Rafael Orozco

Rafael Orozco

Auto-generated profile, based on publicly available information

Rafael Orozco

Georgia Institute of Technology 1 , School of Computational Science and Engineering, Atlanta, Georgia, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 February 2023 in Geophysics
Verified
Journal Article
Closed access
ASAli Siahkoohi
Ali Siahkoohi
GRGabrio Rizzuti
Gabrio Rizzuti
RORafael Orozco
Rafael Orozco
FHFelix J. Herrmann
Felix J. Herrmann
Bayesian inference for high-dimensional inverse problems is computationally costly and requires selecting a suitable prior distribution. Amortized variational inference addresses these challenges by pretraining a neural network that acts as a surrogate conditional distribution that approximates the posterior distribution not only for one instance of the observed data but also for the distribution of the data pertaining to a specific inverse problem. When fed previously unseen data, the neural network — in our case, a conditional normalizing flow — provides the posterior samples at virtually no cost. However, the accuracy of amortized variational inference relies on the availability of high-fidelity training data, which seldom exist in geophysical inverse problems because of the earth’s heterogeneous subsurface. In addition, the network is prone to errors if evaluated over data that are not drawn from the training data distribution. As such, we have aimed to increase the resilience of amortized variational inference in the presence of moderate data distribution shifts. We achieve this via a correction to the conditional normalizing flow’s latent distribution that improves the approximation to the posterior distribution for the data at hand. The correction involves relaxing the standard Gaussian assumption on the latent distribution and parameterizing it via a Gaussian distribution with an unknown mean and (diagonal) covariance. These unknowns are then estimated by minimizing the Kullback-Leibler divergence between the corrected and the (physics-based) true posterior distributions. Although generic and applicable to other inverse problems by means of a linearized seismic imaging example, we find that our correction step improves the robustness of amortized variational inference with respect to changes in the number of seismic sources, noise variance, and shifts in the prior distribution. This approach, given noisy seismic data simulated via the linearized Born modeling, provides a seismic image with limited artifacts and an assessment of its uncertainty at approximately the same cost as five reverse time migrations.

7 January 2024 in Geophysics
Verified
Journal Article
Closed access
Ziyi YinZiyi Yin
Ziyi Yin
RORafael Orozco
Rafael Orozco
MLMathias Louboutin
Mathias Louboutin
FHFelix J. Herrmann
Felix J. Herrmann
We introduce a probabilistic technique for full-waveform inversion, using variational inference and conditional normalizing flows to quantify uncertainty in migration-velocity models and its impact on imaging. Our approach integrates generative artificial intelligence with physics-informed common-image gathers, reducing reliance on accurate initial velocity models. Considered case studies demonstrate its efficacy producing realizations of migration-velocity models conditioned by the data. These models are used to quantify amplitude and positioning effects during subsequent imaging.

13 May 2025 in Geophysical Journal International
Verified
Journal Article
Open access
AGAbhinav Prakash Gahlot
Abhinav Prakash Gahlot
RORafael Orozco
Rafael Orozco
Ziyi YinZiyi Yin
Ziyi Yin
GBGrant Bruer
Grant Bruer
FHFelix J Herrmann
Felix J Herrmann
SUMMARY: Geological Carbon Storage (GCS) is one of the most viable climate-change mitigating net-negative CO2-emission technologies for large-scale CO2 sequestration. However, subsurface complexities and reservoir heterogeneity demand a systematic approach to uncertainty quantification to ensure both containment and conformance, as well as to optimize operations. As a step toward a digital twin for monitoring and control of underground storage, we introduce a new machine-learning-based data-assimilation framework validated on realistic numerical simulations. The proposed digital shadow combines simulation-based inference (SBI) with a novel neural adaptation of a recently developed nonlinear ensemble filtering technique. To characterize the posterior distribution of CO2 plume states (saturation and pressure) conditioned on multimodal time-lapse data, consisting of imaged surface seismic and well-log data, a generic recursive scheme is employed, where neural networks are trained on simulated ensembles for the time-advanced state and observations. Once trained, the digital shadow infers the state as time-lapse field data become available. Unlike ensemble Kalman filtering, corrections to predicted states are computed via a learned nonlinear prior-to-posterior mapping that supports non-Gaussian statistics and nonlinear models for the dynamics and observations. Training and inference are facilitated by the combined use of conditional invertible neural networks and bespoke physics-based summary statistics. Starting with a probabilistic permeability model derived from a baseline seismic survey, the digital shadow is validated against unseen simulated ground-truth time-lapse data. Results show that injection-site-specific uncertainty in permeability can be incorporated into state uncertainty, and the highest reconstruction quality is achieved when conditioning on both seismic and wellbore data. Despite incomplete permeability knowledge, the digital shadow accurately tracks the subsurface state throughout a realistic CO2 injection project. This work establishes the first proof-of-concept for an uncertainty-aware, scalable digital shadow, laying the foundation for a digital twin to optimize underground storage operations.

