Mohammad Ahmadi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mohammad Ahmadi has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Reza Yousefzadeh
Amirkabir University of Technology
12 shared publications - Alireza Kazemi
Department of Petroleum and Chemical Engineering, College of Engineering, Sultan Qaboos University, Muscat 123, Oman
10 shared publications Alireza Kazemi
Department of Petroleum and Chemical Engineering, Sultan Qaboos University, Muscat, Oman
7 shared publications- Jebraeel Gholinezhad
University of Portsmouth
6 shared publications - Mohammad Sharifi
Department of Petroleum and Geoenergy Engineering, Amirkabir University of Technology, Tehran, Iran
6 shared publications - Abdolhossein Hemmati-Sarapardeh
Shahid Bahonar University of Kerman
5 shared publications
Latest Publications
- 29 June 2026
- Published by Wiley in The Canadian Journal of Chemical Engineering
Electrical submersible pump fault diagnosis: A comprehensive review and practical recommendations for real‐time monitoring using an adaptive rule‐based framework
Electrical submersible pump (ESP) failures often arise from complex interactions among mechanical, electrical, and fluid‐dynamic factors that remain difficult to detect using conventional threshold‐based or black‐box diagnostic models. This comprehensive review examines more than 15 years of ESP diagnostic methods and provides clear practical recommendations for field engineers. This study presents an adaptive hybrid rule‐based expert system for real‐time ESP fault diagnosis, integrating 500 dynamically prioritized rules across 10 functional domains within a feedback‐driven adaptive hybrid inference loop (AHIL). The framework combines deterministic reasoning, statistical drift analysis, and machine‐learning insights to enable contextual interpretation of multi‐sensor data while continuously adjusting rule confidence weights and activation thresholds based on operational feedback. Validation using representative simulated and field‐aligned datasets demonstrates a detection accuracy of 94.3% and an average alert latency of 87 s, corresponding to improvements of approximately 12% and 30%, respectively, compared with conventional supervisory control and data acquisition alarm systems. These results confirm that adaptive rule evolution and interpretability coupling establish a scalable, transparent foundation for intelligent ESP monitoring, bridging the gap between expert‐driven reasoning and data‐driven adaptability.
- 29 June 2026
- Published by Wiley in The Canadian Journal of Chemical Engineering
Electrical submersible pump fault diagnosis: A comprehensive review and practical recommendations for real‐time monitoring using an adaptive rule‐based framework
Electrical submersible pump (ESP) failures often arise from complex interactions among mechanical, electrical, and fluid‐dynamic factors that remain difficult to detect using conventional threshold‐based or black‐box diagnostic models. This comprehensive review examines more than 15 years of ESP diagnostic methods and provides clear practical recommendations for field engineers. This study presents an adaptive hybrid rule‐based expert system for real‐time ESP fault diagnosis, integrating 500 dynamically prioritized rules across 10 functional domains within a feedback‐driven adaptive hybrid inference loop (AHIL). The framework combines deterministic reasoning, statistical drift analysis, and machine‐learning insights to enable contextual interpretation of multi‐sensor data while continuously adjusting rule confidence weights and activation thresholds based on operational feedback. Validation using representative simulated and field‐aligned datasets demonstrates a detection accuracy of 94.3% and an average alert latency of 87 s, corresponding to improvements of approximately 12% and 30%, respectively, compared with conventional supervisory control and data acquisition alarm systems. These results confirm that adaptive rule evolution and interpretability coupling establish a scalable, transparent foundation for intelligent ESP monitoring, bridging the gap between expert‐driven reasoning and data‐driven adaptability.
- Open Access
- 22 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A physics-informed multi-modal transformer framework for predictive maintenance and remaining useful life estimation of electrical submersible pumps
Electrical Submersible Pumps (ESPs) are widely used in oil and gas production but are highly vulnerable to mechanical, electrical, hydraulic, and thermal degradation under harsh downhole conditions. Unexpected ESP failures can result in severe production losses, costly interventions, and reduced operational reliability, highlighting the importance of predictive maintenance and Remaining Useful Life (RUL) estimation. Existing prognostic approaches often rely on single-modality data and lack physical consistency in degradation modeling. This study proposes HF-ESPNet, a physics-informed multi-modal transformer framework for joint ESP failure prediction and RUL estimation. The proposed model integrates heterogeneous operational data, including electrical telemetry, pressure, temperature, vibration indicators, well metadata, and maintenance history within a unified transformer-based architecture. Domain-specific physics-informed constraints related to hydraulic behavior, thermal dynamics, and vibration degradation are incorporated into the learning objective to improve physical consistency and prognostic reliability. The framework was evaluated using an anonymized real-world ESP dataset containing more than 58,000 multivariate time-series samples under diverse operational conditions. Experimental results demonstrate that HF-ESPNet outperforms conventional machine learning, deep learning, and transformer-based baseline models in both failure prediction and RUL estimation tasks. Ablation analysis further confirms the importance of vibration-derived features and physics-informed constraints in improving predictive robustness and degradation modeling accuracy. The results demonstrate that combining multi-modal representation learning, transformer-based temporal modeling, and physics-informed learning provides a robust and interpretable framework for ESP prognostics, supporting improved maintenance scheduling, reduced unplanned downtime, and enhanced operational reliability in oil and gas production systems.
