POSTECH

Project

Project

  2. Big-data collection

NLP based database generation from scientific document

 As the interest in machine learning increases, the interest in databases for use in machine learning is also increasing. Despite the increasing demand for databases in the material field, there is no clear database to date. Therefore, in this project, we intend to build a database based on research results in the field of materials existing in Internet documents through natural language processing techniques.

  • Machine learning application

Assessing Additive Compositions for Glass Using MLP, MD, and DFT-based Simulations

 Amorphous silicon dioxide (SiO₂) is a fundamental oxide material with extensive scientific and commercial applications, attributed to its excellent thermal properties, dielectric characteristics, and optical transmission performance. To enhance the transparency of silica glass—the amorphous form of SiO₂—dopants such as germanium (Ge) or titanium (Ti) are often introduced to increase optical light transmission. Using ab initio molecular dynamics, potential datasets are generated on Ge- and Ti-doped amorphous SiO₂ to train machine learning potentials. These trained models enable the reproduction of amorphous structures with quantum-level accuracy. The dielectric constant, and consequently the refractive index, of the Ge/Ti-doped amorphous SiO₂ is then calculated to assess the system’s transmission coefficient.

Full-Cycle AI Technology for Developing Ferroelectrics toward In-Memory Computing

 In-memory computing (IMC) is a computing technology that performs data storage and computation within the system’s main memory, overcoming the von Neumann bottleneck. The IMC systems require superior memory devices with both scalable, non-volatile storage and low-power, high-endurance, high-speed computing properties. Ferroelectric RAM (FeRAM) is a promising device for IMC systems, which is non-volatile and low power operation, but its large cell-size and weak endurance are still in challenges. A full-cycle AI-based materials design integrates materials, process, microstructure, device, and circuit level properties through AI-driven generation, prediction, and optimization. Using an automated data crawling system based on natural language processing (NLP) with experimental validation process, this design system can rapidly predict optimal recipes for superior FeRAM devices, addressing the shortcomings in current IMC applications.

Understanding the domain walls movement of ferroelectric HfO2 with machine learning potential

 HfO2-based FeRAM has been spotlighted as a key material for future semiconductor technologies such as logic-in-memory, neuromorphic computing, and negative capacitance FET, but it is facing difficulties in practical use due to its high coercive field and low domain wall velocity. Therefore, this study aims to understand and investigate the phenomenon related to the movement of domain walls under the electric field of HfO2-based ferroelectric materials at the atomic level through machine learning and molecular dynamics simulation.

Accelerated materials design of protonic ceramic electrolysis cell (PCEC) using first-principles calculation and machine learning

 Protonic ceramic electrolysis cell is a next-generation hydrogen production system that can be operated at low temperatures and generates pure hydrogen from the fuel electrode. High chemical stability and proton conductivity material design is required as air electrode and electrolyte materials for PCEC. Using first-principle calculations, the mechanisms of proton conduction and water splitting reactions are identified, and doping materials are explored. Based on the first principle calculation data, PCEC materials are optimized in a wide composition space through a material performance prediction machine learning model.

Discovery of organic cathode material for high performance organic Li-ion battery

 Inorganic cathode materials that are currently commercialized have environmental problems such as large amount of carbon emissions generated during the process and the use of expensive metals such as Co and Ni. Due to these problems, interest in organic-based batteries is increasing. However, in order to use organic-based cathode materials, low power, low energy density problems must be solved. Unlike inorganic materials, organic-based cathode materials have numerous possible combinations, so it is difficult to develop them through experiments. Therefore, we want to search for organic cathode materials with optimal performance through screening based on first-principle calculation and machine learning.

AI based supercritical materials research

 As global issues emerge, exploration and development of resources and energy in extreme environments such as space, deep sea, and polar regions are actively progressing. Supercritical materials that greatly exceed the physical properties of existing materials are indispensable for stable work. However, its slow development speed and high probability of failure are blocked the progressing. Therefore, in this project, 7 promising supercritical materials that are used in the future extreme environment were selected, and an AI platform that integrates material design/manufacturing, synthesis/analysis, and evaluation is built to develop those materials in a relatively short time.

