International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Volume XLII-3/W10
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W10, 403–409, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W10-403-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W10, 403–409, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W10-403-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  07 Feb 2020

07 Feb 2020

MAPPING URBAN AREAS USING DENSE TIME SERIES OF LANDSAT IMAGES AND GOOGLE EARTH ENGINE

D. C. Pu, J. Y. Sun, Q. Ding, Q. Zheng, T. T. Li, and X. F. Niu D. C. Pu et al.
  • College of Geo-exploration Science and Technology, Jilin University, 130026 Changchun, China

Keywords: Time Series Images, Landsat, Multidimensional Arrays, Supervised Classification, Google Earth Engine

Abstract. Urban information extraction from satellite based remote sensing data could provide the basic scientific decision-making data for the construction and management of future cities. In particular, long-term satellite based remote sensing such as Landsat observations provides a rich source of data for urban area mapping. Urban area mapping based on the single-temporal Landsat observations is vulnerable to data quality (such as cloud coverage and stripe), and it is difficult to extract urban areas accurately. The composite of dense time series Landsat observations can significantly reduce the effect of data quality on urban area mapping. Multidimensional array is currently effective theory for geographic big data analysis and management, providing a theoretical basis for the composite of dense time series Landsat observations. Google Earth Engine (GEE) not only provides rich satellite based remote sensing data for the composite of dense time series data, but also has powerful massive data analysis capabilities. In the study, we chose Random Forest (RF) algorithm for the urban area extraction owing to its stable performance, high classification accuracy and feature importance evaluation. In this work, the study area is located in the central part of the city of Beijing, China. Our main data source is all Landsat8 OLI images in Beijing (path/row: 123/32) in 2017.Based on the multidimensional array for geographic big data theory and the GEE cloud computing platform, four commonly used reducer methods are selected to composite the annual dense time series Landsat 8 OLI data. After collecting the training samples, RF algorithm was selected for supervised classification, feature importance evaluation and accuracy verification for urban area mapping. The results showed that 1), compared with the single temporal image of Landsat 8 OLI, the quality of annual composite image was improved obviously, especially for urban extraction in cloudy areas; 2) for the evaluation results of feature importance based on RF algorithm, Coastal, Blue, NIR, SWIR1 and SWIR2 bands were the more important characteristic bands, while the Green and Red bands were comparatively less important; 3) the annual composite images obtained by the ee.Reducer.min, ee.Reducer.max, ee.Reducer.mean and ee.Reducer.median methods were classified and accuracy verification was carried out using the verification points. The overall accuracy of the urban area mapping reached 0.805, 0.820, 0.868 and 0.929, respectively. In summary, the ee.Reducer.median method is a suitable method for annual dense time series Landsat image composite, which could improve the data quality, and ensure the difference of features and the higher accuracy of urban area mapping.