265-MR280
An interpretable ensemble machine-learning workflow for permeability predictions in tight sandstone reservoirs using logging data
Tight sandstone reservoirs exhibit strong vertical heterogeneity and complex pore structures, challenging conventional permeability evaluation methods based on well-logging data. Although rising machine-learning (ML) techniques have demonstrated excellent accuracy for industrial applications, the physics and rationality within such a powerful “black box” remain less clear. Hence, reliable permeability prediction would benefit from an interpretable ML-based workflow that could reveal the controlling factors. To compare the models and examine the underlying features, 16 different ML submodels are tested after data preprocessing, feature selection, and hyperparameter optimization. By comparing the fitting accuracy and tuning time, the light gradient boosting machine optimized by the whale optimization algorithm, referred to as LGB-WOA, is determined to be the optimal model with the best fitting accuracy and relatively short tuning time. A field data application demonstrates that even in highly heterogeneous reservoir sections, the LGB-WOA model outperformed conventional petrophysical models by being the most consistent with reservoir permeability directly measured from the core samples (R2>0.6). The Shapley additive explanation values are then used to interpret the predictions of our LGB-WOA model. As expected, the porosity curve exhibits the highest feature importance among all input features, significantly contributing to permeability predictions. Conversely, a wellbore diameter and compensated neutron log contribute the least and need not be used for subsequent model improvements. These experiments and workflow provide a powerful method for accurately assessing the permeability in complex reservoirs and contribute to a broader understanding of the application of ML in reservoir characterization, paving the way for establishing more interpretable and reliable prediction models.
- 9 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (5) , MR265-MR280
An interpretable ensemble machine-learning workflow for permeability predictions in tight sandstone reservoirs using logging data
Tight sandstone reservoirs exhibit strong vertical heterogeneity and complex pore structures, challenging conventional permeability evaluation methods based on well-logging data. Although rising machine-learning (ML) techniques have demonstrated excellent accuracy for industrial applications, the physics and rationality within such a powerful “black box” remain less clear. Hence, reliable permeability prediction would benefit from an interpretable ML-based workflow that could reveal the controlling factors. To compare the models and examine the underlying features, 16 different ML submodels are tested after data preprocessing, feature selection, and hyperparameter optimization. By comparing the fitting accuracy and tuning time, the light gradient boosting machine optimized by the whale optimization algorithm, referred to as LGB-WOA, is determined to be the optimal model with the best fitting accuracy and relatively short tuning time. A field data application demonstrates that even in highly heterogeneous reservoir sections, the LGB-WOA model outperformed conventional petrophysical models by being the most consistent with reservoir permeability directly measured from the core samples (R2>0.6). The Shapley additive explanation values are then used to interpret the predictions of our LGB-WOA model. As expected, the porosity curve exhibits the highest feature importance among all input features, significantly contributing to permeability predictions. Conversely, a wellbore diameter and compensated neutron log contribute the least and need not be used for subsequent model improvements. These experiments and workflow provide a powerful method for accurately assessing the permeability in complex reservoirs and contribute to a broader understanding of the application of ML in reservoir characterization, paving the way for establishing more interpretable and reliable prediction models.
- 7 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (4) , MR197-MR207
Investigating the causes of permeability anisotropy in heterogeneous conglomeratic sandstone using multiscale digital rock
Heterogeneous conglomeratic sandstone exhibits anisotropic physical properties, rendering a comprehensive analysis of its physical processes challenging with experimental measurements. Digital rock technology provides a visual and intuitive analysis of the microphysical processes in rocks, thereby aiding in scientific inquiry. Nevertheless, the multiscale characteristics of conglomeratic sandstone cannot be fully captured by a single-scale digital rock, thus limiting its ability to characterize the pore structure. Our work introduces a proposed workflow that uses multiscale digital rock fusion to investigate permeability anisotropy in heterogeneous rock. We use a cycle-consistent generative adversarial network to fuse computed tomography scan data of different resolutions, creating a large-scale and high-precision digital rock that comprehensively represents the conglomeratic sandstone pore structure. Subsequently, the digital rock is partitioned into multiple blocks, and the permeability of each block is simulated using a pore network. Finally, the total permeability of the sample is calculated by conducting an upscaling numerical simulation using the Darcy-Stokes equation. This process facilitates the analysis of the pore structure in conglomeratic sandstone and provides a step-by-step solution for permeability. From a multiscale perspective, this approach reveals that the anisotropy of permeability in conglomeratic sandstone stems from the layered distribution of grain sizes and differences in grain arrangement across different directions.
- 7 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (4) , MR197-MR207
Investigating the causes of permeability anisotropy in heterogeneous conglomeratic sandstone using multiscale digital rock
Heterogeneous conglomeratic sandstone exhibits anisotropic physical properties, rendering a comprehensive analysis of its physical processes challenging with experimental measurements. Digital rock technology provides a visual and intuitive analysis of the microphysical processes in rocks, thereby aiding in scientific inquiry. Nevertheless, the multiscale characteristics of conglomeratic sandstone cannot be fully captured by a single-scale digital rock, thus limiting its ability to characterize the pore structure. Our work introduces a proposed workflow that uses multiscale digital rock fusion to investigate permeability anisotropy in heterogeneous rock. We use a cycle-consistent generative adversarial network to fuse computed tomography scan data of different resolutions, creating a large-scale and high-precision digital rock that comprehensively represents the conglomeratic sandstone pore structure. Subsequently, the digital rock is partitioned into multiple blocks, and the permeability of each block is simulated using a pore network. Finally, the total permeability of the sample is calculated by conducting an upscaling numerical simulation using the Darcy-Stokes equation. This process facilitates the analysis of the pore structure in conglomeratic sandstone and provides a step-by-step solution for permeability. From a multiscale perspective, this approach reveals that the anisotropy of permeability in conglomeratic sandstone stems from the layered distribution of grain sizes and differences in grain arrangement across different directions.
- 18 August 2023
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 230
Reconstruction of 3D digital rocks with controllable porosity using CVAE-GAN
- 18 August 2023
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 230
Reconstruction of 3D digital rocks with controllable porosity using CVAE-GAN