Prediction of polymer properties using machine learning from the composition of various raw materials

 Various properties of copolymer generally come from their constituent units (monomer). Several factors including type of units, composition of units, manufacturing conditions can affect properties of copolymer. Traditionally, to achieve desired properties, trial-and-error experiment method have been used but the cost is high because a lot of samples to be prepared to test. In this project, to address the limitations, we predict properties of copolymer through the machine learning models. Experimental dataset comprised of over 350 features is used for training data. Based on the models, we aim to find out suitable materials and their optimized compositions for desired products.

  • Completed projects

Development of Novel Resistance Switching Materials by using First Principle-based Machine Learning Platform

 AIM-HS(Ab Initio calculation based Machine learning High-throughput Screening) platform is Ab initio calculation high-throughput screening system based on multi-dimensional machine learning analysis. This project is purposed to detect hidden correlation between calculated properties and make criterion based on big data of Ab initio calculation. The final goal is material designing based on needs for material property.

Development of machine learning model for predicting corrosion of high corrosion-resistant alloy plated steel

 Alloy plating is used to prevent corrosion of steel construction materials, but it has limited lifespan under harsh environments. Through a machine learning model developed from alloy plated steel corrosion images and experimental environment data, we predict lifespan of construction materials in real marine and soil environments.

  • Battery

Discovery of organic cathode material for high performance organic Li-ion battery

 Inorganic cathode materials that are currently commercialized have environmental problems such as large amount of carbon emissions generated during the process and the use of expensive metals such as Co and Ni. Due to these problems, interest in organic-based batteries is increasing. However, in order to use organic-based cathode materials, low power, low energy density problems must be solved. Unlike inorganic materials, organic-based cathode materials have numerous possible combinations, so it is difficult to develop them through experiments. Therefore, we want to search for organic cathode materials with optimal performance through screening based on first-principle calculation and machine learning.

  • Fuel cell

Accelerated materials design of protonic ceramic electrolysis cell (PCEC) using first-principles calculation and machine learning

 Protonic ceramic electrolysis cell is a next-generation hydrogen production system that can be operated at low temperatures and generates pure hydrogen from the fuel electrode. High chemical stability and proton conductivity material design is required as air electrode and electrolyte materials for PCEC. Using first-principle calculations, the mechanisms of proton conduction and water splitting reactions are identified, and doping materials are explored. Based on the first principle calculation data, PCEC materials are optimized in a wide composition space through a material performance prediction machine learning model.

Identification of Degradation Mechanisms in Ni-Based Cermet Cathodes in Solid Oxide Electrolysis Cells (SOECs) via First-Principles Calculations

 The Solid Oxide Electrolysis Cell (SOEC) is a promising technology for hydrogen production due to its use of a solid oxide electrolyte, which addresses compatibility and safety concerns typically associated with other systems. Operating at elevated temperatures, SOECs not only enhance hydrogen production efficiency but also provide thermal energy that can be leveraged for additional applications. Despite these advantages, SOEC stability remains a challenge, primarily due to the degradation of the Ni-based cermet cathode. High temperatures, steam concentrations, and applied voltages cause Ni within the cermet to aggregate and volatilize, yet the precise mechanisms underlying this degradation are not fully understood. To address this gap, first-principles calculations are employed to investigate the degradation processes in Ni cermet, with a focus on its surfaces and interfaces. This multi-scale analysis aims to elucidate various descriptors related to Ni cermet degradation, contributing valuable insights for the design of more stable Ni-based SOEC cathodes.

  • Completed

Identification of the mechanism of formation of Ni-rich NCM cathode material from Li raw materials

 The sintering process of Ni-rich NCM cathode takes a long time. To identify the mechanism process of formation of Ni-rich NCM cathode by using the first principle calculation at the atomic level. Then, to derive reducing process time or improving quality based on the identified mechanism process.

Dopants Effect on the Stability of Ni-rich Li Cathodes

 Ni-rich cathodes have been considered as promising cathode due to their high electrochemical capacities and low costs. However, the undesirable capacity fading hinders their development. We used first-principles calculations to understand physical origin of structural instability under low Li content and find dopants that can enhance stability.

Design and synthesis of novel Pb-free light-absorbers

 Designing and tuning the crystal structure of the energy bands using first-principles calculation. Non- perovskite structure of the series Pb-free synthetic photoactive material New photoactive material development from photoelectric conversion efficiency and degradation characteristic

Development and Characterization of oxygen transport membrane (OTM) materials

 Design new OTM(oxygen transport membrane) materials with high ionic and electronic conductivity. Understand the activation energy of oxygen ion diffusion inside OTM and the mechanism of redox reaction on OTM surface using first-principles calculation.

