About

Akhil Datta-Gupta is a Professor of Petroleum Engineering at Texas A&M University and a member of the National Academy of Engineering. He holds the L.F. Peterson '36 Chair and is a University Distinguished Professor and Regents Professor. His educational background includes a Ph.D. and M.S. in Petroleum Engineering from the University of Texas at Austin, and a B.S. from the Indian School of Mines, Dhanbad. His research interests encompass rapid flow simulation techniques, reservoir optimization, large-scale parameter estimation via inverse methods, uncertainty quantification and assessments, streamline simulation and applications, inverse modeling and multi-scale data integration, geostatistics, stochastic reservoir characterization, and modeling and scale-up of enhanced oil recovery. Dr. Datta-Gupta has received notable awards such as the John Franklin Carll Award from the Society of Petroleum Engineers and the Lester C. Uren Award, and has been recognized for his contributions to basic research in geosciences by the U.S. Department of Energy.

Selected publications

• Fast Marching Method: A New Paradigm for Rapid Simulation of Enhanced Geothermal Systems

  SSRN Electronic Journal · 2025-01-01 · 2 citations

  preprintOpen access
  PublisherDOI

• Real Time CO2 Plume Monitoring and Visualization Considering Geologic Uncertainty at the Illinois Basin-Decatur Carbon Sequestration Project

  SPE Annual Technical Conference and Exhibition · 2025-10-13

  articleSenior author

  Abstract Monitoring the CO2 plume evolution is essential for ensuring geologic storage security and integrity. Traditional numerical simulation-based data assimilation workflow is computationally expensive, and this is further complicated by the fact that geologic uncertainty must be incorporated for robust performance prediction. Therefore, reservoir simulation and model calibration accounting for geologic uncertainty are not amenable to real time monitoring of the CO2 plume evolution for large-scale applications. We propose a deep learning-based approach which enables near real time CO2 plume visualization and rapid data assimilation incorporating multiple geological realizations for predicting future CO2 plume evolution and area of review (AOR) determination. The proposed deep learning-based data assimilation framework considers geological uncertainty utilizing multiple plausible models for training data generation. Rather than utilizing all available geologic realizations, a representative subset is sampled using dissimilarity measures in flow patterns computed via multidimensional scaling (MDS) and streamline time-of-flight. The approach substantially reduces training data generation cost while preserving the uncertainty inherent in the original ensemble of geomodels. The CO2 plume evolution is represented using ‘onset time’ images, depicting the calendar time when the CO2 saturation exceeds a prespecified threshold value at a given location. The use of a single CO2 onset time image instead of multiple CO2 saturation snapshots across different timesteps significantly reduces the dimensionality of the problem, making the deep learning model robust and scalable for large-scale field applications. A variational autoencoder encodes the onset time images into latent variables, which are predicted by another neural networks using the available monitoring data. The power and efficacy of the proposed method are demonstrated through application to a large-scale field case, the Illinois Basin-Decatur Carbon Sequestration Project. The available monitoring data consists of bottom-hole pressure at the injector, distributed pressure data and CO2 saturation log data at the monitoring well. Out of 200 geostatistical realizations, 10 representative models are selected by the MDS while preserving diversity of the geologic model. Additional calibration parameters including transmissibility and pore volume multipliers are applied to the selected realizations for generating a comprehensive training dataset. The trained ML model is then employed for reservoir model calibration, significantly accelerating the calibration process and enabling real time CO2 plume imaging from the monitoring data. The trained deep learning model achieves history matching of both pressure and saturation responses in seconds. The calibrated models are then used for forecasting future CO2 plume migration and the AOR assessment. The deep learning-based data assimilation approach enables near real time monitoring and verification of field-scale CO2 sequestration projects while accounting for geologic uncertainty. Utilizing the trained deep learning model, reservoir model calibration and prediction of CO2 plume evolution is performed within seconds, orders of magnitude faster compared to traditional history matching.

