Publications
WORKSHOPS:
M. G. Fernández-Godino, "Autoencoder-Based Models for Plume Transport Predictions". Work in Progress Presentation - Physical and Life Sciences. Lawrence Livermore National Laboratory, March 22, 2023. Download presentation
M. G. Fernández-Godino, "An Introduction to K-Nearest Neighbors (KNN)". Applied Statistics Workshop - Lawrence Livermore National Laboratory, August 18, 2021. Download presentation
PANELS:
M. G. Fernández-Godino, "PSAAPII – University of Florida Center for Compressible Multiphase Turbulence". Career Opportunities at the NNSA Labs - Panel discussion at PSAAP Forum. Albuquerque, New Mexico. June 6, 2023.
ONLINE ARTICLES:
M. G. Fernández-Godino, SIAM NEWS, March 27, 2023. "Color Image-driven Deep Autoencoders Predict Atmospheric Pollutant Patterns". Read article
M. G. Fernández-Godino, PLS NEWS, February 27, 2023. "Predicting Wind-driven Spatial Patterns of Atmospheric Pollutants". Read article
D. O'Malley, G. Srinivasan , and M. G. Fernández-Godino, SIAM NEWS, December 1, 2020. "Scale-bridging with Machine Learning to Characterize Brittle Damage and Failure". Read article
SEMINARS:
M. G. Fernández-Godino, "Predicting Wind-Driven Spatial Deposition through Deep Autoencoders in a Complex Terrain". Seminar - Brown University - CRUNCH group, September 9, 2022. Download presentation
M. G. Fernández-Godino, "Solving Complex Problems of Interest to National Security Aided by Machine Learning and Data Science". Seminar - Lawrence Livermore National Laboratory, June 22, 2022.
M. G. Fernández-Godino, "Machine Learning Approaches for Predicting Seismic, Acoustic and Atmospheric Data". Seminar - Caltech, May 27, 2021. Download presentation - Watch this presentation
M. G. Fernández-Godino, " Machine learning tools to aid in solving complex problems of interest to national nuclear security ". Seminar - University of Florida, February 11, 2021. Download presentation - Watch this presentation
M. G. Fernández-Godino, "Quantifying Particle Departure from Axisymmetry in Multiphase Cylindrical Detonation". Seminar San Diego State University, May 10, 2019 Download presentation
INVITED SPEAKER:
M. G. Fernández-Godino, "Machine Learning Approaches for Atmospheric and Material Fracture Applications and their Uncertainty Quantification". Workshop on Controlling Error and Efficiency of Numerical Models: Methods, Benchmarks, and Case Studies. The Fields Institute for Research in Mathematical Sciences, Toronto, Canada. December 2, 2021. Download presentation - Watch presentation
M. G. Fernández-Godino, N. Panda, K. Larkin, A. Hunter, D. O'Malley, and G. Srinivasan, "Leveraging Machine Learning Approaches to Understand, Predict and Reduce Costs in Complex Physical Phenomena". Rising Star in Computational & Data Sciences 2020, Austin, Texas. October 13, 2020. Download presentation
M. G. Fernández-Godino, N. Panda, D. O’Malley, K. Hickmann, D. Oyen, R. T. Haftka, and G. Srinivasan, “Discovering Graph-based Representations of Fracture Networks through Machine Learning”. IMACXXXVIII Conference, February 10–13, 2020, Houston, Texas. Download Presentation
M. G. Fernández-Godino, S. Balachandar, R. T. Haftka, “On the use of Symmetries to Improve Surrogates Models”. SIAM Conference on Uncertainty Quantification, Garden Grove, California, USA. April 16-19, 2018. Download presentation
FIRST AUTHOR PAPERS:
M. G. Fernández-Godino, Donald D. Lucas, and Q. Kong, "Predicting Wind-Driven Spatial Deposition through Simulated Color Images using Deep Autoencoders". Nature Scientific Reports 13, 1394 (2023). Download paper
M. G. Fernández-Godino, J. B. Nakhleh, M. J. Grosskopf, B. M. Wilson, J. Kline, and G. Srinivasan, "Identifying Entangled Physics Relationships through Sparse Matrix Decomposition to Inform Plasma Fusion Design". IEEE Transactions on Plasma Science 49.8 (2021): 2410-2419. Download paper
