Yue Yang

Dr. Yue Yang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 September 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YYYue Yang
Yue Yang
JCJan Cermak
Jan Cermak
KYKangzhuo Yang
Kangzhuo Yang
EPEva Pauli
Eva Pauli
YCYunping Chen
Yunping Chen
Atmospheric aerosols can impact human health, necessitating the understanding of their distribution determinants, especially in urban areas. The study discusses the relationships between five major land cover types and aerosol optical depth (AOD) within a city combining the high-resolution satellite-derived AOD products (derived from Sentinel-2) and land cover products (60 m and 100 m, respectively) for Beijing and its surroundings from 2017 to 2019. Contribution analysis is performed to quantitatively evaluate the influences of land cover on regional AOD over the study area. Patterns of aerosol distribution remarkably vary in time and space. Statistics of seasonal average AOD peak in spring and then progressively decline from summer through autumn to winter. High AOD values coincide with a low normalized difference vegetation index (NDVI) and a high normalized difference built-up index (NDBI). Urban and built-up land is a major contributor to regional AOD in the study area, especially in spring; forest and grassland always reduce AOD. Anthropogenic activities have a non-negligible influence on AOD and can even reverse the contribution of a land cover type to aerosols. Insights of the study promote the comprehension of the impacts of land cover on aerosols and air pollution and contribute to the planning of land use within a city.

8 March 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YYYue Yang
Yue Yang
KYKangzhuo Yang
Kangzhuo Yang
YCYunping Chen
Yunping Chen
High-resolution aerosol retrieval is of great significance for understanding the impact of aerosols on air pollution and climate change. In this study, an algorithm for aerosol retrieval at a spatial resolution of 60 m over complex urban areas is developed using Sentinel-2 images. The proposed algorithm has two assumptions: 1) the blue–red surface reflectance ratio does not change temporally in a single season; and 2) surface reflectance over bright areas is invariant over three months. Then, aerosol optical depth (AOD) is retrieved from the surface reflectance correlations with a combination of temporal signatures over the vegetated areas and bright areas. Aerosol Robotic Network (AERONET) measurements in Beijing and its surrounding from 2017 to 2019 are collected and used to validate the retrieved 60 m Sentinel-2 AODs. Seventy-seven percent of the retrieved Sentinel-2 AODs fall within the expected error (EE), and the correlation coefficient is of 0.927. MODerate resolution Imaging Spectrometer (MODIS) AOD products at 1 and 10 km resolutions (MCD19A2 and MOD04_L2, respectively) are acquired to compare with the retrieved Sentinel-2 AODs. Comparison results show that the retrieved Sentinel-2 AODs are superior to the MOD04_L2 dark target (DT) and MCD19A2 AODs and slightly better than the MOD04_L2 deep blue (DB) and DT and DB combined (DTBC) AODs. The validation and comparison results indicate that the proposed algorithm is able to describe aerosol distributions at high resolution continuously. However, further work is needed to apply the proposed algorithm on global scale.

8 July 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YYYue Yang
Yue Yang
JCJan Cermak
Jan Cermak
XCXu Chen
Xu Chen
YCYunping Chen
Yunping Chen
XHXi Hou
Xi Hou
Characterizing the spatial distribution of particles smaller than 10 μm (PM10) is of great importance for air quality management yet is very challenging because of the sparseness of air quality monitoring stations. In this study, we use a model-agnostic meta-learning-trained artificial neural network (MAML-ANN) to estimate the concentrations of PM10 at 60 m × 60 m spatial resolution by combining satellite-derived aerosol optical depth (AOD) with meteorological data. The network is designed to regress from the predictors at a specific time to the ground-level PM10 concentration. We utilize the ANN model to capture the time-specific nonlinearity among aerosols, meteorological conditions, and PM10, and apply MAML to enable the model to learn the nonlinearity across time from only a small number of data samples. MAML is also employed to transfer the knowledge learned from coarse spatial resolution to high spatial resolution. The MAML-ANN model is shown to accurately estimate high-resolution PM10 in Beijing, with coefficient of determination of 0.75. MAML improves the PM10 estimation performance of the ANN model compared with the baseline using pre-trained initial weights. Thus, MAML-ANN has the potential to estimate particulate matter estimation at high spatial resolution over other data-sparse, heavily polluted, and small regions.

5 October 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YCYunping Chen
Yunping Chen
YYYue Yang
Yue Yang
YXYaju Xiong
Yaju Xiong
YSYuan Sun
Yuan Sun
Retrieving aerosol optical thickness (AOT) from remote sensing images of urban areas remains challenging, especially for bright-reflecting land surfaces. In this study, a novel algorithm, called multi-spectrum hierarchical segmentation (MSHS), was developed to retrieve the AOTs for urban surfaces. In this algorithm, the apparent reflectance of multiple shortwave infrared (SWIR) bands were employed and divided into tiny segments successively and hierarchically. Each segment was further segmented into object and non-object parts using the Otsu algorithm in the coastal band. Hereafter, the congeneric apparent reflectance pixels of the object part were extracted, and the surface reflectance of this congener was obtained based on the minimum reflectivity and 6S model. AOT was then retrieved based on a precalculated look-up table (LUT) using the coastal band. Aerosol Robotic Network (AERONET) sun/sky radiometer measurements from 2013 to 2019 from Beijing, China, were used for validation. Results showed that the 30 m AOT retrievals obtained using Landsat-8 images exhibited good consistency with the ground-based measurements, with an overall correlation coefficient of ~ 0.871, expected error of ~ 59.04%, root mean square error of ~ 0.148, and mean absolute error of ~ 0.096. Compared to dense dark vegetation algorithm, MSHS algorithm exhibited higher correlation and lower error. This implied that this new algorithm can help in characterizing aerosol distribution patterns within a city in a more refined way and provide support for tracing air pollution sources.