- 22 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA physics-informed multi-modal transformer framework for predictive maintenance and remaining useful life estimation of electrical submersible pumps
Electrical Submersible Pumps (ESPs) are widely used in oil and gas production but are highly vulnerable to mechanical, electrical, hydraulic, and thermal degradation under harsh downhole conditions. Unexpected ESP failures can result in severe production losses, costly interventions, and reduced operational reliability, highlighting the importance of predictive maintenance and Remaining Useful Life (RUL) estimation. Existing prognostic approaches often rely on single-modality data and lack physical consistency in degradation modeling. This study proposes HF-ESPNet, a physics-informed multi-modal transformer framework for joint ESP failure prediction and RUL estimation. The proposed model integrates heterogeneous operational data, including electrical telemetry, pressure, temperature, vibration indicators, well metadata, and maintenance history within a unified transformer-based architecture. Domain-specific physics-informed constraints related to hydraulic behavior, thermal dynamics, and vibration degradation are incorporated into the learning objective to improve physical consistency and prognostic reliability. The framework was evaluated using an anonymized real-world ESP dataset containing more than 58,000 multivariate time-series samples under diverse operational conditions. Experimental results demonstrate that HF-ESPNet outperforms conventional machine learning, deep learning, and transformer-based baseline models in both failure prediction and RUL estimation tasks. Ablation analysis further confirms the importance of vibration-derived features and physics-informed constraints in improving predictive robustness and degradation modeling accuracy. The results demonstrate that combining multi-modal representation learning, transformer-based temporal modeling, and physics-informed learning provides a robust and interpretable framework for ESP prognostics, supporting improved maintenance scheduling, reduced unplanned downtime, and enhanced operational reliability in oil and gas production systems.
- Open Access
- 11 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A quantitative assessment of diagenetic controls in the lower Sarvak reservoir of an Iranian oil field, Zagros Basin
This study investigates the heterogeneity of geomechanical parameters such as pore pressure, uniaxial compressive strength (UCS) and Young's modulus utilizing the coefficient of variation index in the Lower part of Sarvak Formation, a key reservoir within an oilfield in the Dezful Embayment. The main objective of this study is to establish a genetically based understanding of geomechanical heterogeneity by (1) identifying a representative geomechanical heterogeneity index (CVG), (2) characterizing the controlling mechanisms within each geomechanical facies, and (3) explaining the spatial distribution of geomechanical heterogeneity. Therefore, the effect of main diagenetic parameters such as cementation, dissolution, compaction and dolomitization along with shaliness and fracture intensity on geomechanical parameters variation were investigated. Electrofacies analysis of the reservoir led to the definition of five geomechanical electrofacies, characterized by their individual geomechanical and diagenetic properties. Based on this assessment, diagenetic parameters and shale volume can influence the geomechanical heterogeneity. In addition, in order to distinct the effect of each diagenesis processes on different facies, geomechanical electrofacies analysis can assist. According to this analysis, the effect of diagenesis modifications on heterogeneity in geomechanical facies are different based on its inherent geomechanical properties. In addition, fracture intensity developing can be varied in each geomechanical facies. As a result, this study introduces a new geomechanical coefficient of variation (CVG) heterogeneity index based on CV of three geomechanical properties to evaluate the diagenetic processes and shaliness effects on geomechanical properties which can be used for heteronomous carbonate geomechanical models.