M. G. Fernández-Godino, N. Panda, D. O’Malley, K. Larkin, A. Hunter, R. T. Haftka, and G. Srinivasan, “Accelerating continuum-scale brittle fracture simulations with machine learning”. Computational Materials Science, Elsevier, Volume 186, January 2021, p. 109959. DOI:10.1016/j.commatsci.2020.109959. Download paper
M. G. Fernández-Godino, S. Dubreuil, N. Bartoli, C. Gogu, S. Balachandar, and R. T. Haftka, “Linear Regression Based Multi-fidelity Surrogate for Disturbance Amplification in Multi-phase Explosion". Structural and Multidisciplinary Optimization 60.6 (2019): 2205-2220. DOI:10.1007/s00158-019-02387-4 Download
M. G. Fernández-Godino, F. Ouellet, S. Balachandar, R. T. Haftka, “Early time evolution of circumferential perturbation of initial particle volume fraction in explosive cylindrical multiphase dispersion ". ASME. Journal of Fluids Engineering. Vol. 141, Issue 9, 09130201-09130220, September 2019. DOI:10.1115/1.4043055. Download
M. G. Fernández-Godino, S. Balachandar, R. T. Haftka, “On the Use of Symmetries in Building Surrogate Models”. ASME Journal of Mechanical Design. Vol. 141, Issue 6, 06140201-06140214, June 2019. DOI: 10.1115/1.4042047. Download
M. G. Fernández-Godino, C. Park, N. H. Kim, and R. T. Haftka, “Issues in Deciding whether to Use Multi-fidelity Models”. AIAA Journal, Vol 57, No. 5, 2039-2054, May 2019. DOI:10.2514/1.J057750. Download
M. G. Fernández-Godino, C. Park, N. H. Kim, and R. T. Haftka, “Review of Multi-fidelity Models”. arXiv preprint arXiv:1609.07196. September, 2016. Download
CO-AUTHOR PAPERS:
Y. Wang, M. G. Fernández-Godino, N. Gunawardena, D. D. Lucas, and X. Yue. "ST-GasNet: Spatiotemporal Prediction of Plume Evolution using Deep Learning”, Submitted to IEEE Transactions on Neural Networks and Learning Systems, 04-14-2022.
Q. Kong, A. Chiang, A. C. Aguiar, M. G. Fernández-Godino, S. C. Myers, and D. D, 2021. Deep convolutional autoencoders as generic feature extractors in seismological applications. Artificial Intelligence in Geosciences. Download paper
C. Garcia-Cardona, M. G. Fernández-Godino, D. O'Malley, and T. Bhattacharya. "Uncertainty Bounds for Multivariate Machine Learning Predictions on High-Strain Brittle Fracture." Computational Materials Science 201 (2022): 110883. Download paper
J. B. Nakhleh, M. G. Fernández-Godino, M. J. Grosskopf, B. M. Wilson, G. Srinivasan, and J. Kline. "Exploring Sensitivity of ICF Outputs to Design Parameters in Experiments Using Machine Learning". IEEE Transactions on Plasma Science 49.7 (2021): 2238-2246. DOI: 10.1109/TPS.2021.3090299. Download paper
N. Panda, M. G. Fernández-Godino, H. Godinez, C. Dawson, "A Data Driven Non-Linear Assimilation Framework with Neural Networks". Computational Geosciences (2020). DOI:10.1007/s10596-020-10001-6 . Download paper
Y. Wang, D. Oyen, W. Guo, A. Metha, C. Scott, N. Panda, M. G. Fernández-Godino, G. Srinivasan, and X. Yue, "StressNet: Deep Learning to Predict Stress With Fracture Propagation in Brittle Materials". NPJ Materials Degradation 5.1 (2021): 1-10. Download paper
THESIS:
M. G. Fernández-Godino, “Quantifying Particle Departure from Axisymmetry in Multiphase Cylindrical Detonation". PhD Thesis, University of Florida. December 2018. Download
M. G. Fernández-Godino, "Development of a surveillance program for the Argentinian reactor CAREM 24". Undergraduate Thesis for the Degree in Nuclear Engineering, Universidad Nacional de Cuyo, Instituto Balseiro. June, 2014. Download
CONFERENCES:
M. G. Fernández-Godino, W. T. Chung, and D. D. Lucas. "Leveraging Local Scale Deep Autoencoder-Based Models to Improve Early Time Predictions in Global Atmospheric Transport". UNCECOMP 2023, Athens, Greece, June 12-14, 2023. Download presentation.