Development and Characterization of SOFC Component Materials

 The unit cell configuration of equilibrium physical factors and chemical properties and optimizing the stack components through an electrochemical analysis of water in the drive condition.

Synthesis of grain boundary-free metal ultrathin films and basic researches based on the metal films

 Investigating the mechanism of anisotropic growth and grain boundary coarsening, and synthesize grain boundary-free metal ultra thin films on large area. Investigating on the epitaxy growth mechanisms of two-dimensional materials, highly selective catalytic CO2 conversion reaction, and understanding on the lithium metal dendrite formation.

Developing new photocatalyst for efficient CO2 to fuel conversion

 Identifying the mechanism of CO2 to fuel conversion at various catalyst surfaces. Clarifying the role of different co-catalysts for CO2 conversion at different catalystic sites. Design new catalysts that can efficiently convert CO2 into different hydrocarbonic fuel speciesa

  • Memory

Assessing Additive Compositions for Glass Using MLP, MD, and DFT-based Simulations

 Amorphous silicon dioxide (SiO₂) is a fundamental oxide material with extensive scientific and commercial applications, attributed to its excellent thermal properties, dielectric characteristics, and optical transmission performance. To enhance the transparency of silica glass—the amorphous form of SiO₂—dopants such as germanium (Ge) or titanium (Ti) are often introduced to increase optical light transmission. Using ab initio molecular dynamics, potential datasets are generated on Ge- and Ti-doped amorphous SiO₂ to train machine learning potentials. These trained models enable the reproduction of amorphous structures with quantum-level accuracy. The dielectric constant, and consequently the refractive index, of the Ge/Ti-doped amorphous SiO₂ is then calculated to assess the system’s transmission coefficient.

Full-Cycle AI Technology for Developing Ferroelectrics toward In-Memory Computing

 In-memory computing (IMC) is a computing technology that performs data storage and computation within the system’s main memory, overcoming the von Neumann bottleneck. The IMC systems require superior memory devices with both scalable, non-volatile storage and low-power, high-endurance, high-speed computing properties. Ferroelectric RAM (FeRAM) is a promising device for IMC systems, which is non-volatile and low power operation, but its large cell-size and weak endurance are still in challenges. A full-cycle AI-based materials design integrates materials, process, microstructure, device, and circuit level properties through AI-driven generation, prediction, and optimization. Using an automated data crawling system based on natural language processing (NLP) with experimental validation process, this design system can rapidly predict optimal recipes for superior FeRAM devices, addressing the shortcomings in current IMC applications.

Understanding the domain walls movement of ferroelectric HfO2 with machine learning potential

 HfO2-based FeRAM has been spotlighted as a key material for future semiconductor technologies such as logic-in-memory, neuromorphic computing, and negative capacitance FET, but it is facing difficulties in practical use due to its high coercive field and low domain wall velocity. Therefore, this study aims to understand and investigate the phenomenon related to the movement of domain walls under the electric field of HfO2-based ferroelectric materials at the atomic level through machine learning and molecular dynamics simulation.

Engineering Schottky Barrier Stability of Ni/BaTiO₃ Interfaces

 Ni/BaTiO₃-based multilayer ceramic capacitors (MLCCs) are key components in modern electronics, but their reliability is often limited by Schottky barrier degradation at the metal–oxide interface. This degradation primarily originates from oxygen vacancy formation, which alters the interfacial electronic structure and leads to increased leakage. Alloying the Ni electrode with Sn has been reported to suppress such degradation, yet the fundamental mechanism by which Sn stabilizes the interface remains unclear. This project aims to elucidate the atomic-scale origin of Sn-induced Schottky barrier stabilization through first-principles calculations, focusing on interfacial bonding, charge redistribution, and defect energetics. Based on the clarified mechanism, we further explore alternative alloying elements that can provide enhanced interfacial stability beyond Sn, establishing new design principles for the development of reliable and durable MLCC electrode materials.

  • Completed

Discovery of wavelength hyper-selective on-demand zero-energy cooling materials

 Designing zero-energy cooling materials which reflect radiant energy at high temperatures and absorb radiant energy at low temperatures by adjusting optical properties, but have color or transparency. Designing these material  using high-throughput screening calculation and data mining algorithm.

