Edirisuriya M. Dilanga Siriwardane

University of Colombo

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Jianjun Hu

University of South Carolina

Yong Zhao

Southwest Jiaotong University

Yuqi Song

Australian Regenerative Medicine Institute

DÇ

Deniz Çakır

University of North Dakota

Rongzhi Dong

University of South Carolina

Nihang Fu

University of South Carolina

Steph-Yves Louis

University of South Carolina

Sadman Sadeed Omee

University of South Carolina

Wenhui Yang

Nanjing Institute of Technology

Lai Wei

University of South Carolina

Cooperative Institutions

University of South Carolina

University of North Dakota

Guizhou University

University of Colombo

University of Antwerp

Chinese Academy of Sciences

Cornell University

Central South University

Northwestern Polytechnical University

Shenzhen University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Contact map based crystal structure prediction using global optimization

CrystEngComm (2021)

Jianjun Hu Wenhui Yang Rongzhi Dong Yuxin Li Li Xiang

Crystal structure prediction is now playing an increasingly important role in the discovery of new materials or crystal engineering.

Crystal Structure Prediction

Crystal (programming language)

10.1039/d0ce01714k

Cite

Citations (21)

Physics guided deep learning for generative design of crystal materials with symmetry constraints

npj Computational Materials (2023)

Yong Zhao Edirisuriya M. Dilanga Siriwardane Zhenyao Wu Nihang Fu Mohammed Al‐Fahdi

Abstract 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 1869 materials out of 2000 are successfully optimized and deposited into the Carolina Materials Database 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.

Crystal (programming language)

Generative model

10.1038/s41524-023-00987-9

Cite

Citations (54)

Revealing the Formation Energy–Exfoliation Energy–Structure Correlation of MAB Phases Using Machine Learning and DFT

ACS Applied Materials & Interfaces (2020)

Edirisuriya M. Dilanga Siriwardane Rajendra P. Joshi Neeraj Kumar Deniz Çakır

MAB phases became popular as ultrahigh-temperature materials with high damage tolerance and excellent electrical conductivity. MAB is used to exfoliate two-dimensional (2D) transition-metal borides (MBenes), which are promising materials for developing next-generation nanodevices. In this report, we explore the correlation between the formation energy, exfoliation energy, and structural factors of MAB phases with orthorhombic and hexagonal crystal symmetries using density functional theory (DFT) and machine learning. For this, we developed three different machine learning models based on the support vector machine, deep neural network, and random forest regressor to study the stability of the MAB phases by calculating their formation energies. Our support vector machine and deep neural network models are capable of predicting the formation energies with mean absolute errors less than 0.1 eV/atom. MAB phases with the chemical formulas, MAB, M2AB2, and M3AB4, where M = Nb, Mn, Ti, W, V, Sc, Cr, Hf, Mo, Zr, Ta, and Fe, and A = group III-A elements (Al, Ga, In and Tl), were investigated to find out the formation energy and their structure correlation. We demonstrated that the stability of a MAB phase for a given transition-metal decreases when the A element changes from Al to Tl. DFT revealed that M–A and B–A bond strength strongly correlates with the stability of MAB phases. In addition, the exfoliation possibility of 2D MBenes becomes higher when the A element changes from Al to Tl because of weakening of M–A and B–A bonds.

Orthorhombic crystal system

Exfoliation joint

10.1021/acsami.0c03536

Cite

Citations (38)

Material transformers: deep learning language models for generative materials design

Machine Learning Science and Technology (2022)

Nihang Fu Lai Wei Yuqi Song Qinyang Li Rui Xin

Abstract Pre-trained transformer language models (LMs) 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 for the generative design of material compositions. Here we train a series of seven modern transformer models (GPT, GPT-2, GPT-Neo, GPT-J, BLMM, BART, and RoBERTa) for materials design using the expanded formulas of the ICSD, OQMD, and Materials Projects databases. Six different datasets with/out non-charge-neutral or EB samples are used to benchmark the generative design performances and uncover the biases of modern transformer models for the generative design of materials compositions. Our experiments show that the materials transformers based on causal LMs can generate chemically valid material compositions with as high as 97.61% to be charge neutral and 91.22% to be electronegativity balanced, which has more than six times higher enrichment compared to the baseline pseudo-random sampling algorithm. Our LMs also demonstrate high generation novelty and their potential in new materials discovery is proved by their capability to recover the leave-out materials. We also find that the properties of the generated compositions can be tailored by training the models with selected training sets such as high-bandgap samples. Our experiments also show 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 transformers to discover a set of new materials as validated using density functional theory calculations. All our trained materials transformer models and code can be accessed freely at http://www.github.com/usccolumbia/MTransformer .

Generative model

10.1088/2632-2153/acadcd

Cite

Citations (15)

Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials

arXiv (Cornell University) (2022)

Lai Wei Qinyang Li Yuqi Song Stanislav Stefanov Edirisuriya M. Dilanga Siriwardane

Self-supervised neural language models have recently achieved unprecedented success, from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking-based pre-trained language models are not designed for generative design, and their black-box nature makes it difficult to interpret their design logic. Here we propose BLMM Crystal Transformer, a neural network based probabilistic generative model for generative and tinkering design of inorganic materials. Our model is built on the blank filling language model for text generation and has demonstrated unique advantages in learning the "materials grammars" together with high-quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7\% charge neutrality and 84.8\% balanced electronegativity, which are more than 4 and 8 times higher compared to a pseudo random sampling baseline. The probabilistic generation process of BLMM allows it to recommend tinkering operations based on learned materials chemistry and makes it useful for materials doping. Combined with the TCSP crysal structure prediction algorithm, We have applied our model to discover a set of new materials as validated using DFT calculations. Our work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user-friendly web app has been developed for computational materials doping and can be accessed freely at \url{www.materialsatlas.org/blmtinker}.

