DCDaniele Colombo

Daniele Colombo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Daniele Colombo has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Agentic Full-Waveform Inversion Using Local and Global Optimizers

    by Daniele Colombo, Runhai Feng, Ersan Turkoglu, Ernesto Sandoval-Curiel

  • Velocity model building via wellbore-supervised learning: Applications with 3D seismic and helicopter-borne transient electromagnetics

    by Daniele Colombo, Ersan Turkoglu, Ernesto Sandoval-Curiel

    The shallow subsurface, particularly in arid regions, presents substantial challenges for seismic exploration due to pronounced velocity heterogeneities in the vertical and horizontal dimensions. Traditional refraction-based traveltime inversion techniques face significant limitations in resolving shallow velocity reversals, while full-waveform inversion approaches are difficult to apply in land seismic environments. Areas characterized by intensive seismic exploration typically provide velocity calibration from wells in the form of shallow upholes, deep check shots, and sonic logs that can be used to support velocity model building by 3D seismic data. The use of wellbore velocity information for calibrating inversion-based 3D velocity modeling typically relies on interpretative and highly subjective methods. We develop algorithms and software based on statistics and machine learning, which provide a seamless integration of sparse borehole velocity calibrations with 3D surface seismic data sets for velocity model building. The result is the construction of accurate 3D velocity models calibrated by well data. Seismic gathers with multiwave arrivals or other high-resolution geophysical data, such as helicopter-borne transient electromagnetics, are used as input. The effectiveness of the approach is demonstrated through applications to the synthetic SEAM Arid Model and to field data acquired in complex near-surface and overburden conditions.


  • Self-supervised active learning inversion: Transient electromagnetics and full-waveform seismic

    by Daniele Colombo, Ersan Turkoglu

    Supervised learning requires training samples extracted from a probability distribution compatible with the data to be tested in the inference step. We develop a self-supervised machine learning inversion scheme able to learn directly from field data by using physics as the auxiliary task for generating training labels. The self-supervised online learning process is achieved through the combination of multiple learning paradigms. Active learning selects the most informative samples of a data pool. Unsupervised learning quantifies diversity in the data. Reinforcement learning explores the parameter space through a physics-based agent and generates labels. The labeled data pool is then used for supervised learning. The iterative process involves data augmentation at each cycle and results in a gradual steering of the learning toward the field data distribution. Several benefits are provided to the inversion of geophysical data by introducing nonlinearity and stochastic processes while reducing, at the same time, the computer resource utilization. Offline training involving expensive forward modeling operations is eliminated where field data become the source of online learning. Self-supervised active learning inversion is of immense impact for field data applications. Exploration-scale implementations include the inversion of helicopter-borne transient electromagnetics and land seismic full-waveform inversion in complex geologic settings. The developed self-supervised active learning inversion scheme is likely generalized to a tutorial for a variety of scientific applications.


  • Multiphysics framework for cost-effective, long-term monitoring of carbon storage in a carbonate reservoir

    by Taqi Alyousuf, Daniele Colombo, Ersan Turkoglu, Muhammad Almajid, Mohammed Shawaf, Mohammed Ali

    We evaluate an effective and cost-efficient multiphysics approach for long-term monitoring of carbon storage in carbonate reservoirs. A key focus of our study is to advocate for a cost-effective, long-term monitoring strategy for carbon storage projects through the integration of surface and borehole multiphysics measurements. By leveraging technologies related to electromagnetic (EM) and gravity methods, we present a framework that addresses the monitoring of the dynamic behavior of injected CO2 over an extended period. The modeling setup integrates realistic static reservoir models with simulated dynamic saturation models to provide results as close as possible to real experimental conditions. Results demonstrate the high sensitivity of EM fields to changes in reservoir CO2 saturation, especially when surface-to-reservoir acquisition configurations are adopted. Additionally, gravity simulations, employing three-axis vector surface gravity measurements and borehole vector gravity, effectively capture density variations over time. Our proposed framework highlights the sequential use of seismic imaging for preinjection site characterization and the transition to EM and gravity surveys for continuous monitoring during and after the injection phases. The multiphysics simulation results performed on realistic carbon storage conditions contribute to the evolving landscape of effective geophysical CO2 monitoring technology for reliable long-term reservoir management.