3 January 2025 in Geophysics
Verified
Journal Article
Closed access
Ziyi YinZiyi Yin
Ziyi Yin
RORafael Orozco
Rafael Orozco
FHFelix J. Herrmann
Felix J. Herrmann
We develop a semiamortized variational inference (VI) framework designed for computationally feasible uncertainty quantification in full-waveform inversion to explore the multimodal posterior distribution without dimensionality reduction. The framework is called full-waveform VI via subsurface extensions with refinements (WISER). WISER builds on top of a supervised generative artificial intelligence method that performs approximate amortized inference that is low-cost albeit showing an amortization gap. This gap is closed through nonamortized refinements that make frugal use of wave physics. Case studies illustrate that WISER is capable of full-resolution, computationally feasible, and reliable uncertainty estimates of velocity models and imaged reflectivities.

14 March 2025 in Inverse Problems
Verified
Journal Article
Open access
RORafael Orozco
Rafael Orozco
ASAli Siahkoohi
Ali Siahkoohi
MLMathias Louboutin
Mathias Louboutin
FHFelix J Herrmann
Felix J Herrmann
Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intractable. New advances in machine learning and variational inference (VI) have lowered this computational barrier by leveraging data-driven learning. Two VI paradigms have emerged that represent different tradeoffs: amortized and non-amortized. Amortized VI can produce fast results but due to generalizing to many observed datasets it produces suboptimal inference results. Non-amortized VI is slower at inference but finds better posterior approximations since it is specialized towards a single observed dataset. Current amortized VI techniques run into a sub-optimality wall that cannot be improved without more expressive neural networks or extra training data. We present a solution that enables iterative improvement of amortized posteriors that uses the same networks architectures and training data. The benefits of our method requires extra computations but these remain frugal since they are based on physics-hybrid methods and summary statistics. Importantly, these computations remain mostly offline thus our method maintains cheap and reusable online evaluation while bridging the optimality gap between these two paradigms. We denote our proposed method ASPIRE - Amortized posteriors with Summaries that are Physics-based and Iteratively REfined. We first validate our method on a stylized problem with a known posterior then demonstrate its practical use on a high-dimensional and nonlinear transcranial medical imaging problem with ultrasound. Compared with the baseline and previous methods in the literature, ASPIRE stands out as an computationally efficient and high-fidelity method for posterior inference.

31 July 2019 in Uniciencia
Verified
Journal Article
Open access
PDF file
JGJosé Antonio García-García
José Antonio García-García
JBJose Bernal Azofeifa Bolaños
Jose Bernal Azofeifa Bolaños
Frank Solano-CamposFrank Solano-Campos
Frank Solano-Campos
RORafael Orozco-Rodríguez
Rafael Orozco-Rodríguez
This investigation was carried out to evaluate the effect of two cytokinins: 6-benzilaminopurine (BAP) (6.5 mg l-1) and kinetin (K) (2.5 mg l-1), as well as the growth inhibitor abscisic acid (ABA) (1.0 mg l-1) on the in vitro tuberization capacity of two potato varieties: Atlantic and Alpha. The basal culture medium MS (1962) was used as a control. The responses were different between varieties. In cv. Atlantic, the analysis of the number (NM), weight (WM) and diameter (DM) of microtubers indicated that the addition of growth regulators did not affect induction and development of microtubers. However, when BAP was used, a non-significant increment of 41 % was observed in the number of the microtubers compared to the control treatment, from 2.6 to 4.4. The addition of cytokinins and ABA to the medium did not have a significant impact on the development of microtubers. In cv. Alpha the cytokinins used without ABA increased the number of microtubers, which were larger and heavier than those of the control treatment. In this variety, ABA significantly reduced the values of the NM, WM and DM variables. The exogenous action of cytokinins in the culture medium is likely to have caused an endogenous hormonal imbalance in the Atlantic and Alpha genotypes which interfered with their innate microtuberization ability, a result that was even more evident for cv. Alpha, which showed the need to continue optimizing protocols of genotype-specific systems in potato tissue culture to increase yield and seed quality.