# SAIL: Spectroscopy and AI Lab (Joonyoung F. Joung Lab, Kookmin University)

> SAIL, the Spectroscopy and AI Lab at Kookmin University led by Joonyoung F. Joung: machine learning for molecular properties, reactions, design, and databases.

The Spectroscopy and AI Lab (SAIL), led by Joonyoung F. Joung (정준영), Assistant Professor in the Department of Chemistry at Kookmin University, integrates machine learning with chemistry. Website: https://sail.kookmin.ac.kr

Other names: Joonyoung F. Joung Lab; 인공지능화학연구실. Kookmin University in Korean: 국민대학교. GitHub: https://github.com/sailgroup

In Korean, in the lab's own words: 국민대학교 화학부 SAIL 연구실(Spectroscopy and AI Lab)은 인공지능과 화학을 융합하여 화학 반응 예측과 신소재 개발을 연구합니다.

Principal investigator: Joonyoung F. Joung (정준영), Assistant Professor, Department of Chemistry, Kookmin University. Google Scholar: https://scholar.google.com/citations?user=0uuwTRQAAAAJ · ORCID: https://orcid.org/0000-0002-5976-2048

Research areas:
- Prediction of Physicochemical Properties: We leverage machine learning models and quantum chemical calculations (e.g., DFT) to predict critical physicochemical properties of molecules, such as optical properties, energy levels, and solubility. These predictions not only aid in discovering desired materials or pharmaceuticals but also support the optimization of separation processes by providing insights into solubility behavior.
- Chemical Reaction Prediction: Chemical reaction prediction has traditionally relied on expert knowledge and reaction rules, making it difficult to anticipate unexpected byproducts or impurities. We develop models that predict products either in an end-to-end manner or by learning mechanistic pathways. This helps to explain impurity formation and ultimately discover novel reactions.
- De Novo Molecular Design: Traditional approaches to molecular design rely heavily on trial-and-error experimentation, even when the desired properties are known. At SAIL, we develop machine learning-based de novo design techniques that generate candidate molecules expected to exhibit target properties. This accelerates material discovery while reducing cost and effort. In addition to generative modeling, we leverage quantum chemical methods such as DFT to understand how molecular structure determines properties. This allows us to extract design principles grounded in theory and propose new molecular structures with improved performance.
- Database Development: Reliable AI models require high-quality data. We build structured databases by extracting information from experiments and literature, and use these data for training and benchmarking models.

## Key pages
- [Research](https://sail.kookmin.ac.kr/research/): the lab's research directions, each with a figure from the lab's own papers.
- [Publications](https://sail.kookmin.ac.kr/publications/): 47 papers; each has a detail page at https://sail.kookmin.ac.kr/publications/<id>/ with its citation, and its abstract and DOI where it has them.
- [Members](https://sail.kookmin.ac.kr/members/) and [Alumni](https://sail.kookmin.ac.kr/alumni/): lab people, each with a page at https://sail.kookmin.ac.kr/people/<slug>/.
- [Principal Investigator](https://sail.kookmin.ac.kr/pi/): Joonyoung F. Joung.
- [News](https://sail.kookmin.ac.kr/news/): lab updates and milestones.
- [Positions](https://sail.kookmin.ac.kr/positions/): how to join the lab and how to apply (postdoctoral researcher, graduate student, and undergraduate research), including currently advertised undergraduate projects. Written in Korean.

## Selected recent publications
- [Encoding Composition-Dependent Intermolecular Interactions into Learned Molecular Representations](https://sail.kookmin.ac.kr/publications/47/): Chem. Eng. J., accepted (2026).
- [Wavenumber-Aware Deep Learning for Robust Analysis of Raman Spectra](https://sail.kookmin.ac.kr/publications/46/): Submitted (2026). Preprint: https://doi.org/10.48550/arXiv.2610.30746
- [Synergistic Ligand and Composition Control for Bright and Stable CsPbBr3/Cs4PbBr6 Core/Shell Colloidal Perovskite Nanocrystals](https://sail.kookmin.ac.kr/publications/45/): J. Alloys Compd. (2026). https://doi.org/10.1016/j.jallcom.2026.190954
- [Prediction of experimental excited-state absorption spectra by using vibronic transition calculations: Its practical application to a π-conjugated molecule](https://sail.kookmin.ac.kr/publications/44/): Bull. Korean Chem. Soc. (2026). https://doi.org/10.1002/bkcs.70213
- [Continuous Light-Driven Pure CO2 Production by Regenerative Non-Aqueous Amine–Photoacid Cycling](https://sail.kookmin.ac.kr/publications/43/): ChemRxiv, Preprint (2026). Preprint: https://doi.org/10.26434/chemrxiv.15005144/v1
- [Precursor Diffusion-Controlled Scalable Synthesis of Monodisperse Iodide Perovskite Quantum Dots for Photovoltaics](https://sail.kookmin.ac.kr/publications/42/): ACS Energy Lett. (2026). https://doi.org/10.1021/acsenergylett.6c01560
- [An overview of reaction outcome prediction with physics-based and data-driven methods](https://sail.kookmin.ac.kr/publications/41/): Chem. Soc. Rev. (2026). https://doi.org/10.1039/D6CS00079G
- [Defining Chemical Problems for Artificial Intelligence Models](https://sail.kookmin.ac.kr/publications/40/): Bull. Korean Chem. Soc. (2026). https://doi.org/10.1002/bkcs.70113
- [Higher-level Strategies for Computer-Aided Retrosynthesis](https://sail.kookmin.ac.kr/publications/39/): ACS Cent. Sci. (2026). https://doi.org/10.1021/acscentsci.5c02014
- [Exploring Materials Data through Collaboration: 2024 KRICT ChemDX Hackathon](https://sail.kookmin.ac.kr/publications/38/): J. Mater. Inf. (2025). https://doi.org/10.20517/jmi.2025.65

## Optional
- [Full text](https://sail.kookmin.ac.kr/llms-full.txt): research, every publication with its abstract where it has one, people, the principal investigator's background, and news.