- 11 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA quantitative assessment of diagenetic controls in the lower Sarvak reservoir of an Iranian oil field, Zagros Basin
This study investigates the heterogeneity of geomechanical parameters such as pore pressure, uniaxial compressive strength (UCS) and Young's modulus utilizing the coefficient of variation index in the Lower part of Sarvak Formation, a key reservoir within an oilfield in the Dezful Embayment. The main objective of this study is to establish a genetically based understanding of geomechanical heterogeneity by (1) identifying a representative geomechanical heterogeneity index (CVG), (2) characterizing the controlling mechanisms within each geomechanical facies, and (3) explaining the spatial distribution of geomechanical heterogeneity. Therefore, the effect of main diagenetic parameters such as cementation, dissolution, compaction and dolomitization along with shaliness and fracture intensity on geomechanical parameters variation were investigated. Electrofacies analysis of the reservoir led to the definition of five geomechanical electrofacies, characterized by their individual geomechanical and diagenetic properties. Based on this assessment, diagenetic parameters and shale volume can influence the geomechanical heterogeneity. In addition, in order to distinct the effect of each diagenesis processes on different facies, geomechanical electrofacies analysis can assist. According to this analysis, the effect of diagenesis modifications on heterogeneity in geomechanical facies are different based on its inherent geomechanical properties. In addition, fracture intensity developing can be varied in each geomechanical facies. As a result, this study introduces a new geomechanical coefficient of variation (CVG) heterogeneity index based on CV of three geomechanical properties to evaluate the diagenetic processes and shaliness effects on geomechanical properties which can be used for heteronomous carbonate geomechanical models.
- Open Access
- 1 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Hybrid deep learning and ES-MDA for pressure transient inversion in radial composite reservoirs
Accurate characterization of reservoir heterogeneity is important for improving reservoir management and production forecasting. This study presents a hybrid workflow for permeability estimation in structured radial composite reservoirs using deep learning (DL) and the Ensemble Smoother with Multiple Data Assimilation (ES-MDA). Prior to DL modeling, a quantitative sensitivity and identifiability analysis was performed to evaluate the information content of single-well pressure-transient data. The analysis examined the effects of inner-zone permeability, mobility ratio, and composite radius on pressure-derivative responses, showing that the dominant sensitivities are associated with near-well radial-composite parameters, while sensitivity decreases with increasing radial distance from the well. Two DL architectures-a convolutional neural network (CNN) and a fully connected (FC) network-were evaluated using synthetic pressure-derivative responses generated from radial composite reservoir realizations. The objective of the proposed framework is not to reconstruct arbitrary geological permeability fields, but rather to infer permeability distributions constrained by radial composite reservoir behavior. Both models achieved high prediction accuracy under noise-free conditions, while the CNN demonstrated greater robustness when Gaussian noise was added to the pressure-derivative inputs during testing. For history matching (HM), two initialization strategies were investigated: (i) random radial-composite initialization and (ii) AI-informed initialization derived from CNN predictions. Ten ensemble realizations were generated using ± 5% perturbations, followed by 20 ES-MDA assimilation steps with a constant inflation factor of α = 20. The AI-informed initialization achieved faster convergence and lower final pressure-derivative misfit than the random initialization. Overall, the proposed framework provides an efficient and physically consistent workflow for permeability estimation and history matching in structured radial composite reservoirs.
- 1 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessHybrid deep learning and ES-MDA for pressure transient inversion in radial composite reservoirs
Accurate characterization of reservoir heterogeneity is important for improving reservoir management and production forecasting. This study presents a hybrid workflow for permeability estimation in structured radial composite reservoirs using deep learning (DL) and the Ensemble Smoother with Multiple Data Assimilation (ES-MDA). Prior to DL modeling, a quantitative sensitivity and identifiability analysis was performed to evaluate the information content of single-well pressure-transient data. The analysis examined the effects of inner-zone permeability, mobility ratio, and composite radius on pressure-derivative responses, showing that the dominant sensitivities are associated with near-well radial-composite parameters, while sensitivity decreases with increasing radial distance from the well. Two DL architectures-a convolutional neural network (CNN) and a fully connected (FC) network-were evaluated using synthetic pressure-derivative responses generated from radial composite reservoir realizations. The objective of the proposed framework is not to reconstruct arbitrary geological permeability fields, but rather to infer permeability distributions constrained by radial composite reservoir behavior. Both models achieved high prediction accuracy under noise-free conditions, while the CNN demonstrated greater robustness when Gaussian noise was added to the pressure-derivative inputs during testing. For history matching (HM), two initialization strategies were investigated: (i) random radial-composite initialization and (ii) AI-informed initialization derived from CNN predictions. Ten ensemble realizations were generated using ± 5% perturbations, followed by 20 ES-MDA assimilation steps with a constant inflation factor of α = 20. The AI-informed initialization achieved faster convergence and lower final pressure-derivative misfit than the random initialization. Overall, the proposed framework provides an efficient and physically consistent workflow for permeability estimation and history matching in structured radial composite reservoirs.