  PublisherDOI

• Multi-Resolution Deep Learning for Accelerated Well Control Optimization in CO2 Storage: A Field Application at the Illinois Basin Decatur Project (IBDP)

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

• Dynamic Reservoir Modeling of the Utah FORGE Enhanced Geothermal Project Using Fast Marching Method

  2025-09-01

  articleSenior author

  Abstract The Utah FORGE project is the largest Enhanced Geothermal System (EGS) demonstration site for geothermal energy production in low permeability formation with limited subsurface water availability. The FORGE project encompasses hydraulic stimulation followed by fluid circulation test. High-resolution EGS simulations are computationally intensive because they involve non-isothermal flow within hard rocks containing hydraulic and natural fractures. This study involves the development and history-matching of a reservoir model at the Utah FORGE site based on a discrete fracture network model and dynamic data from circulation tests for assessment of long-term performance and sustainability of the geothermal project. We propose a novel Fast-Marching-Method (FMM) based accelerated dynamic reservoir modeling approach enabling orders of magnitude faster simulation and demonstrate its power and efficacy through application at the Utah FORGE site. The reservoir dynamic model for the Utah FORGE site is developed based on a Discrete Fracture Network (DFN) model constructed using well logs and microseismic data. A month-long circulation test results are used as observational data for history matching and model updating. To mitigate the high computational cost from repeated simulations during history matching, we utilize the Fast Marching Method (FMM)-based simulation that transforms 3D fine-scale simulations into equivalent multi-resolution simulations using Diffusive Time of Flight (DTOF) as spatial coordinate. The DTOF represents the propagation time of the ‘pressure front’ and is computed in seconds by solving the Eikonal equation with FMM. Using the DTOF contours, the 3D fine-scale model is converted into a coarse multi-resolution model while preserving the 3D fine-scale near-wellbore region to maintain the hydraulic fracture fidelity and leading to the orders of magnitude acceleration in simulation time. The FMM-based multi-resolution simulation is applied to the Utah FORGE model and compared with 3D fine-scale simulation using a commercial simulator. The proposed approach is shown to speed up the simulation by more than an order of magnitude (10 to 20 times) with minimal loss of accuracy. Using the fast simulation model, a multi-objective genetic algorithm is applied to calibrate the reservoir model using bottomhole pressure and fluid temperature obtained during the circulation test. The calibrated reservoir model is used to predict long-term geothermal performance for 10 years at the Utah FORGE site, providing estimates of production rates, fluid temperatures and thermal power output.

  PublisherDOI

• Multi-stage three-phase and compositional history matching: Field application to CO2 enhanced oil recovery in the Permian Basin, Texas

  Fuel · 2025-01-15 · 6 citations

  article
  PublisherDOI

• CO2 plume monitoring and injection optimization based on pathlines, source clouds and time clouds: Field application at the Illinois Basin-Decatur carbon sequestration project

  International journal of greenhouse gas control · 2025-04-10 · 1 citations

  articleSenior author
  PublisherDOI

• Acceleration of Data-Driven Proxy Models Using Physics-Based Reduced-Order-Model: Pseudo-Steady-State-Based Simulation

  SPE Annual Technical Conference and Exhibition · 2025-10-13

  articleSenior author

  Abstract Injecting CO₂ into subsurface formations for large-scale geological carbon sequestration requires rapid and reliable reservoir pressure estimation for storage integrity and minimizing potential seismic activities. Although various machine/deep-learning models have been proposed for this purpose, these models typically require numerous reservoir simulations to generate adequate training data, which can be computationally expensive and potentially offset the acceleration in pressure prediction. This work utilizes a novel Pseudo-Steady-State-based Simulation (PSS-SIM) to significantly reduce training data generation cost while maintaining high performance predictions of data driven proxy models for near real time monitoring and control of carbon sequestration projects. PSS-SIM is a reduced-order modelling approach that converts 3D simulations to equivalent multi-resolution simulations using pseudo-steady-state (PSS) pressure contours as spatial coordinate. The multi-resolution grid achieves significant reduction in active cells and accelerates reservoir simulation by orders of magnitude. Our proposed method is applied to the Illinois Basin Decatur Project (IBDP), which is a large-scale CO₂ injection project into deep saline aquifer at the Illinois Basin, USA. Using PSS-SIM, training data for data-driven proxy models is generated with orders of magnitude acceleration in computational time compared to traditional fine-scale simulation. The simulated pressure from PSS-SIM is first validated against commercial reservoir simulations, demonstrating accuracy of the proposed approach. Next, Fourier Neural Operator (FNO), which solves PDEs by learning frequency-domain mappings through the Fourier transform, is trained using the PSS-SIM model simulations. The trained proxy model predicts reservoir pressure distribution from given geologic model and CO₂ injection schedule as spatial and temporal information. We account for the interactions between geologic heterogeneity and the flow field in the data-driven proxy model through the PSS pressure solution as input. The PSS contour exhibits strong correlation with pressure distribution, highlighting the effectiveness of the PSS-SIM-based proxy model. Machine/Deep learning models for geological carbon storage typically require hundreds of reservoir simulations for training data generation. The PSS-SIM reduces the generation costs by orders of magnitude for constructing data-driven proxy models. This substantial reduction in data generation costs enhances the feasibility of employing data-driven models in CCS projects, thereby enabling rapid scenario evaluations for both operational decision-making and field development planning.

