Su-Chul Yoon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Su-Chul Yoon has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Chae-Ho Kim
Convergence Engineering Department of Smart City and Construction, Daejin University, Pocheon-si 11159, Republic of Korea
1 shared publication - Dong-Chul Shin
Department of Smart Construction and Environmental Engineering, Daejin University, Pocheon-si 11159, Republic of Korea
1 shared publication - Hyeon-Jun Cho
Department of Environmental and Energy Engineering Anyang University Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 23 December 2025
- Published by MDPI AG in Atmosphere
- Vol. 17 (1) , 18
Clustering as a Prerequisite for Reliable Machine Learning Prediction of Multi-Odor Systems in Wastewater Treatment
Complex odor emissions from wastewater treatment plants consist of multiple volatile compounds that exhibit heterogeneous temporal dynamics and low linear correlations, making accurate prediction and interpretation difficult when analyzed on a single-compound basis. This study investigates whether clustering can serve not only as an exploratory tool but as an essential preprocessing step to enhance machine-learning performance in multi-odor prediction systems. A total of 22 designated odorants were continuously monitored, and their pairwise dependencies were evaluated using Pearson correlation and mutual information. Data-driven clustering was performed through K-means, hierarchical linkage, and principal-component–based latent grouping, and the resulting structures were quantitatively compared with functional-group-based chemical classifications using the consistency ratio and Jaccard similarity index. Cluster validity was further examined using the Silhouette Coefficient, Davies–Bouldin Index, and Calinski–Harabasz Index. The predictive contribution of clustering was verified by training XGBoost regression models on both raw and cluster-structured datasets. The clustered dataset yielded higher predictive accuracy, with increased R2 and reduced MAE and RMSE across most odorants. SHAP analysis further confirmed that clustering improved model interpretability by stabilizing feature contributions and reducing noise-driven importance shifts. The findings demonstrate that clustering is not a supplementary diagnostic tool, but a prerequisite for building reliable, high-performance machine-learning models in complex odor systems. This integrative framework offers a methodological foundation for multi-odor forecasting, source tracking, and next-generation odor management platforms.
- 23 December 2025
- Published by MDPI AG in Atmosphere
- Vol. 17 (1) , 18
Open AccessClustering as a Prerequisite for Reliable Machine Learning Prediction of Multi-Odor Systems in Wastewater Treatment
Complex odor emissions from wastewater treatment plants consist of multiple volatile compounds that exhibit heterogeneous temporal dynamics and low linear correlations, making accurate prediction and interpretation difficult when analyzed on a single-compound basis. This study investigates whether clustering can serve not only as an exploratory tool but as an essential preprocessing step to enhance machine-learning performance in multi-odor prediction systems. A total of 22 designated odorants were continuously monitored, and their pairwise dependencies were evaluated using Pearson correlation and mutual information. Data-driven clustering was performed through K-means, hierarchical linkage, and principal-component–based latent grouping, and the resulting structures were quantitatively compared with functional-group-based chemical classifications using the consistency ratio and Jaccard similarity index. Cluster validity was further examined using the Silhouette Coefficient, Davies–Bouldin Index, and Calinski–Harabasz Index. The predictive contribution of clustering was verified by training XGBoost regression models on both raw and cluster-structured datasets. The clustered dataset yielded higher predictive accuracy, with increased R2 and reduced MAE and RMSE across most odorants. SHAP analysis further confirmed that clustering improved model interpretability by stabilizing feature contributions and reducing noise-driven importance shifts. The findings demonstrate that clustering is not a supplementary diagnostic tool, but a prerequisite for building reliable, high-performance machine-learning models in complex odor systems. This integrative framework offers a methodological foundation for multi-odor forecasting, source tracking, and next-generation odor management platforms.
- Open Access
- 1 March 2024
- Published by Korean Society of Environmental Engineering in Journal of Korean Society of Environmental Engineers
- Vol. 46 (3) , 73-80
Occurrence of Designated Odor Substances in Wastewater Treatment Plant and Industrial Estate
Objectives : Odor emissions pose a challenge due to the diversity of odor-producing substances, their various sources, and the complex interactions between different compounds. Moreover, people's perception of odor intensity can vary based on their living environment and psychological state, making it difficult to effectively manage and develop mitigation measures for odors, in contrast to other air pollutants. To address this issue, this study focuses on two prominent sources of residential odors, namely wastewater treatment plant and industrial estate.Methods : Through on-site data collection, the study aims to investigate the characteristics of odor emissions and analyze seasonal trends in odor generation. Ultimately, the study seeks to assess the substances contributing to odors in wastewater treatment plant and industrial estate through odor contribution analysis.Results and Discussion : The research findings reveal that wastewater treatment plants predominantly emit high concentrations of fatty acid substances such as Propionic acid, iso-Valeric acid, and n-Valeric acid. In contrast, industrial estates release a variety of odor-causing substances, including Toluene, Xylene, Butyraldehyde, Trimethylamine, and iso-Valeraldehyde.Conclusion Significant differences are observed both in terms of odor concentration and odor contribution. These disparities are attributed to the specific characteristics of wastewater treatment plants and industrial processes that induce odors. Nevertheless, in both types of facilities, Trimethylamine is identified as a major contributor to odors.
- 1 March 2024
- Published by Korean Society of Environmental Engineering in Journal of Korean Society of Environmental Engineers
- Vol. 46 (3) , 73-80
Open AccessOccurrence of Designated Odor Substances in Wastewater Treatment Plant and Industrial Estate
Objectives : Odor emissions pose a challenge due to the diversity of odor-producing substances, their various sources, and the complex interactions between different compounds. Moreover, people's perception of odor intensity can vary based on their living environment and psychological state, making it difficult to effectively manage and develop mitigation measures for odors, in contrast to other air pollutants. To address this issue, this study focuses on two prominent sources of residential odors, namely wastewater treatment plant and industrial estate.Methods : Through on-site data collection, the study aims to investigate the characteristics of odor emissions and analyze seasonal trends in odor generation. Ultimately, the study seeks to assess the substances contributing to odors in wastewater treatment plant and industrial estate through odor contribution analysis.Results and Discussion : The research findings reveal that wastewater treatment plants predominantly emit high concentrations of fatty acid substances such as Propionic acid, iso-Valeric acid, and n-Valeric acid. In contrast, industrial estates release a variety of odor-causing substances, including Toluene, Xylene, Butyraldehyde, Trimethylamine, and iso-Valeraldehyde.Conclusion Significant differences are observed both in terms of odor concentration and odor contribution. These disparities are attributed to the specific characteristics of wastewater treatment plants and industrial processes that induce odors. Nevertheless, in both types of facilities, Trimethylamine is identified as a major contributor to odors.