Kei Shiomi
Papers
2
Total Citations
71
H-Index
2
About
Kei Shiomi is a leading figure in satellite-based remote sensing of atmospheric aerosols, with a primary focus on advancing algorithms for the Greenhouse gases Observing SATellite (GOSAT) series. His key research areas include aerosol optical property retrieval, radiative transfer modeling, and the application of machine learning to satellite data. Shiomi’s most significant contribution is the development of a fast and flexible artificial neural network radiative transfer scheme, which enabled the first successful retrieval of aerosol optical properties over water from the GOSAT-2/CAI-2 sensor. This work, published in 2020 and garnering 66 citations, represents a major step forward in overcoming the computational bottlenecks of traditional radiative transfer models. Earlier, he pioneered an aerosol retrieval algorithm for the TANSO-CAI instrument on the original GOSAT, specifically tailored for the complex aerosol environment of Northeast Asia. This foundational work directly addressed the critical challenge of aerosol interference in carbon dioxide measurements, improving data coverage and reducing retrieval uncertainties. Through his innovative combination of neural networks and satellite remote sensing, Shiomi has significantly enhanced our ability to monitor atmospheric composition and its impacts on climate.
Research Focus
Key Achievements
Top Papers
- 1
- 2