@conference {gahlot2023NIPSWSifp,
	title = {Inference of CO2 flow patterns {\textendash} a feasibility study},
	booktitle = {Neural Information Processing Systems (NeurIPS)},
	year = {2023},
	note = {(NeurIPS 2023 Workshop - Tackling Climate Change with Machine Learning (Spotlight))},
	month = {10},
	abstract = {},
	keywords = {Amortized Variational Inference, Bayesian inference, CCS, conditional normalizing flows, geological carbon storage, monitoring, NIPS, Summary Statistics},
	doi = {10.48550/arXiv.2311.00290},
	url = {https://slim.gatech.edu/Publications/Public/Conferences/NIPS/2023/gahlot2023NIPSWSifp/paper.pdf},
	presentation = {https://slim.gatech.edu/Publications/Public/Conferences/NIPS/2023/gahlot2023NIPSWSifp/poster.pdf},
	author = {Abhinav Prakash Gahlot and Huseyin Tuna Erdinc and Rafael Orozco and Ziyi Yin and Felix J. Herrmann}
}

@article{orozco2023invertiblenetworks, 
doi = {10.21105/joss.06554}, 
url = {https://doi.org/10.21105/joss.06554}, 
year = {2024}, 
publisher = {The Open Journal}, 
volume = {9}, 
number = {99}, 
pages = {6554}, 
author = {Rafael Orozco and Philipp Witte and Mathias Louboutin and Ali Siahkoohi and Gabrio Rizzuti and Bas Peters and Felix J. Herrmann}, 
title = {InvertibleNetworks.jl: A Julia package for scalable normalizing flows}, 
journal = {Journal of Open Source Software} 
}

@CONFERENCE{COP21_2015,
  title        = {United Nations Climate Change Conference},
  booktitle    = {21st Session of the Conference of the Parties (COP) to the UNFCCC and 11th Session of the Meeting of the Parties (CMP) to the Kyoto Protocol},
  year         = {2015},
  month        = {November 30--December 12},
  location     = {Paris, France},
  organization = {United Nations Framework Convention on Climate Change (UNFCCC)}
}

@misc{IEA_2016,
  author       = {{International Energy Agency (IEA)}},
  title        = {20 Years of Carbon Capture and Storage: Accelerating Future Deployment},
  year         = {2016},
  url          = {https://www.iea.org/publications},
}

@article{masson2018global,
  title={Global warming of 1.5 C},
  author={{IPCC special report}},
  journal={An IPCC Special Report on the impacts of global warming of},
  volume={1},
  number={5},
  pages={43--50},
  year={2018}
}

@misc{JUDI,
  author       = {Mathias Louboutin and
                  Philipp Witte and
                  Ziyi Yin and
                  Henryk Modzelewski and
                  Kerim and
                  Carlos da Costa and
                  Peterson Nogueira},
  title        = {slimgroup/JUDI.jl: v3.2.3},
  month        = mar,
  year         = 2023,
  publisher    = {Zenodo},
  version      = {v3.2.3},
  doi          = {10.5281/zenodo.7785440},
  url          = {https://doi.org/10.5281/zenodo.7785440}
}

@misc{jutuldarcy,
  author       = {Olav Møyner and
                  Grant Bruer and
                  Ziyi Yin},
  title        = {sintefmath/JutulDarcy.jl: v0.2.3},
  month        = apr,
  year         = 2023,
  publisher    = {Zenodo},
  version      = {v0.2.3},
  doi          = {10.5281/zenodo.7855628},
  url          = {https://doi.org/10.5281/zenodo.7855628}
}

@ARTICLE{witte2018alf,
  author = {Philipp A. Witte and Mathias Louboutin and Navjot Kukreja and Fabio Luporini and Michael Lange and Gerard J. Gorman and Felix J. Herrmann},
  title = {A large-scale framework for symbolic implementations of seismic inversion algorithms in Julia},
  journal = {Geophysics},
  volume = {84},
  number = {3},
  pages = {F57-F71},
  year = {2019},
  month = {03},
  abstract = {},
  keywords = {FWI, LSRTM, modeling, inversion, software},
  doi = {10.1190/geo2018-0174.1},
  note = {(Geophysics)},
  url = {https://slim.gatech.edu/Publications/Public/Journals/Geophysics/2019/witte2018alf/witte2018alf.pdf}
}

