Journal of Korean Society for Atmospheric Environment
5 papers6 directions
The Journal of Korean Society for Atmospheric Environment is a scientific publication primarily focused on environmental science, air quality, and atmospheric monitoring. While its core scope involves the study of pollutants and sampling methodologies, the venue has served as a platform for research that applies machine learning and artificial intelligence to environmental data. Between 2003 and 2018, the journal featured work that integrated computational techniques with atmospheric observations, such as using Temporal Segment Networks (TSN) for rainfall recognition from road surveillance videos.
In the context of machine learning, the venue has addressed research directions including the automated scaling of video language datasets, overcoming video annotation bottlenecks, and maintaining physical consistency in video world models. These contributions often focus on temporal localization and the statistical analysis of indoor air pollutants. By publishing studies that utilize deep learning and advanced statistical modeling, the journal facilitates the development of automated systems for monitoring environmental conditions and reducing uncertainties in air sampling.
Prolific authors associated with these interdisciplinary efforts include Ho-Jin Choi, Jonghwan Hyeon, Zhun Li, and Dong-Won Jung. Their work at this venue bridges the gap between traditional environmental science—such as CO2 capture and genotoxicity assessments—and modern AI applications. This intersection allows for the exploration of how computer vision and automated data processing can enhance the evaluation of indoor air quality and the recognition of weather patterns through existing infrastructure.
Papers by Year
| 2018 | 1 |
| 2016 | 1 |
| 2014 | 1 |
| 2003 | 2 |
Top Research Directions
Research directions most represented by papers from this venue.
Top Authors
| Author | Papers |
|---|---|
| Ho-Jin Choi | 1 |