Invertible crystallographic representation for inorganic crystals via new API

This project aims to improve thermoelectric material identification and evaluation by utilizing the advanced machine-learning framework. We utilize the vast dataset of the Materials Project database, focusing on material properties including formation energy, band gap, and crystal structure, b...

Full description

Saved in:
Bibliographic Details
Main Author: Phone Myint
Other Authors: Kedar Hippalgaonkar
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/174589
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-174589
record_format dspace
spelling sg-ntu-dr.10356-1745892024-04-06T16:45:41Z Invertible crystallographic representation for inorganic crystals via new API Phone Myint Kedar Hippalgaonkar School of Materials Science and Engineering kedar@ntu.edu.sg Engineering Invertible crystallographic representation Inorganic crystals Thermoelectric properties This project aims to improve thermoelectric material identification and evaluation by utilizing the advanced machine-learning framework. We utilize the vast dataset of the Materials Project database, focusing on material properties including formation energy, band gap, and crystal structure, by combining Variational Autoencoders (VAEs) with semi-supervised learning approaches. Specifically, the approach develops a Fourier Transformed Crystal Properties (FTCP) representation that is carefully designed for deep learning applications. This representation enables our model to encode complex, high-dimensional data into a concise latent space. From this latent space, we develop new materials by the manipulation of latent variables and their subsequent decoding, revealing materials with improved thermoelectric characteristics, such as optimized Seebeck coefficients. This method improves the model's learning process and prediction ability by utilizing both labelled and unlabeled data, going beyond traditional supervised learning. With the help of advanced training strategies like dynamic learning rate adjustments and thorough preparation processes like data normalization and augmentation, the model demonstrates a remarkable ability to predict material attributes. Furthermore, the interaction between different material properties and how that interaction affects thermoelectric performance may be better understood using graphical analysis. This project not only demonstrates the revolutionary potential of machine learning in material science, but it had also established a new standard for the effective and scalable search for advanced thermoelectric materials. Using the model's predictive capability, we set out to investigate the wide range of possible materials to find and develop materials that have the potential to revolutionize thermoelectric technology in the future. Hence, this effort demonstrates the complementary nature of material science and computational science and opens a new path for creative approaches to energy conversion and management. Bachelor's degree 2024-04-03T05:44:37Z 2024-04-03T05:44:37Z 2024 Final Year Project (FYP) Phone Myint (2024). Invertible crystallographic representation for inorganic crystals via new API. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/174589 https://hdl.handle.net/10356/174589 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Invertible crystallographic representation
Inorganic crystals
Thermoelectric properties
spellingShingle Engineering
Invertible crystallographic representation
Inorganic crystals
Thermoelectric properties
Phone Myint
Invertible crystallographic representation for inorganic crystals via new API
description This project aims to improve thermoelectric material identification and evaluation by utilizing the advanced machine-learning framework. We utilize the vast dataset of the Materials Project database, focusing on material properties including formation energy, band gap, and crystal structure, by combining Variational Autoencoders (VAEs) with semi-supervised learning approaches. Specifically, the approach develops a Fourier Transformed Crystal Properties (FTCP) representation that is carefully designed for deep learning applications. This representation enables our model to encode complex, high-dimensional data into a concise latent space. From this latent space, we develop new materials by the manipulation of latent variables and their subsequent decoding, revealing materials with improved thermoelectric characteristics, such as optimized Seebeck coefficients. This method improves the model's learning process and prediction ability by utilizing both labelled and unlabeled data, going beyond traditional supervised learning. With the help of advanced training strategies like dynamic learning rate adjustments and thorough preparation processes like data normalization and augmentation, the model demonstrates a remarkable ability to predict material attributes. Furthermore, the interaction between different material properties and how that interaction affects thermoelectric performance may be better understood using graphical analysis. This project not only demonstrates the revolutionary potential of machine learning in material science, but it had also established a new standard for the effective and scalable search for advanced thermoelectric materials. Using the model's predictive capability, we set out to investigate the wide range of possible materials to find and develop materials that have the potential to revolutionize thermoelectric technology in the future. Hence, this effort demonstrates the complementary nature of material science and computational science and opens a new path for creative approaches to energy conversion and management.
author2 Kedar Hippalgaonkar
author_facet Kedar Hippalgaonkar
Phone Myint
format Final Year Project
author Phone Myint
author_sort Phone Myint
title Invertible crystallographic representation for inorganic crystals via new API
title_short Invertible crystallographic representation for inorganic crystals via new API
title_full Invertible crystallographic representation for inorganic crystals via new API
title_fullStr Invertible crystallographic representation for inorganic crystals via new API
title_full_unstemmed Invertible crystallographic representation for inorganic crystals via new API
title_sort invertible crystallographic representation for inorganic crystals via new api
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/174589
_version_ 1800916412901883904