@article{Kingma2014AdamAM,
title={Adam: A Method for Stochastic Optimization},
author={Diederik P. Kingma and Jimmy Ba},
journal={CoRR},
year={2014},
volume={abs/1412.6980},
url={https://api.semanticscholar.org/CorpusID:6628106}
}

@article{iiasa14349,
    number = {2},
      year = {2017},
      month = {January},
        doi = {10.1038/nclimate3202},
      title = {Key indicators to track current progress and future ambition of the Paris Agreement},
      pages = {118--122},
    volume = {7},
    journal = {Nature Climate Change},
  publisher = {Springer Nature},
      issn = {1758-678X},
    author = {Peters, G. P. and Andrew, R. M. and Canadell, J. G. and Fu{\ss}, S. and Jackson, R. B. and Korsbakken, J. I. and Le Qu{\'e}r{\'e}, C. and Nakicenovic, N.},
        url = {https://pure.iiasa.ac.at/id/eprint/14349/},
  keywords = {Climate-change mitigation, Climate-change policy, Energy economics, Energy policy},
  abstract = {Current emission pledges to the Paris Agreement appear insufficient to hold the global average temperature increase to well below 2 oC above pre-industrial levels. Yet, details are missing on how to track progress towards the 'Paris goal', inform the five-yearly 'global stocktake', and increase the ambition of Nationally Determined Contributions (NDCs). We develop a nested structure of key indicators to track progress through time. Global emissions track aggregated progress, country-level decompositions track emerging trends that link directly to NDCs, and technology diffusion indicates future reductions. We find the recent slowdown in global emissions growth11 is due to reduced growth in coal use since 2011, primarily in China and secondarily in the United States. The slowdown is projected to continue in 2016, with global CO2 emissions from fossil fuels and industry similar to the 2015 level of 36 GtCO2. Explosive and policy-driven growth in wind and solar has contributed to the global emissions slowdown, but has been less important than economic factors and energy efficiency. We show that many key indicators are currently broadly consistent with emission scenarios that keep temperatures below 2 oC, but the continued lack of large-scale carbon capture and storage threatens 2030 targets and the longer-term Paris ambition of net-zero emissions.}
}

@online{GCCSI_2019,
  author       = {{Global CCS Institute (GCCSI)}},
  title        = {GCCSI CO\textsubscript{2}RE Database: 2019},
  year         = {2019},
  url          = {https://co2re.co},
}

@article{gahlot2025erd,
  title={Enhancing Robustness Of Digital Shadow For CO2 Storage Monitoring With Augmented Rock Physics Modeling}, 
  author={Abhinav Prakash Gahlot and Felix J. Herrmann},
  year={2025},
  eprint={2502.07171},
  archivePrefix={arXiv},
  primaryClass={physics.comp-ph},
  url={https://arxiv.org/abs/2502.07171}, 
}

@article{elsemuller2024sensitivityaware,
  title={Sensitivity-Aware Amortized Bayesian Inference},
  author={Lasse Elsem{\"u}ller and Hans Olischl{\"a}ger and Marvin Schmitt and Paul-Christian B{\"u}rkner and Ullrich Koethe and Stefan T. Radev},
  journal={Transactions on Machine Learning Research},
  issn={2835-8856},
  year={2024},
  url={https://openreview.net/forum?id=Kxtpa9rvM0},
  note={}
}

@article{radev2020bayesflow,
  title={BayesFlow: Learning complex stochastic models with invertible neural networks},
  author={Radev, Stefan T and Mertens, Ulf K and Voss, Andreas and Ardizzone, Lynton and K{\"o}the, Ullrich},
  journal={IEEE transactions on neural networks and learning systems},
  volume={33},
  number={4},
  pages={1452--1466},
  year={2020},
  publisher={IEEE}
}

@article{herrmann2023president,
  title={President's Page: Digital twins in the era of generative AI},
  author={Herrmann, Felix J},
  journal={The Leading Edge},
  volume={42},
  number={11},
  pages={730--732},
  year={2023},
  publisher={Society of Exploration Geophysicists}
}

@article{thelen2022comprehensivea,
  title={A comprehensive review of digital twin—part 1: modeling and twinning enabling technologies},
  author={Thelen, Adam and Zhang, Xiaoge and Fink, Olga and Lu, Yan and Ghosh, Sayan and Youn, Byeng D and Todd, Michael D and Mahadevan, Sankaran and Hu, Chao and Hu, Zhen},
  journal={Structural and Multidisciplinary Optimization},
  volume={65},
  number={12},
  pages={354},
  year={2022},
  publisher={Springer}
}

