Journal:

1. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. J. (2024). Stochastic pix2vid: A new spatiotemporal deep learning method for image-to-video synthesis in geologic CO2 storage prediction. Computational Geosciences. https://doi.org/10.1007/s10596-024-10298-7.

2. Raheem, O., Pan, W., Morales, M. M., and Torres-Verdin, C. (2024). Automatic permeability estimation: Machine-learning vs. conventional petrophysical models. Petrophysics.

3. Latrach, A., Malki, M., Morales, M. M., Mehana, M., and Rabiei, M. (2024). Physics-informed machine learning: A comprehensive review to bridge the gap between machine learning and domain knowledge in the oil and gas industry. Geoenergy Science and Engineering. https://doi.org/10.1016/j.geoen.2024.212938.

4. Chen, B., Morales, M. M., Ma, Z., Kang, Q., and Pawar, R. (2024). Assimilation of geophysics-derived spatial data for model calibration in geologic CO2 sequestration. SPE J. https://doi.org/10.2118/212975-PA.

5. Mao, S., Chen, B., Malki, M., Chen, F., Morales, M. M., Ma, Z., and Mehana, M. (2024). Efficient prediction of hydrogen storage performance in depleted gas reservoirs using machine learning. Applied Energy. https://doi.org/10.1016/j.apenergy.2024.122914.

6. Mao, S., Chen, B., Morales, M. M., Malki, M., and Mehana, M. (2024). Cushion gas effects on hydrogen storage in porous rocks: Insights from reservoir simulation and deep learning. Hydrogen Energy. https://doi.org/10.1016/j.ijhydene.2024.04.288.

7. Morales, M. M, Kravchenko, K., Rosales, A., Mendoza, A., Pyrcz, M. J., and Torres-Verdin, C. (2024, in review). A deep learning-based dual latent space method for the estimation of flow properties from fiber-optic measurements. Geophysics.

8. Morales, M. M., Mehana, M., Torres-Verdin, C., Pyrcz, M. J., and Chen, B. (2024, in review). Optimal monitoring design for uncertainty quantification during geologic CO2 sequestration: A machine learning approach. Geoenergy Science and Engineering.

9. Morales, M. M., Eghbali, A., Raheem, O., Pyrcz, M., and Torres-Verdin, C. (2024, in review). Anisotropic resistivity inversion and uncertainty quantification: A comparison between gradient-based inversion and physics-informed neural network inversion. Computers & Geosciences.

Conference:

1. Morales, M. M., Christie, M., Rabinovic, V., Torres-Verdin, C., and Pyrcz, M. (2024). Automatic well log baseline correction for rapid characterization of potential CO2 storage sites using deep learning. IMAGE, Houston, TX, USA, August 2024.

2. Morales, M. M., Raheem, O., Christie, M., Rabinovic, V., Torres-Verdin, C., and Pyrcz, M. (2024). Automatic rock classification from core data to well logs: Using machine learning to accelerate potential CO2 storage site characterization. IMAGE, Houston, TX, USA, August 2024.

3. Raheem, O., Pan, W., Torres-Verdin, C., and Morales, M. M. (2023). Best practices in automatic permeability estimation: Machine-learning methods vs. conventional petrophysical models. SPWLA 64th Annual Logging Symposium, Lake Conroe, TX, USA, June 2023. https://doi.org/10.30632/SPWLA-2023-0084. 

Preprints:

1. Morales, M. M. and Pomeranz, S. B. (2024). Boundary element method for the Dirichlet problem for Laplace's equation on a disk. arXiv math.NA. https://doi.org/10.48550/arXiv.2401.11616. 

2. Latrach, A., Malki, M., Morales, M. M., Mehana, M., and Rabiei, M. (2023). A critical review of physics-informed machine learning applications in subsurface energy systems. arXiv cs.LG. https://doi.og/10.48550/2308.04457.

3. Seczon, D., Morales, M. M., Achee, M. C., and Harkness, A. R. (in preparation). Tutorial: Determining when the nervous system is starting to reach to a stimulus using mathematical modeling.

In preparation:

1. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. (in preparation). Ensemble model calibration and uncertainty quantification in geologic CO2 storage using a spatiotemporal deep learning proxy.

2. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. (in preparation). Well placement and control optimization for geologic CO2 storage prediction under geologic uncertainty using a spatiotemporal deep learning proxy.

3. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. J. (in preparation). Coupled variational autoencoders for geologic inversion from multi-source dynamic data.

4. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. J. (in preparation). A deep learning method for closed-loop modeling of subsurface flow using coupled variational autoencoders.

5. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. J. (in preparation). Dimensionality reduction techniques for subsurface modeling.

6. Crisafulli, D., Morales, M. M., and Torres-Verdin, C. (in preparation). Deep learning-based automated rock classification via high-resolution drone-captured core sample imagery.

