arXiv subjects

Edirisuriya M. Dilanga Siriwardane

Publications and source records attributed to Edirisuriya M. Dilanga Siriwardane.

7 recordsLinked to original sources

arXiv2022

Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts' heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700\% compared to FTCP, one of the latest structure generators and by more than 45\% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1,869 materials out of 2,000 are successfully optimized and deposited into the Carolina Materials Database \url{www.carolinamatdb.org}, of which 39.6\% have negative formation energy and 5.3\% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.

cond-mat.mtrl-sci↗

arXiv2022

Materials Transformers Language Models for Generative Materials Design: a benchmark study

Pre-trained transformer language models on large unlabeled corpus have produced state-of-the-art results in natural language processing, organic molecule design, and protein sequence generation. However, no such models have been applied to learn the composition patterns of inorganic materials. Here we train a series of seven modern transformer language models (GPT, GPT-2, GPT-Neo, GPT-J, BLMM, BART, and RoBERTa) using the expanded formulas from material deposited in the ICSD, OQMD, and Materials Projects databases. Six different datasets with/out non-charge-neutral or balanced electronegativity samples are used to benchmark the performances and uncover the generation biases of modern transformer models for the generative design of materials compositions. Our extensive experiments showed that the causal language models based materials transformers can generate chemically valid materials compositions with as high as 97.54\% to be charge neutral and 91.40\% to be electronegativity balanced, which has more than 6 times higher enrichment compared to a baseline pseudo-random sampling algorithm. These models also demonstrate high novelty and their potential in new materials discovery has been proved by their capability to recover the leave-out materials. We also find that the properties of the generated samples can be tailored by training the models with selected training sets such as high-bandgap materials. Our experiments also showed that different models each have their own preference in terms of the properties of the generated samples and their running time complexity varies a lot. We have applied our materials transformer models to discover a set of new materials as validated using DFT calculations.

cond-mat.mtrl-sci↗

arXiv2021

Semi-supervised teacher-student deep neural network for materials discovery

Data driven generative machine learning models have recently emerged as one of the most promising approaches for new materials discovery. While the generator models can generate millions of candidates, it is critical to train fast and accurate machine learning models to filter out stable, synthesizable materials with desired properties. However, such efforts to build supervised regression or classification screening models have been severely hindered by the lack of unstable or unsynthesizable samples, which usually are not collected and deposited in materials databases such as ICSD and Materials Project (MP). At the same time, there are a significant amount of unlabelled data available in these databases. Here we propose a semi-supervised deep neural network (TSDNN) model for high-performance formation energy and synthesizability prediction, which is achieved via its unique teacher-student dual network architecture and its effective exploitation of the large amount of unlabeled data. For formation energy based stability screening, our semi-supervised classifier achieves an absolute 10.3\% accuracy improvement compared to the baseline CGCNN regression model. For synthesizability prediction, our model significantly increases the baseline PU learning's true positive rate from 87.9\% to 97.9\% using 1/49 model parameters. To further prove the effectiveness of our models, we combined our TSDNN-energy and TSDNN-synthesizability models with our CubicGAN generator to discover novel stable cubic structures. Out of 1000 recommended candidate samples by our models, 512 of them have negative formation energies as validated by our DFT formation energy calculations. Our experimental results show that our semi-supervised deep neural networks can significantly improve the screening accuracy in large-scale generative materials design.

cond-mat.mtrl-sci↗

arXiv2021

Crystal structure prediction using age-fitness multi-objective genetic algorithm and coordination number constraints

Crystal structure prediction (CSP) has emerged as one of the most important approaches for discovering new materials. CSP algorithms based on evolutionary algorithms and particle swarm optimization have discovered a great number of new materials. However, these algorithms based on ab initio calculation of free energy are inefficient. Moreover, they have severe limitations in terms of scalability. We recently proposed a promising crystal structure prediction method based on atomic contact maps, using global optimization algorithms to search for the Wyckoff positions by maximizing the match between the contact map of the predicted structure and the contact map of the true crystal structure. However, our previous contact map based CSP algorithms have two major limitations: (1) the loss of search capability due to getting trapped in local optima; (2) it only uses the connection of atoms in the unit cell to predict the crystal structure, ignoring the chemical environment outside the unit cell, which may lead to unreasonable coordination environments. Herein we propose a novel multi-objective genetic algorithms for contact map-based crystal structure prediction by optimizing three objectives, including contact map match accuracy, the individual age, and the coordination number match. Furthermore, we assign the age values to all the individuals of the GA and try to minimize the age aiming to avoid the premature convergence problem. Our experimental results show that compared to our previous CMCrystal algorithm, our multi-objective crystal structure prediction algorithm (CMCrystalMOO) can reconstruct the crystal structure with higher quality and alleviate the problem of premature convergence.

