2021 — Aug. 2025
THE INTERSECTION OF DATA & ENERGY
Exploring what lies
beneath the surface.
I am a Senior Research Engineer at SINOPEC Oil Exploration & Development Research Institute, working in the Oversea Key Project Support Center in Beijing, China. I completed my Ph.D. in Petroleum Engineering at the University of Alberta in August 2025.
My research focuses on deep learning, production forecasting and numerical methods for subsurface systems, connecting field measurements, physical understanding and data-driven models.
CONTACT
Education
2019 — 2021
M.Sc. in Petroleum Engineering
University of Alberta
Edmonton, Alberta, CA
2015 — 2019
B.Sc. in Petroleum Engineering
University of Alberta
Edmonton, Alberta, CA
Experience
Oct. 2025 — Present
Senior Research Engineer
SINOPEC Oil Exploration & Development Research Institute
Oversea Key Project Support Center
Beijing, China
From Sep. 2022 (during graduate studies)
Teaching Assistant (PETE375; PETE475)
University of Alberta
- Assisted in grading assignments and reports.
- Facilitated engaging classroom discussions and responded to student inquiries.
- Provided remote one-on-one guidance and addressed student concerns.
From Sep. 2019 (during graduate studies)
Research Assistant
University of Alberta
- Conducted research and data analysis on unconventional reservoirs.
- Collaborated with professors on publications.
Research projects
Connecting physical understanding with data-driven discovery.
PROJECT / 01April 2023 — Present
AssimNet: Bridging Field Measurements and Numerical Simulations
- Developed a hybrid neural framework that translates field measurements into simulation-ready inputs and calibrates production forecasts during training.
- Evaluated the model on synthetic cases and more than 1,400 Montney shale gas wells, improving forecasting and generalization under limited-data conditions.
PROJECT / 02Dec. 2022 — Present
Graph Convolution for Capturing Well Interference in Production Forecasting
- Developed novel ST-GraphSAGE model for generalizing unseen nodes and computation of evolving graphs.
- Incorporated a GRU encoder-decoder model to capture cross-time neighborhood information effectively.
PROJECT / 03Sep. 2021 — April 2023
Enhanced RNN-Based Production Forecasting for Shale Gas Reservoirs
- Developed novel MRA (Masked Recurrent Alignment) architecture, enabling inputs sequence with varied lengths.
- Proposed novel RUF (Recursively Updated Forecasting) architecture, enabling real-time updates with production data.
- Generated multi-stage hydraulic fracture synthetic dataset using DFNs and geomechanical simulation.
PROJECT / 04Jan. 2019 — Dec. 2021
Impacts of Meshing and Discretization on DPDK Flow Simulation
- Proposed quick analytical workflow for generating non-planar twisted fractures, improving fracture representation.
- Developed novel workflow to restore connectivity between disconnected fractures after discretization.
- Upscaled DFN into DPDK and conducted DPDK Flow simulation on fractured reservoir using a black oil simulator.
Academic activity & service
Geoenergy Science and Engineering
Journal reviewer
SPE Journal
Journal reviewer
Journal publications
1. Xu, Z., & Leung, J. Y. (2026). Multi-horizon probabilistic shale gas production forecasting using VAE-GAN. Geoenergy Science and Engineering, 263, 214528.
https://doi.org/10.1016/j.geoen.2026.214528 ↗
2. Xu, Z., & Leung, J. Y. (2025). Spatial-Temporal Graph-Level Feature Embedding for Shale Gas Production Forecasting with Well Interference. SPE Journal, 30(11), 6547–6564.
https://doi.org/10.2118/220790-PA ↗
3. Ma, Z., Yuan, Q., Xu, Z., & Leung, J. Y. (2025). A dynamic solvent chamber propagation estimation framework using RNN for warm solvent injection in heterogeneous reservoirs. Geoenergy Science and Engineering, 244, 213405.
https://doi.org/10.1016/j.geoen.2024.213405 ↗
4. Xu, Z., & Leung, J. Y. (2024). Shale Gas Production Forecasting with Well Interference Based on Spatial-Temporal Graph Convolutional Network. SPE Journal, 29(10), 5120–5131.