Development of Novel Resistance Switching Materials by using First Principle-based Machine Learning Platform

 AIM-HS(Ab Initio calculation based Machine learning High-throughput Screening) platform is Ab initio calculation high-throughput screening system based on multi-dimensional machine learning analysis. This project is purposed to detect hidden correlation between calculated properties and make criterion based on big data of Ab initio calculation. The final goal is material designing based on needs for material property.

Understanding of the rapid growth of tungsten thin film on TiN adhesion layer for the semiconducting applications

 TiN is a well-known material used for the adhesion layer in the fabrication of semiconductors. However, the rapid growth of W on the TiN layer has been a mystery, as the underlying mechanism is not well-understood. To address this issue, we conducted an investigation using first-principles calculations to determine the growth mechanism of W on the TiN layer. Our research has revealed that W growth on the TiN layer is driven by a combination of the energetics of the system and surface tension, leading to a greater understanding of the growth process. Our findings provide valuable information for future research on this topic.

Development of transition metal oxides for electrolyte forming low voltage filament

 Compared to conventional flash memory, RRAM has advantages such as scalability, durability, and cost, so it is attracting attention as a next-generation memory. The performance of RRAM is greatly influenced by the filament behaviors in the electrolyte, and understanding of the filament behaviors is possible through first-principles calculations. In this project, we predict the behavior of the filaments through first-principles calculations of the change in the properties of defects constituting the filaments and propose an optimal material and composition.

Synthesis of wafer-scale single-grain Si2Te3 2D thin films and fabrication of high-performance atomic switches

 Using a new single crystal synthesis mechanism, Te is reacted on a silicon substrate to synthesize a wafer-scale single crystal Si2Te3 thin film. We intend to develop a highly integrated atomic switch device using no-transcription process that overcomes the difficulties of practical use of 2D thin film materials.To this end atomic switching mechanism and electrical properties and device stability of Si2Te3 thin film are investigated by the first principle calculations.

Understanding the resistance switching mechanism of single-element-based devices using first principle calculation

 Atom-based devices can exhibit memory, switch, and battery characteristics and depend on switching conditions. In addition, it is a clue to overcome various problems of IoT devices. In this project, through the calculation of the first principle, the mechanism for various properties of ions behaving in atom-based device will be identified, and based on this, a method for maximizing the performance of the device will be sought.

Discovery of ultralow operating voltage memristor materials using high-throughput calculations

 Finding out new composition molecular-motion ionic crystal by using high-throughput screening calculations.Selecting new composition material group for memristor by using high-throughput screening calculation

  • Supercritical meterials

AI based supercritical materials research

 As global issues emerge, exploration and development of resources and energy in extreme environments such as space, deep sea, and polar regions are actively progressing. Supercritical materials that greatly exceed the physical properties of existing materials are indispensable for stable work. However, its slow development speed and high probability of failure are blocked the progressing. Therefore, in this project, 7 promising supercritical materials that are used in the future extreme environment were selected, and an AI platform that integrates material design/manufacturing, synthesis/analysis, and evaluation is built to develop those materials in a relatively short time.

Superalloy research from database construction to property analysis

 Superalloys used in aircraft turbines operate under extreme environments, enduring both high rotational pressure and temperatures exceeding 1000°C. Therefore, their tensile and creep properties at elevated temperatures are of critical importance. However, experimental studies require substantial time and cost, and the existing data are often inconsistent. For this reason, the construction of a standardized database is essential for advancing research in this field. To address this challenge, this project aims to collect data from the literature and expand it through DFT calculations to build a comprehensive and consistent database. By analyzing this database, we identify physical parameters related to creep behavior and propose new superalloys with superior high-temperature mechanical performance.

  • Completed

Development of machine learning model for predicting corrosion of high corrosion-resistant alloy plated steel

 Alloy plating is used to prevent corrosion of steel construction materials, but it has limited lifespan under harsh environments. Through a machine learning model developed from alloy plated steel corrosion images and experimental environment data, we predict lifespan of construction materials in real marine and soil environments.

HEA-TRIP steel study with first-principle calculation

 HEAs are one of promising materials with almost infinite potential in numerous combinations. However, the numerous combinations is also bottleneck of advanced research. In this project, we will screen concentrations of systems with more than 5 elements using first-principle calculation with coherent potential approximation which can deal with positional and magnetical randomness.