DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: An interpretable and transferrable vision transformer model for rapid materials spectra classification

Journal Article · · Digital Discovery
DOI: https://doi.org/10.1039/D3DD00198A · OSTI ID:2281408
 [1]; ORCiD logo [1];  [1];  [1];  [2]; ORCiD logo [1]
  1. Department of Mechanical and Aerospace Engineering, University of Missouri, Columbia, MO 65201, USA
  2. Data Science Center, Graduate School of Advanced Science and Technology, Material Science Division, Nara Institute of Science and Technology (NAIST), 8916-5 Takayamacho, Ikoma City, Nara Prefecture 630-0192, Japan

An interpretable and transferrable Vision Transformer (ViT) model was developed for classifying individual materials from their XRD and FTIR spectra.

Sponsoring Organization:
USDOE
Grant/Contract Number:
NONE; FE0031988
OSTI ID:
2281408
Journal Information:
Digital Discovery, Journal Name: Digital Discovery Journal Issue: 2 Vol. 3; ISSN DDIIAI; ISSN 2635-098X
Publisher:
Royal Society of Chemistry (RSC)Copyright Statement
Country of Publication:
United Kingdom
Language:
English

References (47)

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding preprint January 2018
PaLM: Scaling Language Modeling with Pathways preprint January 2022
Mass2SMILES: deep learning based fast prediction of structures and functional groups directly from high-resolution MS/MS spectra preprint July 2023
Spectral deep learning for prediction and prospective validation of functional groups journal January 2020
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks journal March 2023
MassFormer: Tandem Mass Spectrum Prediction for Small Molecules using Graph Transformers preprint January 2021
PMTransformer: Universal Transfer Learning and Cross-material Few-shot Learning in Porous Materials preprint April 2023
Busting the myths around public investment in clean energy journal July 2022
Predicting chemical reaction outcomes: A grammar ontology‐based transformer framework journal January 2021
LLaMA: Open and Efficient Foundation Language Models preprint January 2023
Toward autonomous laboratories: Convergence of artificial intelligence and experimental automation journal February 2023
A Universal and Accurate Method for Easily Identifying Components in Raman Spectroscopy Based on Deep Learning journal March 2023
Determination of polymorphic purity by near infrared spectrometry journal February 2000
A Multiscale Visualization of Attention in the Transformer Model preprint January 2019
Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks journal May 2019
Classification of deep-sea cold seep bacteria by transformer combined with Raman spectroscopy journal February 2023
Attention Is All You Need preprint January 2017
Rapid Identification of X-ray Diffraction Patterns Based on Very Limited Data by Interpretable Convolutional Neural Networks journal March 2020
Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning journal September 2022
Accelerating the discovery of materials for clean energy in the era of smart automation journal April 2018
Learning Deep Features for Discriminative Localization preprint January 2015
Fully Automated Unconstrained Analysis of High-Resolution Mass Spectrometry Data with Machine Learning journal August 2022
Autonomy in materials research: a case study in carbon nanotube growth journal October 2016
Language Models are Few-Shot Learners preprint January 2020
Transfer‐learning‐based Raman spectra identification journal November 2019
Machine learning enhanced spectroscopic analysis: towards autonomous chemical mixture characterization for rapid process optimization journal January 2022
Machine Learning Assisted Synthesis of Metal–Organic Nanocapsules journal December 2019
Deep Learning for the Precise Peak Detection in High-Resolution LC–MS Data journal December 2019
TransG-net: transformer and graph neural network based multi-modal data fusion network for molecular properties prediction journal December 2022
Deep Learning–Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification journal May 2023
Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride journal February 2019
Learning the Language of NMR: Structure Elucidation from NMR spectra using Transformer Models preprint August 2023
A survey on Image Data Augmentation for Deep Learning journal July 2019
How to explore chemical space using algorithms and automation journal January 2019
Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction journal August 2019
Quantifying Attention Flow in Transformers preprint January 2020
Development of Crime Scene Intelligence Using a Hand-Held Raman Spectrometer and Transfer Learning journal June 2021
Scientific discovery in the age of artificial intelligence journal August 2023
Machine Learning Models Capable of Chemical Deduction for Identifying Reaction Products preprint June 2023
ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction preprint January 2020
MIST-CF: Chemical formula inference from tandem mass spectra text January 2023
Functional groups prediction from infrared spectra based on computer-assist approaches journal December 2020
Ridge regression combined with model complexity analysis for near infrared (NIR) spectroscopic model updating journal December 2019
Large language models encode clinical knowledge journal July 2023
Deep learning-based component identification for the Raman spectra of mixtures journal January 2019
Automated Experimentation Powers Data Science in Chemistry journal January 2021
Vision transformer for quality identification of sesame oil with stereoscopic fluorescence spectrum image journal March 2022