  • Ultra-dense nodal seismic acquisition for automated geohazard analysis

    by Daniele Colombo, Ernesto Sandoval-Curiel, Taqi Alyousuf, Ersan Turkoglu, Diego Rovetta

    In this paper, we address the problem of shallow geohazard mapping by developing an integrated workflow consisting of nodal seismic acquisition and automated data analysis. Densely spaced point-receiver land nodes and point sources are adopted as an alternative to receiver arrays or groups conventionally used in seismic exploration. The recently developed methodology of surface-consistent decomposition of the transmitted wavefield is applied to the nodal data. Ultra-resolution mapping of surface-consistent attributes in amplitude and phase is obtained, together with the generation of high-energy signal beams at the common midpoint positions, forming virtual (shot) supergathers (VSGs). The VSG preserves frequency and true-amplitude content thanks to the surface-consistent corrections applied before beam forming. Traveltimes, waveforms, and surface waves are then analyzed in the high signal-to-noise ratio VSG, leading to inversion of the subsurface parameters. Human-intensive interpretation of surface-wave dispersion curves in the f-k spectra is facilitated by the introduction of efficient machine learning algorithms for the unsupervised and supervised paradigms. The ultra-dense nodal acquisition and automated data analysis are effectively applied to the analysis of several cases of near-surface geohazards.


  • Advances in hydraulic fracture characterization via borehole microseismic and strain monitoring

    by Yazeed Altowairqi, Hala Alqatari, Daniele Colombo, Ersan Turkoglu

    We analyze the impact and challenges associated with microseismic monitoring in the development of unconventional reservoirs. We detail advanced methods that address some of these challenges and discuss emerging data analysis and acquisition technologies such as those provided by fiber-optic monitoring. During the development of unconventional resources, it is important to understand the stimulated rock volume obtained from the hydraulic fracturing treatment. Microseismic monitoring is one of the sources of information for estimating stimulated rock volume in which accurate hypocenter calculations provide the horizontal and vertical fracture geometry and extent. We developed hypocenter waveform-based relocation and collapsing techniques and demonstrated these on synthetic and field data to obtain an enhanced description of the fracture geometry. We further provide the initial analysis of a recently acquired data set composed of multiple monitoring wells instrumented with geophones and fiber optics operating simultaneously. Microseismic events recorded by the multiwell dual geophone/fiber setup show meaningful signal-to-noise ratio to enable a joint interpretation. Additional strain and temperature data provided by dynamic fiber-optic measurements extend the interpretation capabilities of the hydraulic fracturing phenomenon while providing an avenue for advanced research on fracture characterization.


  • Self-supervised, active learning seismic full-waveform inversion

    by Daniele Colombo, Ersan Turkoglu, Ernesto Sandoval-Curiel, Taqi Alyousuf

    A novel recursive, self-supervised machine-learning (ML) inversion scheme is developed. It is applied for fast and accurate full-waveform inversion of land seismic data. ML generalization is enhanced by using virtual super gathers (VSGs) of field data for training. These are obtained from midpoint-offset sorting and stacking after applying surface-consistent corrections from the decomposition of the transmitted wavefield. The procedure implements reinforcement learning concepts by adopting an inversion agent to interact with the environment and explore the model space under a data misfit optimization policy. The generated parameter distributions and related forward responses are used as new training samples for supervised learning. The active learning (AL) paradigm is further embedded in the procedure, for which queries on data diversity and uncertainty are used to generate fully informative reduced sets for training. The procedure is recursive. At each cycle, the physics-based inversion is coupled to the ML predictions via penalty terms that promote a long-term data misfit reduction. The resulting self-supervised, AL, physics-driven deep-learning inversion generalizes well with field data. The method is applied to perform full-waveform inversion (FWI) of a complex land seismic data set characterized by transcurrent faulting and related structures. High signal-to-noise VSGs are inverted with a 1.5D Laplace-Fourier FWI scheme. The AL inversion procedure uses a small fraction of data for training while achieving sharper velocity reconstructions and a lower data misfit when compared with previous results. AL FWI is highly generalizable and effective for land seismic velocity model building and for other inversion scenarios.


