PhD Exploration Seismology
Master in Eartquake Seismology
Bachelor in Geology
RESEARCH, TEACHING, or OTHER INTERESTS
Earth and Planetary Sciences, Geophysics, Acoustics and Ultrasonics, Artificial Intelligence
54
Scopus Publications
864
Scholar Citations
16
Scholar h-index
21
Scholar i10-index
Scopus Publications
Integrated characterization of an active fault, insights from fault geometry, roughness and properties Anita Torabi, Behzad Alaei, Abhisek Basa, Juan Jiménez-Millán, Rosario Jiménez Espinosa, Francisco Juan García-Tortosa, Isabel Abad Physics and Chemistry of the Earth, 2026 Fault planes are geometrically rough and non-planar due to their frictional properties. The impact of active faults on the host rock properties is a dynamic process that affects the fluid flow around the fault and hence the mineralogy of both the host rock and the fault rocks. These would influence the stiffness of fault rocks, the size of potential earthquakes and the location of rupture nucleation. In this study, we have investigated a well-exposed active fault plane in Granada Basin, through photogrammetry of outcrops (drone imagery), structural measurements and frequency distribution of fault and fractures as well as non-destructive measurements of permeability and Young’s modulus. Furthermore, we have estimated roughness on the images of the main fault plane by a novel approach utilizing Root Mean Square intensity distribution. This is the first integrated study that relates the distribution of faults and fractures to the fault rock properties and roughness on an active fault. Young’s moduli values are higher, while permeability values are lower, where the fault rocks are exposed corresponding to the locations of minor faults cutting through the main fault plane. These locations show higher roughness on the images of the fault plane. The observed fault rocks of the fault core encompass enhanced granulation and wearing process during the fault slip. This integration of different data contributes to a better understanding of active faults and their properties, which eventually be important for the knowledge of fault seismicity in the future. • Fault roughness was estimated on the drone images of an active fault plane by a novel approach utilizing Root Mean Square intensity distribution. • Young’s moduli values are higher, while permeability values are lower, where the fault rocks are exposed corresponding to the locations of minor faults cutting through the main fault plane. • There is higher roughness on the fault plane where minor faults and fault rocks are present.
Detailed 3D characterization of fault geometric attributes: Insights from deep learning-based fault imaging in seismic data Abhisek Basa, Behzad Alaei, Anita Torabi Journal of Structural Geology, 2026 Generation of 3D fault network in conventional seismic interpretation involves creation of structural models by manually tracking the same discontinuity across seismic horizons on several adjacent vertical profiles. This process is often time-consuming, susceptible to human bias and introduces uncertainties in the characterization of fault geometric attributes-such as length, width and throw-that cannot be reliably quantified. In this study, we adopt a data-driven approach and extract the geometric attributes of the individual segments constituting the 3D seismic fault zone architecture in remarkable detail, that provides insights beyond the capabilities of conventional seismic attributes. This is achieved through the application of 3D Deep Learning (DL) Networks trained on 3D synthetic seismic datasets on a seismic survey from the eastern flank of Polhem Subplatform, SW of Norwegian Barents Sea to automatically create probabilistic fault volumes. Detailed extraction of individual fault segments from the fault probability volume allows us to investigate the seismic fault zone architecture at multiple scales. Our results show that the maximum segment length of all the studied faults is present near the upper tips and reduces towards the lower tips. The fault zone widths of individual segments measured on E-W-oriented vertical scanplanes orthogonal to the strike of the dominant fault set mostly vary between 10-20m. They exhibit higher values at locations where fault segments link laterally/vertically or interact with antithetic fault sets with similar strike of the dominant westward dipping fault set. Throw estimates and the total accumulated fault zone widths are higher towards the lower tips of the faults. Thus, the application of Deep Learning enables data-driven, high-resolution visualization of the seismic fault zone architecture and facilitates comprehensive extraction of fault geometric attributes, providing a more robust complement to traditional interpretation techniques. • Detailed fault geometric attributes in 3D are extracted from deep-learning-based fault imaging of seismic data. • Central portion of the fault zones exhibits most continuous segments. • Width of most segments in the studied fault zones are 10–20 m. • Total accumulated width of segments increases towards the lower tips of fault zones. • Throw estimated below the Upper Barremian Unconformity is higher than above it.
