Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks

@article{Kim2020InorganicMS,
  title={Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks},
  author={Edward Kim and Zach Jensen and Alexander van Grootel and Kevin Huang and Matthew Staib and Sheshera Mysore and Haw-Shiuan Chang and Emma Strubell and Andrew McCallum and Stefanie Jegelka and Elsa A. Olivetti},
  journal={Journal of chemical information and modeling},
  year={2020}
}
  • Edward Kim, Z. Jensen, +8 authors E. Olivetti
  • Published 31 December 2018
  • Physics, Computer Science, Mathematics, Materials Science, Medicine
  • Journal of chemical information and modeling
Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated, unsupervised method for connecting scientific literature to inorganic synthesis insights. Starting from natural language text, we apply word embeddings from language models, which are fed into a named entity recognition model, upon which a conditional variational… Expand
Dataset of Solution-based Inorganic Materials Synthesis Recipes Extracted from the Scientific Literature
The development of a materials synthesis route is usually based on heuristics and experience. A possible new approach would be to apply data-driven approaches to learn the patterns of synthesis fromExpand
Automated extraction of chemical synthesis actions from experimental procedures
TLDR
A deep-learning model based on the transformer architecture to translate experimental procedures from the field of organic chemistry into synthesis actions is developed and refined on manually annotated samples. Expand
Analyzing Research Trends in Inorganic Materials Literature Using NLP
TLDR
This study proposes a large-scale natural language processing (NLP) pipeline for extracting material names and properties from materials science literature to enable the search and retrieval of results in materials science and builds a corpus containing 836 annotated paragraphs extracted from 301 papers for training a named entity recognition (NER) model. Expand
A Machine Learning Approach to Zeolite Synthesis Enabled by Automatic Literature Data Extraction
TLDR
This paper creates natural language processing techniques and text markup parsing tools to automatically extract synthesis information and trends from zeolite journal articles and engineer a data set of germanium-containing zeolites to test the accuracy of the extracted data and to discover potential opportunities for zeolitic morphologies. Expand
Recent Advances and Applications of Deep Learning Methods in Materials Science
Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allowsExpand
Data Augmentation Technique for Process Extraction in Chemistry Publications
In the field of materials science and chemistry, deep understanding of the relation between structure and properties is required for creating new materials. Academists and scientists often seek forExpand
Emerging materials intelligence ecosystems propelled by machine learning
The age of cognitive computing and artificial intelligence (AI) is just dawning. Inspired by its successes and promises, several AI ecosystems are blossoming, many of them within the domain ofExpand
Discovering Relationships between OSDAs and Zeolites through Data Mining and Generative Neural Networks
TLDR
A data-driven approach to unearth generalized OSDA–zeolite relationships using a comprehensive database comprising of 5,663 synthesis routes for porous materials and adapts a generative neural network capable of suggesting new molecules as potential OSDAs for a given zeolite structure and gel chemistry. Expand
Extracting and analyzing inorganic material synthesis procedures in the literature
TLDR
This study proposes a pipeline system that extracts synthesis procedures from a text in the form of a graph with a clear order of operations and objects of conditioning from the literature and applies it to a large body of literature. Expand
Extraction of Inorganic Material Synthesis Procedure from Literature
Structured information extraction from the literature has always been an indispensable technique to support data-driven methods in various fields. However, due to the lack of machinereadable datasetsExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Machine-learned and codified synthesis parameters of oxide materials
TLDR
A collection of aggregated synthesis parameters computed using the text contained within over 640,000 journal articles using state-of-the-art natural language processing and machine learning techniques is presented. Expand
Virtual screening of inorganic materials synthesis parameters with deep learning
TLDR
A framework for suggesting quantitative synthesis parameters and potential driving factors for synthesis outcomes is presented, using a variational autoencoder to compress sparse synthesis representations into a lower dimensional space, which is found to improve the performance of machine-learning tasks. Expand
Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning
In the past several years, Materials Genome Initiative (MGI) efforts have produced myriad examples of computationally designed materials in the fields of energy storage, catalysis, thermoelectrics,Expand
Semi-supervised machine-learning classification of materials synthesis procedures
TLDR
This work demonstrates a semi-supervised machine-learning method to classify inorganic materials synthesis procedures from written natural language, and shows that a Markov chain representation of the order of experimental steps accurately reconstructs a flowchart of possible synthesis procedures. Expand
Planning chemical syntheses with deep neural networks and symbolic AI
TLDR
This work combines Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps that solve for almost twice as many molecules, thirty times faster than the traditional computer-aided search method. Expand
Network analysis of synthesizable materials discovery
TLDR
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 is shown. Expand
Machine-learning-assisted materials discovery using failed experiments
TLDR
This work demonstrates an alternative approach that uses machine-learning algorithms trained on reaction data to predict reaction outcomes for the crystallization of templated vanadium selenites, and successfully predicted conditions for new organically Templated inorganic product formation. Expand
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.
TLDR
A crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Expand
Prediction of Organic Reaction Outcomes Using Machine Learning
TLDR
A model framework for anticipating reaction outcomes that combines the traditional use of reaction templates with the flexibility in pattern recognition afforded by neural networks is reported. Expand
Combinatorial screening for new materials in unconstrained composition space with machine learning
Typically, computational screens for new materials sharply constrain the compositional search space, structural search space, or both, for the sake of tractability. To lift these constraints, weExpand
...
1
2
3
4
5
...