Pan Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pan Luo has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Chen Zhu
2 shared publications- Peng Lu
EXPEC Advanced Research Center, Saudi Aramco, Dhahran, 31311, Saudi Arabia
2 shared publications - Wei Wei
Aramco Research Center—Beijing
2 shared publications - Angelo Sampaolo
PolySense Lab, Dipartimento Interateneo di Fisica, University and Politecnico of Bari, Via Amendola 173, 70126 Bari, Italy
1 shared publication - Charles H. Wellman
School of Biosciences, University of Sheffield, Sheffield, UK
1 shared publication - Geoff Clayton
School of Biosciences, University of Sheffield, Sheffield S10 2TN, U.K
1 shared publication
Latest Publications
- Open Access
- 21 July 2026
- Published by Elsevier in SSRN Electronic Journal
Physically-Constrained Hybrid Machine Learning Framework for Predicting CH4 and CO2 Solubility in Water and NaCl Brines
Predicting CH4 and CO2 solubility in water and brines is important for evaluating dissolution trapping, gas partitioning, and compositional evolution in geological carbon storage, and related gas-production and reservoir-engineering applications. This study proposes a physically-constrained hybrid machine learning (ML) framework that combines baseline modeling with physical trend constraints from thermodynamic modeling data and residual learning from experimental data to predict gas solubility in reservoir conditions with pressure (1-2000 bar), temperature (298.15-550.15 K), salinity (mNaCl 0-6 mol/kg), and gas-composition. A unified database containing 10,106 records, including 3,625 experimental and 6,481 thermodynamic-model generated data points, was compiled for pure CH4, pure CO2, and mixed CH4–CO2 aqueous systems. The results show that the baseline model preserves smooth and physically reasonable solubility trends across broad parameter ranges, while residual correction substantially improves agreement with experimental observations. For CH4–H2O–(NaCl), the hybrid MLP model improved [[EQUATION]] from 0.75 to 0.98, and reduced RMSE from 0.35 to 0.09. For CO2–H2O–(NaCl), [[EQUATION]] increased from 0.90 to 0.99, and RMSE decreased from 0.55 to 0.12. For mixed CH4–CO2 systems, the framework reproduces physically credible composition-dependent dissolution trends, although broader validation is still needed because of limited experimental data. Across different regressors, the hybrid strategy showed strong performance, with the MLP implementation achieving the best overall balance between predictive accuracy and physically reasonable trend behavior in this study. The proposed framework offers a computationally efficient and physically consistent thermodynamic surrogate for gas–water–brine systems, supporting rapid screening, process simulation, and uncertainty analysis in carbon storage and subsurface energy systems.
- 21 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPhysically-Constrained Hybrid Machine Learning Framework for Predicting CH4 and CO2 Solubility in Water and NaCl Brines
Predicting CH4 and CO2 solubility in water and brines is important for evaluating dissolution trapping, gas partitioning, and compositional evolution in geological carbon storage, and related gas-production and reservoir-engineering applications. This study proposes a physically-constrained hybrid machine learning (ML) framework that combines baseline modeling with physical trend constraints from thermodynamic modeling data and residual learning from experimental data to predict gas solubility in reservoir conditions with pressure (1-2000 bar), temperature (298.15-550.15 K), salinity (mNaCl 0-6 mol/kg), and gas-composition. A unified database containing 10,106 records, including 3,625 experimental and 6,481 thermodynamic-model generated data points, was compiled for pure CH4, pure CO2, and mixed CH4–CO2 aqueous systems. The results show that the baseline model preserves smooth and physically reasonable solubility trends across broad parameter ranges, while residual correction substantially improves agreement with experimental observations. For CH4–H2O–(NaCl), the hybrid MLP model improved [[EQUATION]] from 0.75 to 0.98, and reduced RMSE from 0.35 to 0.09. For CO2–H2O–(NaCl), [[EQUATION]] increased from 0.90 to 0.99, and RMSE decreased from 0.55 to 0.12. For mixed CH4–CO2 systems, the framework reproduces physically credible composition-dependent dissolution trends, although broader validation is still needed because of limited experimental data. Across different regressors, the hybrid strategy showed strong performance, with the MLP implementation achieving the best overall balance between predictive accuracy and physically reasonable trend behavior in this study. The proposed framework offers a computationally efficient and physically consistent thermodynamic surrogate for gas–water–brine systems, supporting rapid screening, process simulation, and uncertainty analysis in carbon storage and subsurface energy systems.