ML-Driven Reservoir Characterization Case Study in D Field PM Basin Malaysia N. Nguyen, B. Alaei, D. Austin, S. Rajput Eage Workshop on Advanced Seismic Solutions for Complex Reservoir Challenges, 2025 Summary This study heralds a new era in geoscience, showcasing the revolutionary impact of Artificial Intelligence (AI) and Machine Learning (ML) technologies in maximizing the utility of subsurface data for energy production. Focused on the D field offshore Malaysia, it unveils the critical role of AI/ML in unraveling the complexities of the seismic inverse problem, facilitating the accurate prediction of elastic and reservoir properties from seismic data. The research distinguishes itself through a sophisticated methodology that leverages AI/ML technologies for a comprehensive workflow encompassing data preparation, well scale quality control, and seismic scale property prediction. This approach not only fills existing data voids but also underscores the scalability and efficacy of AI/ML solutions in geophysical research. The findings emphasize the paramount importance of robust data quality control and the strategic application of pre-trained models to enhance predictive accuracy and operational efficiency. By pioneering the use of AI/ML in geoscience, this study marks a significant milestone in the evolution of energy resource exploration and management, setting a precedent for future technological advancements in the field.
A Case Study Integrating Model Uncertainty, Foundation Models and Physics-Informed Neural Networks for Reservoir Characterization E. Larsen, A.K. Kvalheim, T. Citraningtyas, D. Oikonomou, B. Alaei 86th Eage Annual Conference and Exhibition, 2025 Summary Carbon storage sites are often developed in saline aquifers with limited local well data, rather than in data-rich abandoned oil and gas fields. We therefore need to make sure that reservoir characterization methods that we are using as time and cost efficient as well as accurate, reliable, and robust to work in such low-data environments. To achieve this, incorporating approaches to quantify uncertainty is vital. Two uncertainty quantification methods are particularly relevant for this context: Monte Carlo dropout (Approach 1) and implicit model ensemble averaging (Approach 2). Monte Carlo dropout acts as a regularization technique, switching off neurons randomly during iterations, both in training and inference steps. This creates a dynamic architecture where information is distributed more evenly, and the variance of predictions across iterations provides bounds for prediction uncertainty. Such a method enhances reliability in low-data scenarios, where overfitting is a concern. Implicit model ensemble averaging leverages ensemble stacking, where multiple retrained models are combined, either by averaging (for continuous data) or majority voting (for categorical data). This approach provides statistical measures of uncertainty in property predictions by capturing the variability across models, enabling robust decision-making in the face of limited data availability.
Reservoir elastic properties prediction using supervised deep learning versus model-based inversion methods N. Ahmed, D. Oikonomou, N.F.C. Diaz, B. Alaei, E. Larsen, et al. 86th Eage Annual Conference and Exhibition, 2025 Summary This work focuses on a 3D supervised deep machine learning method for predicting reservoir elastic properties from partial-angle stack seismic data. Using well-log data from several well locations from Troll field in the North sea and 3D interval velocity volume, we train a deep convolutional neural network to estimate elastic properties such as P and S waves velocities and density from seismic partial stacks. Furthermore, we have also make a comparison between the deep learning predictions with the model-based seismic inversion methods including Bayesian linearized inversion and stochastic nonlinear inversion schemes. The applications tests on well logs and seismic field data demonstrate that deep learning method can effectively predict property volumes with good lateral continuity as compared to traditional model based inversion techniques. Estimation of these elastic properties allows obtaining other rock properties such as porosity, saturation, and shale volume, which are important for reservoir rock characterization.
Implications of depth conversion on fault geometries and fault-risk assessment in the Smeaheia CO2 storage site, northern North Sea Nora Holden, Behzad Alaei, Elin Skurtveit, Alvar Braathen Geoenergy, 2024 Assessments of fault geometries and fault-risk parameters are crucial when evaluating the integrity of a structurally controlled CO 2 storage site. To perform these assessments, seismic data, recorded in time, must be converted to depth. The velocity models used for this time to depth conversion influence the final depth image and, consequently, the geometry of the interpreted faults. Against this background, we created four velocity models for depth conversion, assessed the impact on fault throw, dip and thickness of the primary seal, and, subsequently, a fault-risk assessment of the Vette Fault Zone in the Smeaheia CO 2 storage site. We found that depth conversion had a larger influence on fault throw and thickness of the primary seal than on fault dip. In contrast, the overall assessment of the presence of a membrane seal and geomechanical integrity showed less sensitivity to the depth conversion process. Consequently, we suggest that a relatively robust fault-risk assessment can be made with a variety of velocity model designs and data input. Nevertheless, we found a mean difference of 2% in the shale gouge ratio, 4% in the slip tendency and 9% in the dilation tendency for the Vette Fault Zone, emphasizing the importance of accounting for the influence of depth conversion in optimizing structural assessments in potential CO 2 storage sites.
