paper.bib

@article{aykol_network_2019,
  title = {Network Analysis of Synthesizable Materials Discovery},
  author = {Aykol, Muratahan and Hegde, Vinay I. and Hung, Linda and Suram, Santosh and Herring, Patrick and Wolverton, Chris and Hummelsh{\o}j, Jens S.},
  year = {2019},
  month = may,
  journal = {Nat Commun},
  volume = {10},
  number = {1},
  pages = {2018},
  publisher = {{Nature Publishing Group}},
  issn = {2041-1723},
  doi = {10.1038/s41467-019-10030-5},
  urldate = {2022-11-14},
  abstract = {Assessing the synthesizability of inorganic materials is a grand challenge for accelerating their discovery using computations. Synthesis of a material is a complex process that depends not only on its thermodynamic stability with respect to others, but also on factors from kinetics, to advances in synthesis techniques, to the availability of precursors. This complexity makes the development of a general theory or first-principles approach to synthesizability currently impractical. Here we show how an alternative pathway to predicting synthesizability emerges from the dynamics of the materials stability network: a scale-free network constructed by combining the convex free-energy surface of inorganic materials computed by high-throughput density functional theory and their experimental discovery timelines extracted from citations. The time-evolution of the underlying network properties allows us to use machine-learning to predict the likelihood that hypothetical, computer-generated materials will be amenable to successful experimental synthesis.},
  copyright = {2019 The Author(s)},
  langid = {english},
  keywords = {Design,Inorganic chemistry,synthesis and processing,Theory and computation},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\AZKKCSDJ\\Aykol et al_2019_Network analysis of synthesizable materials discovery.pdf;C\:\\Users\\sterg\\Zotero\\storage\\26BR3D5L\\s41467-019-10030-5.html}
}

@article{baird_xtal2png_2022,
  title = {Xtal2png: {{A Python}} Package for Representing Crystalstructure as {{PNG}} Files},
  shorttitle = {Xtal2png},
  author = {Baird, Sterling G. and Jablonka, Kevin M. and Alverson, Michael D. and Sayeed, Hasan M. and Khan, Mohammed Faris and Seegmiller, Colton and Smit, Berend and Sparks, Taylor D.},
  year = {2022},
  month = aug,
  journal = {JOSS},
  volume = {7},
  number = {76},
  pages = {4528},
  issn = {2475-9066},
  doi = {10.21105/joss.04528},
  urldate = {2022-08-05},
  abstract = {The latest advances in machine learning are often in natural language processing such as with long short-term memory networks (LSTMs) and Transformers, or image processing such as with generative adversarial networks (GANs), variational autoencoders (VAEs), and guided diffusion models. xtal2png encodes and decodes crystal structures via PNG images (see e.g. Figure 1) by writing and reading the necessary information for crystal reconstruction (unit cell, atomic elements, atomic coordinates) as a square matrix of numbers. This is akin to making/reading a QR code for crystal structures, where the xtal2png representation is an invertible representation. The ability to feed these images directly into image-based pipelines allows you, as a materials informatics practitioner, to get streamlined results for new state-of-the-art image-based machine learning models applied to crystal structures.},
  langid = {english},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\CGJ99564\\Baird et al_2022_xtal2png.pdf}
}

@article{jain_commentary_2013,
  title = {Commentary: {{The Materials Project}}: {{A}} Materials Genome Approach to Accelerating Materials Innovation},
  shorttitle = {Commentary},
  author = {Jain, Anubhav and Ong, Shyue Ping and Hautier, Geoffroy and Chen, Wei and Richards, William Davidson and Dacek, Stephen and Cholia, Shreyas and Gunter, Dan and Skinner, David and Ceder, Gerbrand and Persson, Kristin A.},
  year = {2013},
  month = jul,
  journal = {APL Materials},
  volume = {1},
  number = {1},
  pages = {011002},
  publisher = {{American Institute of Physics}},
  doi = {10.1063/1.4812323},
  urldate = {2022-11-14},
  abstract = {Accelerating the discovery of advanced materials is essential for human welfare and sustainable, clean energy. In this paper, we introduce the Materials Project (www.materialsproject.org), a core program of the Materials Genome Initiative that uses high-throughput computing to uncover the properties of all known inorganic materials. This open dataset can be accessed through multiple channels for both interactive exploration and data mining. The Materials Project also seeks to create open-source platforms for developing robust, sophisticated materials analyses. Future efforts will enable users to perform ``rapid-prototyping'' of new materials in silico, and provide researchers with new avenues for cost-effective, data-driven materials design.},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\CLQCGW93\\Jain et al_2013_Commentary.pdf}
}