  • Ultra‐resolution surface‐consistent full waveform inversion

    by Daniele Colombo, Ernesto Sandoval‐Curiel, Ersan Turkoglu, Diego Rovetta, Apostolos Kontakis

    Full waveform inversion for land seismic data requires the development of specific strategies for modelling the complex response associated to the near surface. Seismic wave propagation is distorted by several effects, such as topographic relief, wavefield scattering, attenuation (often frequency‐dependent) and anisotropy. The modelling of such shallow complexities is often unmanageable by parametric inversions such that data preconditioning and surface‐related corrections are required before tackling the full waveform inversion velocity modelling problem. We developed a unified framework addressing both surface‐consistent corrections and full waveform inversion by using the transmitted portion of the wavefield. The problem of surface‐consistent decomposition is recast in terms of the transmitted wavefield leading to kinematic and dynamic corrections to account for sub‐resolution wave propagation distortions occurring in the near surface weathering layer. Seismic data are deconvolved from the effects of the near surface to better represent the deeper subsurface wavefield propagation. Signal‐to‐noise enhancement is obtained after the surface‐consistent transmission preconditioning by the generation of virtual super gathers reconstructed in the midpoint‐offset sorting domain. An original scheme of 1.5D Laplace–Fourier full waveform inversion, involving 3D radiation and 1D velocity inversion, is then applied for the velocity reconstruction where the amplitude information of the seismic data is fully preserved and utilized. The unified approach of surface‐consistent transmission preconditioning and velocity modelling is demonstrated on the Society of Exploration Geophysicists Advanced Modelling arid model dataset as well as on two complex field datasets containing near surface complexities typical of arid regions. The approach provides the solution of the near surface distortions by performing data preconditioning and velocity inversions in a unified scheme. The surface‐consistent full waveform inversion approach has been utilized for large land seismic projects and represents a robust tool for supporting land seismic imaging.


  • Efficient 1.5D full waveform inversion in the Laplace-Fourier domain

    by Apostolos Kontakis, Diego Rovetta, Daniele Colombo, Ernesto Sandoval-Curiel

    Accurate near-surface characterization and velocity model building are important for a number of geotechnical and geophysical applications. 3D full waveform inversion (FWI) can be used to generate a detailed velocity model, but must be provided with a good initial velocity model. A method for producing such an initial velocity model is explored in this paper. Assuming that the near-subsurface can be locally approximated by an effective flat-layered medium, a specialized form of acoustic FWI is proposed. The inversion is based on regularized least-squares in the Laplace-Fourier domain as a measure to mitigate the cycle-skipping problem. Forward modeling is carried out by solving a number of independent finite-difference problems in parallel, for a set of horizontal wavenumbers. The set is determined adaptively, using a pair of algorithms discussed in detail. A numerical implementation of the inverse Hankel transform, used to synthesize data in the frequency-offset domain, is also described. The forward modeling scheme is validated against analytic solutions of the Helmholtz equation, showing good agreement between the two. FWI is tested by inverting a synthetic dataset consisting of flat layers with embedded velocity anomalies. Important features are recovered after inversion at a small number of complex frequencies, providing a detailed initial model for successive 3D FWI.


  • Machine-learning inversion via adaptive learning and statistical sampling: Application to airborne micro-TEM for seismic sand corrections

    by Daniele Colombo, Ersan Turkoglu, Ernesto Sandoval-Curiel, Diego Rovetta, Weichang Li

    We develop a novel physics-adaptive machine-learning (ML) inversion scheme showing optimal generalization capabilities for field data applications. We apply the physics-driven deep-learning inversion to a massive helicopter-borne transient electromagnetic (TEM) field data set. The objective is the accurate modeling of the near surface for enhancing the exploration of low-relief structures in a sand covered desertic area. Enhanced generalization of a neural network (NN) or other ML techniques is obtained from automatic physics-based adaptive training using images of real-world data. Data reduction schemes, based on statistical sampling techniques, enable the use of small and fully informative data sets for accelerated training. Adaptive learning is implemented via an iterative physics-driven data augmentation strategy. A deterministic inversion is regularized by a penalty term built from the difference between the inverted models and the models predicted by ML. The resulting inverted models and calculated responses are used for augmenting the ML training base. The automated procedure converges rapidly, producing a trained network model, which captures the general background data statistics as well as the characteristics of field-specific geophysical data as embedded in the augmented samples. The high-resolution ML inversions with acceptable levels of data misfit are obtained for large volumes of the field geophysical data. We test several different learning models, such as artificial NNs, convolutional NN (U-Net), and the Gaussian process, which provide stable and comparable results with network-specific characteristics. The developed scheme is successfully applied to micro-TEM data providing accurate near-surface seismic corrections for the exploration of low-relief structures.