Fault asperity and roughness, insight from faults in 3D reflection seismic data Behzad Alaei, Anita Torabi Marine and Petroleum Geology, 2024 The complexity of faults and the bias in the gathered fault data from different sources such as outcrops, reflection seismic data and earthquakes causes uncertainty to the understanding of fault plane geometry at the seismic scale, among other fault geometric attributes. Fault plane roughness and irregularities at different scales are important geometric attributes caused by asperities, which are linked to the fault frictional behaviour and mechanics. Asperities are localized areas with higher strength on the fault plane, which resist the applied stress to a certain limit before the fault ruptures. Imaging faults’ real geometry can help us to gain more insight into the fault roughness and asperities, thereby enhancing our understanding of the mechanics of faulting and earthquakes. In this study, for the first time, we map fault asperities and roughness on seismic scale faults using their 3D structures extracted from reflection seismic data. We have studied 21 normal faults ranging in depth from about 0.5 to 3 km with clastic dominated lithology and some carbonates by extracting and characterizing their true fault plane geometry on 3D reflection seismic data using Gaussian filtered coherency attributes and measuring throw over the entire fault plane. The outline of the mapped asperities is the envelope of internal tip-points between the segments on the fault plane 3D structure. Our results show that in most cases, at the boundary of the asperities, the strike of fault internal segments changes and the throw increases. We have introduced two new attributes characterizing fault plane roughness at seismic scale, notably 2D roughness attribute and segment mean roughness. The variations of these two attributes, i.e. higher values near the asperity boundary, have close link to the locations of asperities on the fault planes. • Faults 3D shapes were characterized on seismic data using Gaussian filtered coherency attributes and throw measurements. • Fault asperities on internal tip-points between the fault segments were mapped on the 3D fault structures. • At the location of asperities, the strike of fault segments change, and the throw increases. • Two new attributes were introduced to assess fault plane roughness at seismic scale: 2D roughness and segment mean roughness.
Integrated Machine Learning Approaches for Accelerated Understanding of Sand Injectites-Fault Relationships in Exploration and CO2 Storage 85th Eage Annual Conference and Exhibition 2024, 2024
A multi-model AI workflow - integrating from rock samples to basin-scale seismic-based rock property prediction 84th Eage Annual Conference and Exhibition, 2023
Missed pay identification using machine learning - A case study D. Stoddart, G. Valeras, A. Papapostolou, G. Xenogiannopoulos, D. Oikonomou, B. Alaei, D. Austin, E. Larsen, I. Martin, E. Zabihi Naeini Eage AAPG Digital Subsurface for Asia Pacific Conference 2020, 2020
Towards subsurface ML metrics S. Purves, B. Alaei, D. Lolis 81st Eage Conference and Exhibition 2019 Workshop Programme, 2019
The digital underground: Integrating petroleum geoscience with data science principles to create an intelligent subsurface platform Eage Subsurface Intelligence Workshop 2019, 2019
Seismic forward modelling of two fault-related folds from the Dezful Embayment of the Iranian Zagros Mountains Journal of Seismic Exploration, 2005
RECENT SCHOLAR PUBLICATIONS
Integrated characterization of an active fault, insights from fault geometry, roughness and properties A Torabi, B Alaei, A Basa, J Jiménez-Millán, RJ Espinosa, ... Physics and Chemistry of the Earth, Parts A/B/C, 104346 , 2026 2026
Detailed 3D characterization of fault geometric attributes: Insights from deep learning-based fault imaging in seismic data A Basa, B Alaei, A Torabi Journal of Structural Geology, 105569 , 2025 2025