M. G. Fernández-Godino, W. T. Chung, Y. Wang, and D. D. Lucas, "Deep Autoencoder-Based Approaches for Plume Transport Predictions", SIAM CSE 2023, Amsterdam, The Netherlands, February 26- March 2, 2023. Download presentation.
M. G. Fernández-Godino, W. T. Chung, Y. Wang, and D. D. Lucas, "Predicting Wind-Driven Spatial Deposition using Deep Autoencoders". CASIS conference 2022, Livermore, California, September 7, 2022. Download presentation
M. G. Fernández-Godino, Q. Kong, and D. D. Lucas, "Deep Convolutional Autoencoders for Predicting Wind-Driven Spatial Patterns". Deep Learning Approaches for Applied Sciences and Engineering, ECCOMAS Congress 2022, Oslo, Norway, June 5-9, 2022. Download presentation
M. G. Fernández-Godino, Q. Kong, G. J. Anderson, and D. D. Lucas, "Predicting Wind-Driven Spatial Patterns via Deep Convolutional Autoencoders". American Geophysical Union Fall Meeting 2021, December 13-17, 2021. Download presentation
Y. Wang, M. G. Fernández-Godino, N. Gunawardena, X. Yue, and D. D. Lucas. “Predicting the time evolution of dispersing atmospheric clouds using deep neural networks”. American Geophysical Union Fall Meeting 2021, December 13-17, 2021.
M. G. Fernández-Godino, O. Alvarez, D. Lucas, L. Glascoe, and S. Myers, "Radioxenon Data Fusion for Event Association ". CTBT International Noble Gases Experiment Workshop 2021, November 22-26, 2021. Download presentation
I. Hoffman, M. G. Fernández-Godino, D. Lucas, L. Glascoe, and S. Myers, "IMS Data Fusion and the Possibilities of Dempster-Schafer Theory". CTBT SnT2021, Virtual Symposium, June 28-July 2, 2021. Download presentation
M. G. Fernández-Godino, J. B. Nakhleh, M. J. Grosskopf, B. M. Wilson, and G. Srinivasan, "Using Machine Learning Techniques to Study and Validate Plasma Fusion Experiments". NYSDS2020, Virtual Symposium, October 20-23, 2020. Download presentation
J. B. Nakhleh, M. G. Fernández-Godino, M. J. Grosskopf, B. M. Wilson, G. Srinivasan, and J. Kline, "Exploring Sensitivity of ICF Outputs to Design Parameters in Experiments using Machine Learning". NYSDS2020, Virtual Symposium, October 20-23, 2020.
J. B. Nakhleh, M. G. Fernández-Godino, M. J. Grosskopf, B. M. Wilson, G. Srinivasan, and J. Kline, "Using machine learning to identify physical relationships and quantify uncertainties in Inertial Confinement Fusion". ASME V&V 2020, Virtual Symposium, May 20-22, 2020. Student poster presentation award, second place. Download presentation
M. G. Fernández-Godino, J. B. Nakhleh, M. J. Grosskopf, B. M. Wilson, and G. Srinivasan, "Using Machine Learning Techniques to Study and Validate Plasma Fusion Experiments". ASME V&V 2020, Virtual Symposium, May 20-22, 2020. Download presentation
M. G. Fernández-Godino, N. Panda, D. O’Malley, K. Hickmann, D. Oyen, R. T. Haftka, and G. Srinivasan, “Flyer Plate Continuum Simulations Informed with Machine Learning (ML) Crack Evolution”. 22th AIAA Non-Deterministic Approaches Conference, Kissimmee, FL, USA. January 6-10, 2020. Download paper - Download Presentation
R. T. Haftka, N.H. Kim, C. Park, M. G. Godino-Fernández, Z. Guo, "Challenges in the use of Multi-fidelity Surrogates", The Asian Congress of Structural and Multidisciplinary Optimization. May 21 - 24, 2018, Dalian, China.