@article{spantini2022coupling,
  title={Coupling techniques for nonlinear ensemble filtering},
  author={Spantini, Alessio and Baptista, Ricardo and Marzouk, Youssef},
  journal={SIAM Review},
  volume={64},
  number={4},
  pages={921--953},
  year={2022},
  publisher={SIAM}
}

@book{ringrose2020store,
  title={How to store CO$_{2}$ underground: Insights from early-mover CCS Projects},
  author={Ringrose, Philip},
  volume={129},
  year={2020},
  publisher={Springer}
}

@book{ringrose2023storage,
  title={Storage of Carbon Dioxide in Saline Aquifers: Building confidence by forecasting and monitoring},
  author={Ringrose, Philip},
  year={2023},
  publisher={Society of Exploration Geophysicists}
}

@article{doi:10.1073/pnas.1912789117,
  author = {Kyle Cranmer  and Johann Brehmer  and Gilles Louppe },
  title = {The frontier of simulation-based inference},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {117},
  number = {48},
  pages = {30055-30062},
  year = {2020},
  doi = {10.1073/pnas.1912789117},
  URL = {https://www.pnas.org/doi/abs/10.1073/pnas.1912789117},
  eprint = {https://www.pnas.org/doi/pdf/10.1073/pnas.1912789117},
  abstract = {Many domains of science have developed complex simulations to describe phenomena of interest. While these simulations provide high-fidelity models, 
  they are poorly suited for inference and lead to challenging inverse problems. We review the rapidly developing field of simulation-based inference and identify 
  the forces giving additional momentum to the field. Finally, we describe how the frontier is expanding so that a broad audience can appreciate the profound 
  influence these developments may have on science.}
}

@article{papamakarios2019sequential,
  title={Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows}, 
  author={George Papamakarios and David C. Sterratt and Iain Murray},
  year={2019},
  eprint={1805.07226},
  archivePrefix={arXiv},
  primaryClass={stat.ML}
}

@inproceedings{kruse2021hint,
  title={HINT: Hierarchical invertible neural transport for density estimation and Bayesian inference},
  author={Kruse, Jakob and Detommaso, Gianluca and K{\"o}the, Ullrich and Scheichl, Robert},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={35},
  number={9},
  pages={8191--8199},
  year={2021}
}

@article{lumley20104d,
  title={4D seismic monitoring of CO 2 sequestration},
  author={Lumley, David},
  journal={The Leading Edge},
  volume={29},
  number={2},
  pages={150--155},
  year={2010},
  publisher={Society of Exploration Geophysicists}
}

@article{lumley2001time,
  title={Time-lapse seismic reservoir monitoring},
  author={David E. Lumley},
  journal={Geophysics},
  year={2001},
  volume={66},
  pages={50-53},
  url={https://api.semanticscholar.org/CorpusID:128497642}
}

@book{avseth2010quantitative,
  title={Quantitative seismic interpretation: Applying rock physics tools to reduce interpretation risk},
  author={Avseth, Per and Mukerji, Tapan and Mavko, Gary},
  year={2010},
  publisher={Cambridge university press}
}

@book{Mavko2009handbook,
  place={Cambridge},
  edition={2},
  title={The Rock Physics Handbook: Tools for Seismic Analysis of Porous Media},
  publisher={Cambridge University Press},
  author={Mavko, Gary and Mukerji, Tapan and Dvorkin, Jack},
  year={2009}
}

@article{BG,
  author = "E. Jones, C. and A. Edgar, J. and I. Selvage, J. and Crook, H.",
  title = "Building Complex Synthetic Models to Evaluate Acquisition Geometries and Velocity Inversion Technologies", 
  journal= "In 74th EAGE Conference and Exhibition Incorporating EUROPEC 2012",
  year = "2012",
  volume = "",
  number = "",
  pages = "cp–293",
  doi = "https://doi.org/10.3997/2214-4609.20148575",
  url = "https://www.earthdoc.org/content/papers/10.3997/2214-4609.20148575",
  publisher = "European Association of Geoscientists \& Engineers",
  issn = "2214-4609",
  type = "",
  eid = "cp-293-00580",
}