Tectonic control and geometric characterization of hydrothermal vent complex using seismic data, Potiguar Basin–Brazil LSB Oliveira, LCV Lucas, D Iacopini, F Balsamo, A Torabi, B Alaei, ... EGUsphere 2025, 1-47 , 2025 2025
Fault Geometric Characterization: Insights from Deep Learning Applied to High Resolution 3D Seismic Data O Silio, B Alaei, A Torabi Seventh International Conference on Fault and Top Seals 2025 (1), 1-5 , 2025 2025
A New Approach to Multi-Scale Characterization of the 3D Seismic Fault Zone Architecture using Deep Learning A Basa, B Alaei, A Torabi Seventh International Conference on Fault and Top Seals 2025 (1), 1-5 , 2025 2025
Fault Architecture and Roughness A Torabi, B Alaei Seventh International Conference on Fault and Top Seals 2025 (1), 1-5 , 2025 2025
Influence of growth fault complexities on fault seal assessments in the Smeaheia CO2 storage site, northern North Sea N Holden, E Skurtveit, B Alaei, I Midtkandal, A Braathen Journal of Structural Geology, 105501 , 2025 2025 Citations: 2
Reservoir elastic properties prediction using supervised deep learning versus model-based inversion methods N Ahmed, D Oikonomou, NFC Diaz, B Alaei, E Larsen, H Nguyen 86th EAGE Annual Conference & Exhibition 2025 (1), 1-5 , 2025 2025 Citations: 7
ML-Driven Reservoir Characterization Case Study in D Field PM Basin Malaysia N Nguyen, B Alaei, D Austin, S Rajput EAGE Workshop on Advanced Seismic Solutions for Complex Reservoir Challenges … , 2025 2025
Unraveling the key factors controlling active faulting in Tertiary and Quaternary sequences A Basa, A Torabi, J Jiménez-Millán, B Alaei, FJ Garcia-Tortosa Earth and Planetary Science Letters 656, 119268 , 2025 2025 Citations: 3
Legacy Insights to Modern CCS Evaluation: An Integrated Approach to Optimising Subsurface Suitability Analysis M Powney, J Masi, T Citraningtyas, B Alaei, S Cornelius, F Dias, P Emmet First Break 43 (2), 35-41 , 2025 2025
Implications of depth conversion on fault geometries and fault-risk assessment in the Smeaheia CO2 storage site, northern North Sea N Holden, B Alaei, E Skurtveit, A Braathen Geoenergy 2 (1), geoenergy2024-006 , 2024 2024 Citations: 6
Seismic and outcrop-based 3D characterization of fault damage zones in sandstones, Rio do Peixe Basin, Brazil LSB Oliveira, FCC Nogueira, DL Vasconcelos, A Torabi, B Alaei, ... Journal of Structural Geology 189, 105276 , 2024 2024 Citations: 5
Fault asperity and roughness, insight from faults in 3D reflection seismic data B Alaei, A Torabi Marine and Petroleum Geology 170, 107145 , 2024 2024 Citations: 8
Fault characteristics in exhumed basement rocks; implications for understanding subsurface basement faults A Torabi, B Alaei, A Smith Tectonophysics 887, 230445 , 2024 2024 Citations: 2
Machine learning-based Vs prediction of Utsira Formation NH Mondol, B Alaei 85th EAGE Annual Conference & Exhibition 2024 (1), 1-5 , 2024 2024
Integrated Machine Learning Approaches for Accelerated Understanding of Sand Injectites-Fault Relationships in Exploration and CO2 Storage H Nguyen, E Larsen, D Evans, D Oikonomou, TM Citraningtyas, B Alaei 85th EAGE Annual Conference & Exhibition 2024 (1), 1-5 , 2024 2024 Citations: 2
Data augmentation for 3D seismic fault interpretation using deep learning W Bönke, B Alaei, A Torabi, D Oikonomou Marine and Petroleum Geology 162, 106706 , 2024 2024 Citations: 26
Automatic 3D fault detection and characterization—A comparison between seismic attribute methods and deep learning LSB Brito, B Alaei, A Torabi, KM Leopoldino-Oliveira, D Lino Vasconcelos, ... Interpretation 11 (4), T793-T808 , 2023 2023 Citations: 16
Legacy Learnings to Future Insight–Characterising CCUS Sites Using Legacy Data with Machine Learning M Powney, J Masi, D Austin, T Citraningtyas, M Dyrendahl, B Alaei, ... First EAGE Workshop on Hydrogen & CCS in LATAM 2023 (1), 1-4 , 2023 2023
MOST CITED SCHOLAR PUBLICATIONS