https://doi.org/10.2118/215056-PA ↗
5. Xu, Z., & Leung, J. Y. (2024). Dynamic Real-Time Production Forecasting Model for Complex Subsurface Flow Systems with Variable Length Input Sequences. SPE Journal, 29(9), 4510–4526.
https://doi.org/10.2118/221482-PA ↗
6. Xu, Z., & Leung, J. Y. (2024). A novel formulation of RNN-based neural network with real-time updating–An application for dynamic hydraulic fractured shale gas production forecasting. Geoenergy Science and Engineering, 233, 212491.
https://doi.org/10.1016/j.geoen.2023.212491 ↗
Corrigendum ↗
7. Xu, Z., & Leung, J. Y. (2023). An Improved Dual-Porosity Dual-Permeability Modeling Workflow for Representing Nonplanar Hydraulic Fractures. Gas Science and Engineering, 118, 205108.
https://doi.org/10.1016/j.jgsce.2023.205108 ↗
8. Chen, J., Xu, Z., & Leung, J. Y. (2022). Analysis of fracture interference–Coupling of flow and geomechanical computations with discrete fracture modeling using MRST. Journal of Petroleum Science and Engineering, 219, 111134.
https://doi.org/10.1016/j.petrol.2022.111134 ↗
9. Xu, Z., & Leung, J. Y. (2022). Analyzing the Impacts of Meshing and Grid Alignment in Dual-Porosity Dual-Permeability Upscaling. SPE Reservoir Evaluation & Engineering, 25(1), 61–80.
https://doi.org/10.2118/208573-PA ↗
Preprints
Xu, Z., & Leung, J. Y. (2025). AssimNet: A Hybrid Deep Learning Model Bridging Field Measurements and Numerical Simulations for Large-Scale Subsurface Time-Series Forecasting. SSRN preprint. Posted December 27, 2025.
https://doi.org/10.2139/ssrn.5974792 ↗Conferences
1. Xu, Z., & Leung, J. (2025, October). Physics-Constrained Production Forecasting with Direct Fracture Characterization by Field Data. SPE Annual Technical Conference and Exhibition, Houston, Texas, USA. SPE-228139-MS.
https://doi.org/10.2118/228139-MS ↗2. Xu, Z., Liu, H., & Leung, J. Y. (2025, March). Deep Learning-Based Production Forecasting for Liquid-Rich Gas in the Duvernay Shale Play. SPE Canadian Energy Technology Conference and Exhibition, Calgary, Alberta, Canada. SPE-224009-MS.
https://doi.org/10.2118/224009-MS ↗3. Xu, Z., & Leung, J. Y. (2024, September). Graph-Level Feature Embedding with Spatial–Temporal GCN Method for Interconnected Well Production Forecasting. SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA. SPE-220790-MS.
https://doi.org/10.2118/220790-MS ↗4. Xu, Z., & Leung, J. Y. (2023, October). Shale Gas Production Forecasting with Well Interference Based on Spatial-Temporal Graph Convolutional Network. SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA. SPE-215056-MS.
https://doi.org/10.2118/215056-MS ↗5. Ma, Z., Yuan, Q., Xu, Z., & Leung, J. Y. (2023, October). A Recurrent Neural Network-Based Solvent Chamber Estimation Framework During Warm Solvent Injection in Heterogeneous Reservoirs. SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA. SPE-214984-MS.
https://doi.org/10.2118/214984-MS ↗6. Xu, Z., & Leung, J. (2023, August). A Recursively Enhanced GRU Model for Real-Time Production Forecasting in Central Montney Shale Gas Reservoirs. International Association for Mathematical Geosciences (IAMG) Conference, Trondheim, Norway.
Conference abstract ↗Corporation
- Github: https://github.com/ziming-zx
- LinkedIn: https://linkedin.com/in/ziming-xu-kimi
- ORCID: https://orcid.org/0000-0002-6937-1307
- Google Scholar: https://scholar.google.ca/citations?user=AakA-w0AAAAJ&hl=en&oi=sra