@article{nf,
  author = {Papamakarios, George and Nalisnick, Eric and Rezende, Danilo Jimenez and Mohamed, Shakir and Lakshminarayanan, Balaji},
  title = {Normalizing Flows for Probabilistic Modeling and Inference},
  year = {2021},
  issue_date = {January 2021},
  publisher = {JMLR.org},
  volume = {22},
  number = {1},
  issn = {1532-4435},
  journal = {J. Mach. Learn. Res.},
  month = {jan},
  articleno = {57},
  numpages = {64},
  keywords = {normalizing flows, generative models, probabilistic modeling, probabilistic inference, invertible neural networks}
}

@article{yin2024wise,
  title={WISE: full-Waveform variational Inference via Subsurface Extensions},
  author={Yin, Ziyi and Orozco, Rafael and Louboutin, Mathias and Herrmann, Felix J},
  journal={Geophysics},
  volume={89},
  number={4},
  pages={1--31},
  year={2024},
  publisher={Society of Exploration Geophysicists}
}

@article{gahlot2025uads,
	author = {Gahlot, Abhinav Prakash and Orozco, Rafael and Yin, Ziyi and Bruer, Grant and Herrmann, Felix J},
	title = {An uncertainty-aware digital shadow for underground multimodal CO2 storage monitoring},
	journal = {Geophysical Journal International},
	volume = {242},
	number = {1},
	pages = {ggaf176},
	year = {2025},
	month = {05},
	doi = {10.1093/gji/ggaf176},
	url = {https://doi.org/10.1093/gji/ggaf176},
}

@article{song2020score,
  title={Score-based generative modeling through stochastic differential equations},
  author={Song, Yang and Sohl-Dickstein, Jascha and Kingma, Diederik P and Kumar, Abhishek and Ermon, Stefano and Poole, Ben},
  journal={arXiv preprint arXiv:2011.13456},
  year={2020}
}

@article{tancik2020fourier,
  title={Fourier features let networks learn high frequency functions in low dimensional domains},
  author={Tancik, Matthew and Srinivasan, Pratul and Mildenhall, Ben and Fridovich-Keil, Sara and Raghavan, Nithin and Singhal, Utkarsh and Ramamoorthi, Ravi and Barron, Jonathan and Ng, Ren},
  journal={Advances in neural information processing systems},
  volume={33},
  pages={7537--7547},
  year={2020}
}

@misc{louboutin2021imagegather,
  author       = {Mathias Louboutin},
  title        = {slimgroup/ImageGather.jl},
  year         = {2021},
  publisher    = {Zenodo},
  version      = {v0.2.3},
  doi          = {10.5281/zenodo.5033319},
  url          = {https://doi.org/10.5281/zenodo.5033319}
}

@misc{SeismicAngleGathers,
  author = {Gahlot, Abhinav Prakash},
  title = {{SeismicAngleGathers.jl}: Convert Common Image Gathers from subsurface offset to angle domain},
  year = {2024},
  url = {https://github.com/apgahlot/SeismicAngleGathers},
  note = {Julia package; Radon and geometry-based offset-to-angle conversion for CIGs}
}

@article{sava2011extended,
  title = {Wave-equation migration velocity analysis using extended images},
  author = {Sava, Paul and Vasconcelos, Ivan},
  journal = {Geophysics},
  volume = {76},
  number = {5},
  pages = {WA65--WA76},
  year = {2011},
  publisher = {Society of Exploration Geophysicists},
  note = {Subsurface-offset extended imaging; CIGs for MVA and AVA}
}

@proceedings{10.1190/image2025-4316853.1,
    author = {Gahlot, Abhinav Prakash and Erdinc, Huseyin Tuna and Herrmann, Felix J.},
    title = {Sensitivity-aware rock physics enhanced digital shadow for underground-energy storage monitoring},
    volume = {Fifth International Meeting for Applied Geoscience \& Energy},
    series = {SEG Technical Program Expanded Abstracts},
    pages = {1868-1872},
    year = {2025},
    month = {08},
    abstract = {Underground energy storage, which includes storage of hydrogen, compressed air, and CO2, requires careful monitoring to track potential leakage pathways, a situation where time-lapse seismic imaging alone may be inadequate. A recently developed Digital Shadow (DS) enhances forecasting using machine learning and Bayesian inference, yet their accuracy depends on assumed rock physics models, the mismatch of which can lead to unreliable predictions for the reservoir’s state (saturation/pressure). Augmenting DS training with multiple rock physics models mitigates errors but averages over uncertainties, obscuring their sources. To address this challenge, we introduce context-aware sensitivity analysis inspired by amortized Bayesian inference, allowing the DS to learn explicit dependencies between seismic data, the reservoir state, e.g., CO2 saturation, and rock physics models. At inference time, this approach allows for real-time “what if” scenario testing rather than relying on costly retraining, thereby enhancing interpretability and decision-making for safer, more reliable underground storage.},
    doi = {10.1190/image2025-4316853.1},
    url = {https://doi.org/10.1190/image2025-4316853.1},
    eprint = {https://pubs.geoscienceworld.org/segeab/proceedings-pdf/SEGEAB.44/1/1868/7753019/image2025-4316853.1.pdf},
}