- Open Access
- 28 August 2025
- Published by Springer Nature in Journal of Petroleum Exploration and Production Technology
- Vol. 15 (9) , 1-24
Time-aware predictive maintenance of electrical submersible pumps using catboost ensemble learning and trend-based labeling
- 28 August 2025
- Published by Springer Nature in Journal of Petroleum Exploration and Production Technology
- Vol. 15 (9) , 1-24
Open AccessTime-aware predictive maintenance of electrical submersible pumps using catboost ensemble learning and trend-based labeling
- 13 August 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (24) , 20445-20466
A Comprehensive Review of Failure Modes in Electrical Submersible Pumps: Diagnosis, Predictive Maintenance, and Engineer’s Guide
- 13 August 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (24) , 20445-20466
A Comprehensive Review of Failure Modes in Electrical Submersible Pumps: Diagnosis, Predictive Maintenance, and Engineer’s Guide
- Open Access
- 26 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Correction: Formation permeability estimation using mud loss data by deep learning
- 26 May 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Open AccessCorrection: Formation permeability estimation using mud loss data by deep learning
- Open Access
- 30 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Formation permeability estimation using mud loss data by deep learning
Permeability estimation plays an essential role in the assessment of reservoirs and hydrocarbon extraction. There are various methods to evaluate the formation and estimate the formation permeability, but in some cases, the evaluation may not be done or it may not be done correctly. This study focuses on a novel method to estimate the formation’s permeability with appropriate accuracy using the mud loss data. Machine learning applications are becoming more popular nowadays and can succeed in many fields. This current research focuses on the application of mud loss data and deep learning to estimate the formation’s permeability. To implement and validate our methodology, it is considered pilot cases including reservoir and drilling parameters values (depth, formation type, formation thickness, mud density, mud viscosity, and formation permeability). It is assumed that mud loss was occurred because of deferential pressure between formation pressure and bottom-hole pressure. The mud loss rate data were generated at different sets of reservoir and drilling data values using a reservoir simulator and then evaluated by calculating the correlation coefficients to ensure their validity and to check the fit under real conditions. This can be used to estimate the formation permeability values. One-dimensional convolutional neural networks(1D-CNN), a type of convolutional neural network, is utilized to be trained with data to perform a regression problem based on the contribution of flattening, dropout, and fully connected layers to estimate permeability with high accuracy (training data R2 = 0.970, testing data R2 = 0.964). Then the new deep learning method, Deep jointly informed neural network (DJINN), with the cooperation of neural networks and decision trees, provides a more accurate model than 1D-CNN (training data R2 = 0.978, testing data R2 = 0.972). These descriptions may provide new applications for mud loss data, where data while drilling can be used to predict formation permeability and provide insights for petroleum engineers to accurately measure design.
- 30 April 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Open AccessFormation permeability estimation using mud loss data by deep learning
Permeability estimation plays an essential role in the assessment of reservoirs and hydrocarbon extraction. There are various methods to evaluate the formation and estimate the formation permeability, but in some cases, the evaluation may not be done or it may not be done correctly. This study focuses on a novel method to estimate the formation’s permeability with appropriate accuracy using the mud loss data. Machine learning applications are becoming more popular nowadays and can succeed in many fields. This current research focuses on the application of mud loss data and deep learning to estimate the formation’s permeability. To implement and validate our methodology, it is considered pilot cases including reservoir and drilling parameters values (depth, formation type, formation thickness, mud density, mud viscosity, and formation permeability). It is assumed that mud loss was occurred because of deferential pressure between formation pressure and bottom-hole pressure. The mud loss rate data were generated at different sets of reservoir and drilling data values using a reservoir simulator and then evaluated by calculating the correlation coefficients to ensure their validity and to check the fit under real conditions. This can be used to estimate the formation permeability values. One-dimensional convolutional neural networks(1D-CNN), a type of convolutional neural network, is utilized to be trained with data to perform a regression problem based on the contribution of flattening, dropout, and fully connected layers to estimate permeability with high accuracy (training data R2 = 0.970, testing data R2 = 0.964). Then the new deep learning method, Deep jointly informed neural network (DJINN), with the cooperation of neural networks and decision trees, provides a more accurate model than 1D-CNN (training data R2 = 0.978, testing data R2 = 0.972). These descriptions may provide new applications for mud loss data, where data while drilling can be used to predict formation permeability and provide insights for petroleum engineers to accurately measure design.
- Open Access
Correction: Alizadeh et al. Comprehensive Review of Carbon Capture and Storage Integration in Hydrogen Production: Opportunities, Challenges, and Future Perspectives. Energies 2024, 17, 5330
Due to some mistakes made when formatting and organizing the References Section, some references need to be updated in
Open AccessCorrection: Alizadeh et al. Comprehensive Review of Carbon Capture and Storage Integration in Hydrogen Production: Opportunities, Challenges, and Future Perspectives. Energies 2024, 17, 5330
Due to some mistakes made when formatting and organizing the References Section, some references need to be updated in