@article{palizhati_agents_2022,
  title = {Agents for Sequential Learning Using Multiple-Fidelity Data},
  author = {Palizhati, Aini and Torrisi, Steven B. and Aykol, Muratahan and Suram, Santosh K. and Hummelsh{\o}j, Jens S. and Montoya, Joseph H.},
  year = {2022},
  month = mar,
  journal = {Sci Rep},
  volume = {12},
  number = {1},
  pages = {4694},
  publisher = {{Nature Publishing Group}},
  issn = {2045-2322},
  doi = {10.1038/s41598-022-08413-8},
  urldate = {2022-11-14},
  abstract = {Sequential learning for materials discovery is a paradigm where a computational agent solicits new data to simultaneously update a model in service of exploration (finding the largest number of materials that meet some criteria) or exploitation (finding materials with an ideal figure of merit). In real-world discovery campaigns, new data acquisition may be costly and an optimal strategy may involve using and acquiring data with different levels of fidelity, such as first-principles calculation to supplement an experiment. In this work, we introduce agents which can operate on multiple data fidelities, and benchmark their performance on an emulated discovery campaign to find materials with desired band gap values. The fidelities of data come from the results of DFT calculations as low fidelity and experimental results as high fidelity. We demonstrate performance gains of agents which incorporate multi-fidelity data in two contexts: either using a large body of low fidelity data as a prior knowledge base or acquiring low fidelity data in-tandem with experimental data. This advance provides a tool that enables materials scientists to test various acquisition and model hyperparameters to maximize the discovery rate of their own multi-fidelity sequential learning campaigns for materials discovery. This may also serve as a reference point for those who are interested in practical strategies that can be used when multiple data sources are available for active or sequential learning campaigns.},
  copyright = {2022 The Author(s)},
  langid = {english},
  keywords = {Chemistry,Energy science and technology,Engineering,Materials science,Mathematics and computing,Optics and photonics},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\DH8KQM5X\\Palizhati et al_2022_Agents for sequential learning using multiple-fidelity data.pdf;C\:\\Users\\sterg\\Zotero\\storage\\845UQV6C\\s41598-022-08413-8.html}
}

@article{pedregosa_scikit-learn_2011,
  title = {Scikit-Learn: {{Machine Learning}} in {{Python}}},
  shorttitle = {Scikit-Learn},
  author = {Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and Vanderplas, Jake and Passos, Alexandre and Cournapeau, David and Brucher, Matthieu and Perrot, Matthieu and Duchesnay, {\'E}douard},
  year = {2011},
  journal = {Journal of Machine Learning Research},
  volume = {12},
  number = {85},
  pages = {2825--2830},
  issn = {1533-7928},
  urldate = {2022-11-14},
  abstract = {Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net.},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\AT4FWI28\\Pedregosa et al_2011_Scikit-learn.pdf}
}

@article{tshitoyan_unsupervised_2019,
  title = {Unsupervised Word Embeddings Capture Latent Knowledge from Materials Science Literature},
  author = {Tshitoyan, Vahe and Dagdelen, John and Weston, Leigh and Dunn, Alexander and Rong, Ziqin and Kononova, Olga and Persson, Kristin A. and Ceder, Gerbrand and Jain, Anubhav},
  year = {2019},
  month = jul,
  journal = {Nature},
  volume = {571},
  number = {7763},
  pages = {95--98},
  issn = {0028-0836, 1476-4687},
  doi = {10.1038/s41586-019-1335-8},
  urldate = {2022-08-06},
  langid = {english},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\5UP8VYLB\\Tshitoyan et al. - 2019 - Unsupervised word embeddings capture latent knowle.pdf}
}

@misc{zhao_physics_2022,
  title = {Physics {{Guided Generative Adversarial Networks}} for {{Generations}} of {{Crystal Materials}} with {{Symmetry Constraints}}},
  author = {Zhao, Yong and Siriwardane, Edirisuriya M. Dilanga and Wu, Zhenyao and Hu, Ming and Fu, Nihang and Hu, Jianjun},
  year = {2022},
  month = mar,
  number = {arXiv:2203.14352},
  eprint = {2203.14352},
  primaryclass = {cond-mat},
  publisher = {{arXiv}},
  urldate = {2022-06-24},
  abstract = {Discovering new materials is a long-standing challenging task that is critical to the progress of human society. Conventional approaches such as trial-and-error experiments and computational simulations are labor-intensive or costly with their success heavily depending on experts' heuristics. Recently deep generative models have been successfully proposed for materials generation by learning implicit knowledge from known materials datasets, with performance however limited by their confinement to a special material family or failing to incorporate physical rules into the model training process. Here we propose a Physics Guided Crystal Generative Model (PGCGM) for new materials generation, which captures and exploits the pairwise atomic distance constraints among neighbor atoms and symmetric geometric constraints. By augmenting the base atom sites of materials, our model can generates new materials of 20 space groups. With atom clustering and merging on generated crystal structures, our method increases the generator's validity by 8 times compared to one of the baselines and by 143\% compared to the previous CubicGAN along with its superiority in properties distribution and diversity. We further validated our generated candidates by Density Functional Theory (DFT) calculation, which successfully optimized/relaxed 1869 materials out of 2000, of which 39.6\% are with negative formation energy, indicating their stability.},
  archiveprefix = {arxiv},
  langid = {english},
  keywords = {Computer Science - Machine Learning,Condensed Matter - Materials Science},
  file = {C\:\\Users\\sterg\\Zotero\\storage\\FFITBMRW\\Zhao et al. - 2022 - Physics Guided Generative Adversarial Networks for.pdf}
}