cond-mat.mtrl-sci↗

arXiv2021

Crystal structure prediction of materials with high symmetry using differential evolution

Crystal structure determines properties of materials. With the crystal structure of a chemical substance, many physical and chemical properties can be predicted by first-principles calculations or machine learning models. Since it is relatively easy to generate a hypothetical chemically valid formula, crystal structure prediction becomes an important method for discovering new materials. In our previous work, we proposed a contact map-based crystal structure prediction method, which uses global optimization algorithms such as genetic algorithms to maximize the match between the contact map of the predicted structure and the contact map of the real crystal structure to search for the coordinates at the Wyckoff Positions(WP). However, when predicting the crystal structure with high symmetry, we found that the global optimization algorithm has difficulty to find an effective combination of WPs that satisfies the chemical formula, which is mainly caused by the inconsistency between the dimensionality of the contact map of the predicted crystal structure and the dimensionality of the contact map of the target crystal structure. This makes it challenging to predict the crystal structures of high-symmetry crystals. In order to solve this problem, here we propose to use PyXtal to generate and filter random crystal structures with given symmetry constraints based on the information such as chemical formulas and space groups. With contact map as the optimization goal, we use differential evolution algorithms to search for non-special coordinates at the Wyckoff positions to realize the structure prediction of high-symmetry crystal materials. Our experimental results show that our proposed algorithm CMCrystalHS can effectively solve the problem of inconsistent contact map dimensions and predict the crystal structures with high symmetry.

cond-mat.mtrl-sci↗

arXiv2020

Computational discovery of new 2D materials using deep learning generative models

Two dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties. While several thousand 2D materials have been screened in existing materials databases, discovering new 2D materials remains to be challenging. Herein we propose a deep learning generative model for composition generation combined with random forest based 2D materials classifier to discover new hypothetical 2D materials. Furthermore, a template based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. So far, we have discovered 267,489 new potential 2D materials compositions and confirmed twelve 2D/layered materials by DFT formation energy calculation. Our results show that generative machine learning models provide an effective way to explore the vast chemical design space for new 2D materials discovery.

cond-mat.mtrl-sci↗

arXiv2020

Distance Matrix based Crystal Structure Prediction using Evolutionary Algorithms

Crystal structure prediction (CSP) for inorganic materials is one of the central and most challenging problems in materials science and computational chemistry. This problem can be formulated as a global optimization problem in which global search algorithms such as genetic algorithms (GA) and particle swarm optimization have been combined with first principle free energy calculations to predict crystal structures given only a material composition or only a chemical system. These DFT based ab initio CSP algorithms are computationally demanding and can only be used to predict crystal structures of relatively small systems. The vast coordinate space plus the expensive DFT free energy calculations limits their efficiency and effectiveness. On the other hand, a similar structure prediction problem has been intensively investigated in parallel in the protein structure prediction community of bioinformatics, in which the dominating predictors are knowledge based approaches including homology modeling and threading that exploit known protein structures. Herein we explore whether known geometric constraints such as the pairwise atomic distances of a target crystal material can help predict/reconstruct its structure given its space group and lattice information. We propose DMCrystal, a genetic algorithm based crystal structure reconstruction algorithm based on predicted atomic pairwise distances. Based on extensive experiments, we show that the predicted distance matrix can dramatically help to reconstruct the crystal structure and usually achieves much better performance than CMCrystal, an atomic contact map based crystal structure prediction algorithm. This implies that knowledge of atomic interaction information learned from existing materials can be used to significantly improve the crystal structure prediction in terms of both speed and quality.

cond-mat.mtrl-sci↗