  PublisherDOI

• CO2 Plume Imaging with Accelerated Deep Learning-based Data Assimilation Considering Multiple Realizations: Application to the Illinois Basin-Decatur Carbon Sequestration Project

  2025-03-03

  articleOpen accessSenior author

  We propose a fast and efficient deep learning workflow for near real-time data assimilation, forecasting and visualization of CO2 plume evolution in saline aquifer and demonstrate its application at a field site. Unlike the previous work, this study incorporates the impact of spatial heterogeneity using multiple realizations. In the proposed workflow, a neural network model utilizes available monitoring data such as downhole pressure measurements as input and predicts the propagating pressure ‘front’ using the diffusive time of flight (DTOF) map which is considered as representative reservoir image of the flow field. The DTOF is the arrival time of pressure front propagation, which can be computed by the Fast Marching Method rapidly without flow simulations. Reservoir model calibration can be implemented by selecting the training data samples that describe the predicted DTOF map based on observed data. The power and efficacy of our workflow is demonstrated by application to the Illinois Basin-Decatur Project.

  PublisherDOI

• Screening and Ranking of Geostatistical Models Through Identification of Reservoir Connectivity and Preferential Flow Paths Using Physics Informed Machine Learning

  Quantitative geology and geostatistics · 2025-01-01

  book-chapterSenior author
  PublisherDOI

• Fast Marching Method: A new paradigm for rapid simulation of enhanced geothermal systems

  Geoenergy Science and Engineering · 2025-10-15

  articleOpen access

  Enhanced Geothermal System (EGS) provide access to thermal energy stored in hot, dry rock formations beyond the reach of conventional hydrothermal systems, yet a significant challenge remains in reliably predicting the flow rate, temperature, and thermal performance of the produced subsurface fluids. Reservoir simulation, widely used in the oil and gas industry for forecasting subsurface fluid production, is also applied to EGS. These simulations must resolve complex non-isothermal, compositional flow through fractured porous media, leading to significant computational demands and runtimes of several hours to days per simulation. We propose a new paradigm for rapid multi-domain, multi-resolution simulation of EGS that accelerates reservoir simulation by orders of magnitude. Our reservoir simulation method uses a finite-volume-based Fast Marching Method (FMM) to efficiently compute Diffusive Time of Flight (DTOF) and transform 3D simulations into equivalent 1D simulations using DTOF as spatial coordinate. The DTOF, which tracks pressure front propagation, guides the discretization of the 1D mesh. To maintain accuracy, the proposed method preserves 3D resolution near the wellbore and hydraulic fractures while converting the rest of the reservoir to 1D grid, resulting in significant computational speed up. The 3D and 1D domains communicate through non-neighbor connections that incorporate both fluid and heat transmissibility. The proposed method was applied to a triplet horizontal well configuration, featuring one horizontal injector positioned between two horizontal producers to optimize heat extraction, with reservoir simulations conducted over 20 years to assess the long-term performance of geothermal projects. The proposed FMM based multi-resolution simulation model provides flow rates, temperature and thermal power output with orders of magnitude (10-25 times) speed up compared to the traditional full 3D numerical simulations. With the accelerated workflow, the proposed approach enables performance assessment and optimization of geothermal projects in hours compared to the typical timeframe of several days using commercial simulators, making such modeling practically feasible for routine applications. • High-fidelity performance of Enhanced Geothermal Systems is quantitatively assessed • FMM-SIM is extended for geothermal applications, incorporating fluid and heat flow • Multi-resolution model accelerates geothermal simulation by orders of magnitude • Applied to EDFM and field-scale fractured model with triplet horizontal wells • Demonstrated rapid simulation studies of well spacing and operational parameters

  PublisherDOI

Labs

• Petroleum Engineering LabsPI

Awards & honors

• John Franklin Carll Award, Society of Petroleum Engineers
• Outstanding Contributions to Basic Research in Geosciences,…
• Lester C. Uren Award, Society of Petroleum Engineers
• Member, National Academy of Engineering
• Honorary Member, Society of Petroleum Engineers