- Open Access
- 15 August 2024
- Published by Elsevier in Marine and Petroleum Geology
- Vol. 169
Acritarch Palynomorph Darkness Index (PDI) as an indicator of thermal maturity in Silurian sections from Saudi Arabia
- 15 August 2024
- Published by Elsevier in Marine and Petroleum Geology
- Vol. 169
Open AccessAcritarch Palynomorph Darkness Index (PDI) as an indicator of thermal maturity in Silurian sections from Saudi Arabia
- Open Access
- 18 January 2022
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 7 (4) , 3395-3406
Simultaneous Detection of Methane, Ethane, and Propane by QEPAS Sensors for On-Site Hydrocarbon Characterization and Production Monitoring
Natural gas is sampled and produced throughout the lifespan of a petroleum field. Gas composition and isotope data are critical inputs in the exploration and field development, such as gas show identification, petroleum system analysis, fluid characterization, and production monitoring. On-site gas analysis is usually conducted within a mud gas unit, which is operationally unavailable after drilling. Gas samples need to be taken from the field and shipped back to the laboratory for gas chromatography and isotope-ratio mass spectrometry analyses. Results are usually without sufficient resolution to fully characterize the heterogeneity and dynamics of fluids within the reservoir and the production system. In addition, it often takes a considerable time to obtain the results using the traditional method. A novel QEPAS (quartz-enhanced photoacoustic spectroscopy) sensor system was developed to move gas composition analyses to field for quasi-real-time characterization and monitoring. With respect to previously reported QEPAS prototypes for trace gas detection, the new system realized measuring concentrations of methane (C1), ethane (C2), and propane (C3) in gas phase within the percentage range that is typically encountered in natural gas samples from oil and gas fields. A gas mixing enclosure was used to dilute the natural gas-like mixtures in nitrogen gas (N2) to avoid the saturation of QEPAS signals. An iterative analysis based on multilinear regression of QEPAS spectra was developed to filter out the influence of gas matrix variation from multiple hydrocarbon components. The advance in simultaneous measuring hydrocarbon gases and expanded linearity range of QEPAS, with previously reported detection of H2S, CO2, and gas isotopes (12CO2/13CO2, 13CH4/12CH4), opens a way to use the advanced sensing technology for in situ and real-time gas detection and chemical analysis in the oil industry.
- 18 January 2022
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 7 (4) , 3395-3406
Open AccessSimultaneous Detection of Methane, Ethane, and Propane by QEPAS Sensors for On-Site Hydrocarbon Characterization and Production Monitoring
Natural gas is sampled and produced throughout the lifespan of a petroleum field. Gas composition and isotope data are critical inputs in the exploration and field development, such as gas show identification, petroleum system analysis, fluid characterization, and production monitoring. On-site gas analysis is usually conducted within a mud gas unit, which is operationally unavailable after drilling. Gas samples need to be taken from the field and shipped back to the laboratory for gas chromatography and isotope-ratio mass spectrometry analyses. Results are usually without sufficient resolution to fully characterize the heterogeneity and dynamics of fluids within the reservoir and the production system. In addition, it often takes a considerable time to obtain the results using the traditional method. A novel QEPAS (quartz-enhanced photoacoustic spectroscopy) sensor system was developed to move gas composition analyses to field for quasi-real-time characterization and monitoring. With respect to previously reported QEPAS prototypes for trace gas detection, the new system realized measuring concentrations of methane (C1), ethane (C2), and propane (C3) in gas phase within the percentage range that is typically encountered in natural gas samples from oil and gas fields. A gas mixing enclosure was used to dilute the natural gas-like mixtures in nitrogen gas (N2) to avoid the saturation of QEPAS signals. An iterative analysis based on multilinear regression of QEPAS spectra was developed to filter out the influence of gas matrix variation from multiple hydrocarbon components. The advance in simultaneous measuring hydrocarbon gases and expanded linearity range of QEPAS, with previously reported detection of H2S, CO2, and gas isotopes (12CO2/13CO2, 13CH4/12CH4), opens a way to use the advanced sensing technology for in situ and real-time gas detection and chemical analysis in the oil industry.