Fault zone architecture and its scaling laws: where does the damage zone start and stop? A Torabi, TSS Ellingsen, MU Johannessen, B Alaei, A Rotevatn, ... 2020 Citations: 133
Application of spatial correlation functions in permeability estimation of deformation bands in porous rocks A Torabi, H Fossen, B Alaei Journal of Geophysical Research: Solid Earth 113 (B8) , 2008 2008 Citations: 70
Normal fault 3D geometry and displacement revisited: Insights from faults in the Norwegian Barents Sea A Torabi, B Alaei, A Libak Marine and Petroleum Geology 99, 135-155 , 2019 2019 Citations: 69
Seismic imaging of fault damaged zone and its scaling relation with displacement B Alaei, A Torabi Interpretation 5 (4), SP83-SP93 , 2017 2017 Citations: 51
Fault visualization and identification in fault seismic attribute volumes: Implications for fault geometric characterization A Libak, B Alaei, A Torabi Interpretation 5 (2), B1-B16 , 2017 2017 Citations: 48
Seismic modeling of complex geological structures B Alaei Seismic Waves-Research and Analysis 11, 528-529 , 2012 2012 Citations: 46
Faults and fractures in basement rocks, their architecture, petrophysical and mechanical properties A Torabi, B Alaei, TSS Ellingsen Journal of Structural Geology 117, 256-263 , 2018 2018 Citations: 38
Analysis of fault scaling relations using fault seismic attributes A Torabi, B Alaei, D Kolyukhin Geophysical Prospecting 65 (2), 581-595 , 2017 2017 Citations: 33
Clinoform development and topset evolution in a mud‐rich delta–the Middle Triassic Kobbe Formation, Norwegian Barents Sea TG Klausen, JA Torland, CH Eide, B Alaei, S Olaussen, D Chiarella Sedimentology 65 (4), 1132-1169 , 2018 2018 Citations: 32
Envisioning faults beyond the framework of fracture mechanics A Torabi, J Rudnicki, B Alaei, G Buscarnera Earth-Science Reviews 238, 104358 , 2023 2023 Citations: 29
Data augmentation for 3D seismic fault interpretation using deep learning W Bönke, B Alaei, A Torabi, D Oikonomou Marine and Petroleum Geology 162, 106706 , 2024 2024 Citations: 26
Geological modelling and finite difference forward realization of a regional section from the Zagros fold-and-thrust belt B Alaei, SA Petersen Petroleum Geoscience 13 (3), 241-251 , 2007 2007 Citations: 24
An integrated procedure for migration velocity analysis in complex structures of thrust belts B Alaei Journal of Applied Geophysics 59 (2), 89-105 , 2006 2006 Citations: 24
Improved fault imaging by integration of frequency decomposition and fault attributes, example from mid Norwegian sea B Alaei 3rd EAGE International Conference on Fault and Top Seals, cp-311-00036 , 2012 2012 Citations: 17
Automatic 3D fault detection and characterization—A comparison between seismic attribute methods and deep learning LSB Brito, B Alaei, A Torabi, KM Leopoldino-Oliveira, D Lino Vasconcelos, ... Interpretation 11 (4), T793-T808 , 2023 2023 Citations: 16
Is machine learning taking productivity in petroleum geoscience on a Moore’s Law trajectory? E Larsen, SJ Purves, D Economou, B Alaei First Break 36 (12), 135-141 , 2018 2018 Citations: 16
Single arrival Kirchhoff prestack depth migration of complex faulted folds from the Zagros mountains, Iran B Alaei, J Pajchel CSEG Recorder 31 (1), 41-48 , 2006 2006 Citations: 16
Fault geometric and seismic attributes–an integrated study with focus on the Barents Sea A Torabi, B Alaei, D Kolyukhin, RH Libak, RH Gabrielsen, A Braathen First Break 34 (5) , 2016 2016 Citations: 15
Assessing the accuracy of fault interpretation using machine-learning techniques when risking faults for CO 2 storage site assessment EAH Michie, B Alaei, A Braathen Interpretation 10 (1), T73-T93 , 2022 2022 Citations: 12
EarthNET a native cloud web based solution for next generation subsurface workflows D Oikonomou, E Larsen, B Alaei, G Stefos, S Purves 81st EAGE Conference and Exhibition 2019 Workshop Programme 2019 (1), 1-4 , 2019 2019 Citations: 12
