Dr. Maosi Chen Profile

Dr. Maosi Chen

at USDA UV-B Monitoring and Research Program

SPIE Involvement:

Author

Publications (52)

Proceedings Article | 3 October 2022 Presentation

Study the wildfire impacts on surface UV irradiance by ground measurement

Joey Paulson, Zhibin Sun, Maosi Chen, Wei Gao

Proceedings Volume 12233, 122330L (2022) https://doi.org/10.1117/12.2633516

KEYWORDS: Ultraviolet radiation, Aerosols, Solar radiation, Scattering, Earth's atmosphere, Combustion, Atmospheric particles

Read Abstract +

Proceedings Article | 6 September 2019 Paper

Reconstruct missing pixels of Landsat land surface temperature product using a CNN with partial convolution

Maosi Chen, Benjamin Newell, Zhibin Sun, Chelsea Corr, Wei Gao

Proceedings Volume 11139, 111390E (2019) https://doi.org/10.1117/12.2529462

KEYWORDS: Convolutional neural networks, Clouds, Earth observing sensors, Landsat, Computer programming, Satellite imaging, Data modeling, Agriculture

Read Abstract +

Proceedings Article | 27 September 2018 Paper

Spatial interpolation of surface ozone observations using deep learning

Maosi Chen, Zhibin Sun, John Davis, Chaoshun Liu, Wei Gao

Proceedings Volume 10767, 107670C (2018) https://doi.org/10.1117/12.2320755

KEYWORDS: Neural networks, Optical filters, Convolution, Convolutional neural networks, Process modeling, Error analysis, Matrices

Read Abstract +

Surface ozone can trigger many health problems for human (e.g. coughing, bronchitis, emphysema, and asthma), especially for children and the elderly. It also has harmful effects on plants (e.g. chlorosis, necrosis, and yield reduction). The United State (U.S.) Environmental Protection Agency (EPA) has been monitoring surface ozone concentrations across the U.S. since 1980s. However, their stations are sparsely distributed and mainly in urban areas. Evaluation of surface ozone effects at any given locations in the U.S. requires spatial interpolation of ozone observations. In this study, we implemented two traditional spatial interpolation methods (i.e. triangulation-based linear interpolation and geostatistics-based method). One limitation of these two methods is their reliance on single-scene observations in constructing the spatial relationship, which is prone to influence of noisy observations and has large uncertainty. Deep learning, on the other hand, is capable of simulating common patterns (including complex spatial patterns) from a large amount of training samples. Therefore, we also implemented three deep learning algorithms for the spatial interpolation problem: mixture model network (MoNet), Convolutional Neural Network for Graphs (ChebNet), and Recurrent Neural Network (RNN). The training and validation data of this study are the 2016 EPA hourly surface ozone observations within ±3-degree box centered at the Billings, Oklahoma station (USDA UV-B Monitoring and Research Program). The results showed that among the five methods, RNN and MoNet outperformed the two traditional spatial interpolation methods and RNN has the lowest validation error (mean absolute error: 2.82 ppb; standard deviation: 2.76 ppb). Finally, we used the integrated gradients method to analyze the attribution of RNN inputs on the surface ozone prediction. The results showed that surface ozone observation is the most important input feature followed by distance and absolute locations (i.e. elevations, longitudes, and latitudes).