Generative model

Interpretability

10.48550/arxiv.2204.11953

Cite

Citations (5)

Enhanced Electrochemical Storage Properties of Na- and Mg-Intercalated B-Doped-Graphene Based Heterostructures and Bilayers

The Journal of Physical Chemistry (2019)

Edirisuriya M. Dilanga Siriwardane Deniz Çakır

Modern technology requires novel materials to develop efficient storage systems, which offer high storage capacities and charging/discharging rates while maintaining good mechanical stability and cyclic lifetime. The extended surface areas in the lightweight two-dimensional (2D) materials are useful to achieve a high gravimetric capacity. Among various 2D materials, Ti₂CO₂ and B-doped graphene (≈8%) were selected because of their low molecular weight and good electrical conductivity. Highly abundant Na and Mg are convenient to lower the production cost of ion storage. In this study, we performed first-principles calculations to examine the suitability of Na and Mg intercalation in Ti₂CO₂/B-doped-graphene (B-Gr) heterostructures and B-Gr bilayers. Even though Na- and Mg-intercalated bare graphene bilayers are not energetically stable, our studies reveal that (B-Gr) bilayers facilitate the storing of those ions. As a consequence of smaller atomic size, Mg-intercalated systems show low structural deformations and interlayer distance change (≤0.5 A) and low in-plane lattice constant change (≤0.1%), indicating good mechanical stability during the charging/discharging process. The considered bilayers provide higher capacities than MXene-based heterostructures. Na- and Mg-intercalated Ti₂CO₂/B-Gr systems allow 240.4 and 295.1 mA h/g storage capacities, respectively. In comparison, the calculated gravimetric storage capacities for Na- and Mg-intercalated B-Gr bilayers are 283.8 and 320.6 mA h/g, respectively. All ion-intercalated systems provide average voltages greater than 0.75 V. Our diffusion barrier calculations revealed that very low diffusion barriers, as small as 0.18 eV, are expected for the Na-intercalated systems, offering fast charging/discharging rates for battery applications.

Gravimetric analysis

Source

Cite

Citations (0)

Generative design of stable semiconductor materials using deep learning and density functional theory

npj Computational Materials (2022)

Edirisuriya M. Dilanga Siriwardane Yong Zhao Indika Perera Jianjun Hu

Abstract Semiconductor device technology has greatly developed in complexity since discovering the bipolar transistor. In this work, we developed a computational pipeline to discover stable semiconductors by combining generative adversarial networks (GAN), classifiers, and high-throughput first-principles calculations. We used CubicGAN, a GAN-based algorithm for generating cubic materials and developed a classifier to screen the semiconductors and studied their stability using first principles. We found 12 stable AA $${}^{\prime}$$ ′ MH 6 semiconductors in the F-43m space group including BaNaRhH 6 , BaSrZnH 6 , BaCsAlH 6 , SrTlIrH 6 , KNaNiH 6 , NaYRuH 6 , CsKSiH 6 , CaScMnH 6 , YZnMnH 6 , NaZrMnH 6 , AgZrMnH 6 , and ScZnMnH 6 . Previous research reported that five AA $${}^{\prime}$$ ′ IrH6 semiconductors with the same space group were synthesized. Our research shows that AA $${}^{\prime}$$ ′ MnH 6 and NaYRuH 6 semiconductors have considerably different properties compared to the rest of the AA $${}^{\prime}$$ ′ MH 6 semiconductors. Based on the accurate hybrid functional calculations, AA $${}^{\prime}$$ ′ MH 6 semiconductors are found to be wide-bandgap semiconductors. Moreover, BaSrZnH 6 and KNaNiH 6 are direct-bandgap semiconductors, whereas others exhibit indirect bandgaps.

10.1038/s41524-022-00850-3

Cite

Citations (19)

Electronic and Magnetic Property Modulation of MnCrNO2 Ferromagnetic Semiconductor MXene

Physical Chemistry Chemical Physics (2024)

Sudil Sandeepa Dewamuni Buddi Oshada Vithanage Deniz Çakır Edirisuriya M. Dilanga Siriwardane

A DFT study explored the properties of MnCrNO 2 MXene, revealing a linear relationship of its band gap and magnetic anisotropy energy as a function of biaxial strain. Adsorption of alkali and alkaline earth metals significantly modulates the band gap.

Modulation (music)

Magnetic semiconductor

10.1039/d4cp01810a

Cite

Citations (0)

Materials synthesizability and stability prediction using a semi-supervised teacher-student dual neural network

Digital Discovery (2023)

Daniel Gleaves Nihang Fu Edirisuriya M. Dilanga Siriwardane Yong Zhao Jianjun Hu

A semi-supervised deep neural network (TSDNN) model based on teacher-student architecture is developed for high-performance formation energy and synthesizability prediction by exploiting a large number of unlabelled samples.

10.1039/d2dd00098a

Cite

Citations (6)

Data-driven deep generative design of stable spintronic materials

CrystEngComm (2023)

Edirisuriya M. Dilanga Siriwardane Yong Zhao Jianjun Hu

A computational framework that integrates generative adversarial networks and machine learning classifiers to enable the discovery of novel magnetic materials.

Generative adversarial network

10.1039/d3ce00765k

Cite

Citations (2)