M. G. Fernández-Godino, R. T. Haftka, S. Balachandar, C. Gogu, S. Dubreuil, and N. Bartoli, “Noise Filtering and Uncertainty Quantification in Surrogate based Optimization”. 20th AIAA Non-Deterministic Approaches Conference, Kissimmee, FL, USA. January 8-12, 2018. Download paper - Download Presentation
M. G. Fernández-Godino, F. Ouellet, S. Balachandar, and R. T. Haftka, “Multi-fidelity surrogate-based optimization as a tool to study the physics in explosive dispersal of particles”. 12th World Congress of Structural and Multidisciplinary Optimisation (WCSMO12), Braunschweig, Germany, June 5-9, 2017. Download
M. G. Fernández-Godino, F. Ouellet, S. Balachandar, and R. T. Haftka, “Noise quantification in the study of instabilities during explosive dispersal of solid particles”. V&V ASME Conference, Las Vegas, Nevada, May 3-5, 2017. Download
M. G. Fernández-Godino, C. Park, N. H. Kim, and R. T. Haftka, “Review of Multifidelity Surrogate Models”. ECCOMAS Congress 2016, Uncertainty Quantification in CFD and Fluid Structure Interaction, Crete Island, Greece, June 5-10, 2016. Download
M. G. Fernández-Godino, A. Diggs, C. Park, N. H. Kim, and R. T. Haftka, “Anomaly Detection using Groups of Simulations”. 18th AIAA Non-Deterministic Approaches Conference, San Diego, CA, USA. January 4-8, 2016. Download paper
C. Park, M. G. Fernández-Godino, N.H. Kim, and R.T. Haftka, “Validation, Uncertainty Quantification and Uncertainty Reduction for a Shock Tube Simulation". 18th AIAA Non-Deterministic Approaches Conference, San Diego, CA, USA. January 4-8, 2016. Download paper
REPORTS:
M. G. Fernández-Godino, D. D. Lucas, and S. C. Myers. Analysis of Data Fusion between Waveform Events and Radionuclide Detections Reported in 2021 by the International Data Centre (No. LLNL-TR-841783). Lawrence Livermore National Laboratory, 2022. Download
M. G. Fernández-Godino, G. Weirs, and V. Mousseau. "One-dimensional, one-phase and two-phase, Eulerian explicit shock tube simulation code: development and uncertainty quantification". Sandia National Laboratories Internship Report, 2015. Download
POSTERS:
M. G. Fernández-Godino, D. D. Lucas, W. T. Chung, Glascoe L. G. and Myers, S. C. "Leveraging Local Scale Deep Autoencoder-Based Models to Characterize Early Times of Global Atmospheric Transport". SnT 2023, Vienna, Austria, June 19-23, 2023. Download Lightning Slide - Download Poster.
M. G. Fernández-Godino, W. T. Chung, Y. Wang, and D. D. Lucas, "Deep Learning Predictions for Plume Transport". CASIS conference poster 2022, Livermore, California, September 7, 2022. Download poster
MINISYMPISIUM ORGANIZER:
M. G. Fernández-Godino, and P. Perdikaris. Uncertainty Quantification for Scientific Machine Learning. Minisymposium, UNCECOMP 2023, Athens, Greece, June 12-14, 2023.
M. G. Fernández-Godino, and S. Srinivasan. Data Science Solutions for Earth Sciences – a Path to a Sustainable Future. Minisymposium, SIAM CSE 2023, Amsterdam, The Netherlands, February 26- March 2, 2023.
M. G. Fernández-Godino, C. F. Jekel and C. Gogu. Deep Learning Approaches for Applied Sciences and Engineering Minisymposium, ECCOMAS. Congress 2022, Oslo, Norway, June 5-9, 2022.
DATASETS:
M. G. Fernandez-Godino, D.D. Lucas, and N. Gunawardena (2023). “Computational Fluid Dynamics Simulation Data of Spatial Deposition. In Lawrence Livermore National Laboratory (LLNL) Open Data Initiative” [Data set]. UC San Diego Library Digital Collections.DOI: 10.6075/J0D50N50. Download dataset.