Hyunsoo Park
KAIST Materials Science and Engineering · 재료과학
Hyunsoo Park 교수의 연구실은 인공지능 기반 소재 설계와 데이터 기반 소재 발견을 핵심으로 하며, 특히 금속-유기 프레임워크(MOFs)와 기타 다공성 소재의 합성 조건 최적화, 직접 공기 중 이산화탄소 포집용 소재 설계, 그리고 신규 소재의 자동 생성을 위한 기계학습 및 강화학습 기반 프레임워크를 개발하고 있습니다. 다량의 실험 데이터를 기반으로 한 규칙 기반 및 딥러닝 모델을 융합해 소재 개발의 효율성을 극대화하고 있으며, 다양한 다공성 소재(예: COFs, PPNs, 제올라이트)를 통합적으로 분석할 수 있는 다중모odal 기반의 대규모 소재 기반 모델링도 진행 중입니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Two new metal−organic framework compounds were synthesized under solvothermal conditions using Zn2+ ion, 1,2,4-triazole (TRZ), and 1,4- and 2,6-naphthalenedicarboxylic acids (NDC): Zn4(TRZ)4(1,4-NDC)2·2DMF·2H2O (1) and Zn4(TRZ)4(2,6-NDC)2·2DMF·4H2O (2). Their crystal structures were characterized by single-crystal X-ray diffraction. Structure 1 crystallizes in the P21/n space group with a = 13.609(2) Å, b = 27.181(5) Å, c = 13.617(3) Å, β = 92.46(1) °, V = 5032.4(16) Å3, and Z = 4. Structure 2 c
Three new metal−organic coordination polymers were synthesized hydrothermally using Zn2+ ion, 1,2,4-triazole, and 1,4-benzenedicarboxylic acid (BDC): Zn5(H2O)2(C2H2N3)4(C8H4O4)3·3.9H2O (1), Zn2(C2H2N3)2(C2H3N3)(C8H4O4)·2.5H2O (2), and Zn4(H2O)2(C2H2N3)4(C8H4O4)2·14H2O (3). Their crystal structures were determined by single-crystal X-ray diffraction. Their thermal properties were examined by thermogravimetric analysis. Structure 1 crystallizes in the monoclinic P21/n space group with a = 10.192(2
Identifying optimal synthesis conditions for metal-organic frameworks (MOFs) is a major challenge that can serve as a bottleneck for new materials discovery and development. A trial-and-error approach that relies on a chemist's intuition and knowledge has limitations in efficiency due to the large MOF synthesis space. To this end, 46,701 MOFs were data mined using our in-house developed code to extract their synthesis information from 28,565 MOF papers. The joint machine-learning/rule-based algo
A reinforcement learning framework enables the design and discovery of novel metal–organic frameworks (MOFs) for direct air capture of CO 2 (DAC) in terms of CO 2 heat of adsorption and CO 2 /H 2 O selectivity.
The directed design and discovery of compounds with pre-determined properties is a long-standing challenge in materials research. We provide a perspective on progress toward achieving this goal using generative models for chemical compositions and crystal structures based on a set of powerful statistical techniques drawn from the artificial intelligence community. We introduce the central concepts underpinning generative models of crystalline materials. Coverage is provided of early implementati
Four new coordination polymer compounds have been prepared using 3-amino-1,2,4-triazole (AmTRZ) as an organic linker, namely, ZnCl(AmTRZ) (1), Zn(HCO2)(AmTRZ) (2), Zn5(OH)2(AmTRZ)6(NO3)2·6H2O (3), and Zn5(OH)(AmTRZH)(AmTRZ)6(HCO2)3·5H2O (4). They were synthesized under mild hydro- or solvothermal conditions using water or dimethylformamide as solvent. Their crystal structures were characterized by single-crystal X-ray diffraction techniques, and thermal properties of all compounds were examined
These findings suggest that rubiarbonone C inhibits the proliferation and migration of VSMCs by inhibiting the FAK, MAPK and STAT3 signalling pathways. Therefore, rubiarbonone C could be a good candidate for the treatment of cardiovascular disease.
Two new Zn-based coordination polymers based polymers, namely, Zn7(TRZ)8(SIP)2·7H2O (1) and Zn5Na2(DMA)4(TRZ)4(SIP)4·5H2O (2) (TRZ = 1,2,4-triazole, SIP = sulfoisophthalate, and DMA = dimethylamine), were synthesized under mild solvothermal conditions. Their crystal structures were characterized by single-crystal X-ray diffraction, and their thermal properties were examined by thermogravimetric analysis. Structure 1 crystallizes in monoclinic P21/n space group (a = 14.050(3) Å, b = 12.517(3) Å,
Two new isostructural scandium and indium phosphate frameworks, (C6H14N2)M4F2(PO4)4·4H2O (M = Sc, In), have been synthesized from hydrothermal conditions using an organic amine, 1,4-diazabicyclo[2.2.2]octane (DABCO), as a template. Their structures have been determined by single-crystal X-ray diffraction and supported by solid-state magic-angle spinning (MAS) NMR spectroscopy. They crystallize in the P21/n space group with a = 10.283(2) Å, b = 12.698(2) Å, c = 17.864(3) Å, and β = 102.761(3)° an
Porous materials have emerged as promising solutions for a wide range of energy and environmental applications. However, the asymmetric development in the field of metal-organic frameworks (MOFs) has led to a data imbalance when it comes to MOFs versus other porous materials such as covalent organic frameworks (COFs), porous polymer networks (PPNs), and zeolites. To address this issue, we introduce PMTransformer (Porous Material Transformer), a multimodal Transformer model pretrained on a vast d