@proceedings{kumar2013SEGAVA,
    author = {Kumar, Rajiv and van Leeuwen, Tristan and Herrmann, Felix J.},
    title = {AVA analysis and geological dip estimation via two-way wave-equation based extended images},
    volume = {SEG Technical Program Expanded Abstracts 2013},
    series = {SEG Technical Program Expanded Abstracts},
    pages = {423-427},
    year = {2013},
    month = {09},
    abstract = {In this paper, we present an efficient way to compute extended images for all subsurface offsets without explicitly calculating the source and receiver wavefields for all the sources. Because the extended images contain all possible subsurface offsets, we compute the angle-domain image gathers by selecting the sub-surface offset that is aligned with the local dip. We also propose a method to compute the local dip information directly from common-image-point gathers. To assess the quality of the angle-domain common-image-points gathers we compute the angle-dependent reflectivity coefficients and compare them with theoretical reflectivity coefficients yielded by the (linearized) Zoeppritz equations for a few synthetic models.},
    doi = {10.1190/segam2013-1348.1},
    url = {https://doi.org/10.1190/segam2013-1348.1},
    eprint = {https://pubs.geoscienceworld.org/segeab/proceedings-pdf/SEGEAB.32/1/423/7662001/segam2013-1348.1.pdf},
}

@article{doi:10.1190/1.1441434,
author = {Edip Baysal and Dan D. Kosloff and John W. C. Sherwood},
title = {Reverse time migration},
journal = {GEOPHYSICS},
volume = {48},
number = {11},
pages = {1514-1524},
year = {1983},
doi = {10.1190/1.1441434},
URL = { 
        https://doi.org/10.1190/1.1441434},
eprint = {   
        https://doi.org/10.1190/1.1441434},
    abstract = {}
}

@article{10.1190/1.1707070,
    author = {MacBeth, Colin},
    title = {A classification for the pressure-sensitivity properties of a sandstone rock frame},
    journal = {Geophysics},
    volume = {69},
    number = {2},
    pages = {497-510},
    year = {2004},
    month = {01},
    abstract = {},
    issn = {0016-8033},
    doi = {10.1190/1.1707070},
    url = {https://doi.org/10.1190/1.1707070},
    eprint = {https://pubs.geoscienceworld.org/seg/geophysics/article-pdf/69/2/497/3198881/gsgpy_69_2_497.pdf},
}

@article{10.1190/1.1444973,
    author = {Landrø, Martin},
    title = {Discrimination between pressure and fluid saturation changes from time-lapse seismic data},
    journal = {Geophysics},
    volume = {66},
    number = {3},
    pages = {836-844},
    year = {2001},
    month = {01},
    abstract = {},
    issn = {0016-8033},
    doi = {10.1190/1.1444973},
    url = {https://doi.org/10.1190/1.1444973},
    eprint = {https://pubs.geoscienceworld.org/seg/geophysics/article-pdf/66/3/836/3691093/gsgpy_66_3_836.pdf},
}

@article{10.1190/1.1443207,
    author = {Batzle, M. L. and Wang, Zhijing},
    title = {Seismic properties of pore fluids},
    journal = {Geophysics},
    volume = {57},
    number = {11},
    pages = {1396-1408},
    year = {1992},
    month = {11},
    abstract = {},
    issn = {0016-8033},
    doi = {10.1190/1.1443207},
    url = {https://doi.org/10.1190/1.1443207},
    eprint = {https://pubs.geoscienceworld.org/seg/geophysics/article-pdf/57/11/1396/3161438/1396.pdf},
}