7. Morales, M. M., Raheem, O., Christie, M., Rabinovich, V., Torres-Verdin, C., and Pyrcz, M. (in preparation). Machine learning-based formation evaluation for potential CO2 storage site characterization: Well log baseline correction and core-to-well log rock classification.

8. Morales, M. M., Mabadeje, A., Liu, L., Torres-Verdin, C., and Pyrcz, M. (in preparation). On the stability of deep learning latent feature spaces: A perceptual approach for spatial and temporal data.

9. Morales, M. M., Delshad, M., Torres-Verdin, C., and Pyrcz, M. (in preparation). Evaluating the efficiency of a potential closed-loop hydrogen production and storage pathway.

Abstracts:

1. Morales, M. M., Rahem, O., Christie, M., Rabinovic, V., Torres-Verdin, C., and Pyrcz, M. (2024). Machine learning-based formation evaluation for potential CO2 storage site characterization: Well-log baseline correction and core-to-well log rock classification.. Formation Evaluation Consortium Meeting, Austin, TX.

2. Morales, M. M., Eghabli, A., Raheem, O., Pyrcz, M. J., and Torres-Verdin, C.. (2024). Anisotropic resistivity estimation and uncertainty quantification from borehole triaxial electromagnetic induction measurements: Physics-informed neural network vs. gradient-based inversion. Formation Evaluation Consortium Meeting, Austin, TX.

3. Mao, S., Chen, B., Morales, M. M., Malki, M., Ma, Z., and Mehana, M. (2023). Estimation of hydrogen storage performance in porous rocks integrating deep learning and reservoir simulation. AGU Fall Meeting Abstracts. Vol. 2023. No. 832. San Francisco, CA.

4. Morales, M. M., Pyrcz, M. J., and Torres-Verdin, C. (2023). A deep learning-based dual latent space method for the estimation of physical flow properties from fiber-optic measurements. Formation Evaluation Consortium Meeting. Austin, TX.

5. Morales, M. M., Pyrcz, M. J., and Torres-Verdin, C. (2022). Dimensionality reduction and measurement reconstruction for time-lapse fiber optic sensing. Formation Evaluation Consortium Meeting. Austin, TX.

Posters:

1. Morales, M. M., and Chen, Z. (2024). Deep learning-based surrogate flow models for multi-phase flow simulation. ExxonMobil Student Symposium. Spring, TX.

2. Morales, M. M., Chen, B., and Mehana, M. (2023). Optimal sensor placement and monitoring design in geologic CO2 sequestration using machine learning methods. LANL Student Symposium. Los Alamos, NM.

Presentations:

1. Morales, M. M., (2024). Deep learning-based surrogate flow models for multi-phase flow simulation. ExxonMobil Internship Capstone. Houston, TX.

2. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. (2024). Spatiotemporal proxy modeling for CO2 storage prediction. Equinor-DiReCT Workshop. Austin, TX.

3. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. (2024). Well placement and control optimization for CO2 storage under geologic uncertainty. Equinor-DiReCT Workshop. Austin, TX.

4. Morales, M. M. (2024). Machine learning in subsurface modeling. UT-PGE Grad Student Seminar Series. Austin, TX.

5. Morales, M. M., Pyrcz, M. J., and Torres-Verdin, C. (2024). A deep learning-based dual latent space method for the estimation of physical flow properties from fiber-optic measurements. Chevron-DiReCT Workshop. Houston, TX.

6. Morales, M. M. (2023). La inteligencia artificial en la ingenieria de recursos energeticos. CYTIVEN. Maracaibo, Venezuela.

7. Morales, M. M., Chen, B., and Mehana, M. (2023). Optimal sensor placement and monitoring design in geologic CO2 sequestration: A machine learning and uncertainty quantification approach. EES-16 Science Cafe Seminar. Los Alamos, NM.

8. Morales, M. M. (2023). Topics in deep learning-based latent space modeling for subsurface energy resource engineering. LANL Applied Machine Learning Fellowship Seminar Series. Los Alamos, NM.

9. Morales, M. M., Torres-Verdin, C., and Pyrcz, M. (2023). Spatiotemporal CNN-RNN proxy model for CO2 monitoring. ExxonMobil-DiReCT Workshop. Austin, TX.

10. Jo, H., Santos, J. E., Pan, W., Morales, M. M., and Pyrcz, M. J. (2021). Machine learning-assisted production history matching while retraining geological heterogeneity. GeoGulf 2021. Austin, TX.

Datasets:

1. Morales, M. M. and Pyrcz, M. J. (2023). Machine Learning Training Images Repository (1.0.0). Zenodo. https://doi.org/10.5281/zenodo.7702128

Short Courses:

1. Morales, M. M. (2024). Introduction to Data Science and Machine Learning. CytiVen. https://github.com/CytiVen