Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning

  title={Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning},
  author={Di Chen and Yiwei Bai and Sebastian Ament and Wenting Zhao and D. Guevarra and Lan Zhou and Bart Selman and Robert Bruce van Dover and J. Gregoire and Carla P. Gomes},
  journal={Nat. Mach. Intell.},
  • Di Chen, Yiwei Bai, +7 authors Carla P. Gomes
  • Published 21 August 2021
  • Computer Science, Physics
  • Nat. Mach. Intell.
1Department of Computer Science, Cornell University, Ithaca, NY, USA. 2Division of Engineering and Applied Science and Liquid Sunlight Alliance, California Institute of Technology, Pasadena, CA, USA. 3Department of Materials Science and Engineering, Cornell University, Ithaca, NY, USA. ✉e-mail:; Artificial intelligence (AI)1 aims to develop intelligent systems, inspired in part by human intelligence. AI systems are now performing at human and even… Expand
1 Citations

Figures from this paper

Computational sustainability meets materials science
Computational sustainability harnesses computing and artificial intelligence for human well-being and the protection of our planet. Materials science is central to many sustainability challenges.Expand


Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
On CrystalStructure-Phase-Mapping, DRNets significantly outperform the state of the art and experts’ capabilities, recovering more precise and physically meaningful crystal structures. Expand
Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks
The scarce data problem intrinsic to novel materials development is overcome by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. Expand
Inverse molecular design using machine learning: Generative models for matter engineering
Methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality, are reviewed. Expand
Materials Representation and Transfer Learning for Multi-Property Prediction
The Hierarchical Correlation Learning for Multi-property Prediction (H-CLMP) framework is introduced that seamlessly integrates prediction using only a material’s composition, learning and exploitation of correlations among target properties in multitarget regression, and leveraging training data from tangential domains via generative transfer learning. Expand
Materials representation and transfer learning for multi-property prediction
The adoption of machine learning in materials science has rapidly transformed materials property prediction. Hurdles limiting full capitalization of recent advancements in machine learning includeExpand
Accelerated Development of Perovskite-Inspired Materials via High-Throughput Synthesis and Machine-Learning Diagnosis
A fully connected deep neural network is utilized to classify compounds based on experimental X-ray diffraction data into 0D, 2D, and 3D structures, more than 10 times faster than human analysis and with 90% accuracy. Expand
Neurosymbolic AI: The 3rd Wave
The insights provided by 20 years of neural-symbolic computing are shown to shed new light onto the increasingly prominent role of trust, safety, interpretability and accountability of AI. Expand
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
A semantic loss function is derived from first principles that bridges between neural output vectors and logical constraints and significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. Expand
CRYSTAL: a multi-agent AI system for automated mapping of materials’ crystal structures
We introduce CRYSTAL, a multi-agent AI system for crystal-structure phase mapping. CRYSTAL is the first system that can automatically generate a portfolio of physically meaningful phase diagrams forExpand
Generalized machine learning technique for automatic phase attribution in time variant high-throughput experimental studies
Phase identification is an arduous task during high-throughput processing experiments, which can be exacerbated by the need to reconcile results from multiple measurement techniques to form aExpand