Rapid land cover classification using a 36-year time series of multi-source remote sensing data

Research output: Contribution to journalArticlepeer-review

Electronic versions

Documents

DOI

  • Xingguang Yan
    China University of Mining and Technology-Beijing
  • Jing Li
    China University of Mining and Technology-Beijing
  • Andy Smith
  • Di Yang
    University of Wyoming
  • Tianyue Ma
    China University of Mining and Technology-Beijing
  • Yiting Su
    China University of Mining and Technology-Beijing
Long-time series land cover classification information is the basis for scientific research on urban sprawl, vegetation change, and the carbon cycle. The rapid development of cloud computing platforms such as the Google Earth Engine (GEE) and access to multi-source satellite imagery from Landsat and Sentinel-2 enables the application of machine learning algorithms for image classification. Here, we used the Random Forest algorithm to quickly achieve a time series land cover classification at different scales based on the fixed land classification sample points selected from images acquired in 2022, and the year-by-year spectral differences of sample points. The classification accuracy was enhanced by using multi-source remote sensing data, such as synthetic aperture radar (SAR) and digital elevation model (DEM) data. The results showed that: (i) the maximum difference (threshold) of sample points without land class change determined by counting the sample points of each band of landsat time series from 1986 to 2022 was 0.25; (ii) the kappa coefficient and observed accuracy of the same sensor from Landsat 8 are higher than the results of TM and ETM+ sensor data from 2013 to 2022; (iii) the addition of a mining land cover type increase the kappa coefficient and overall accuracy mean values of the Sentinel 2 image classification for a complex mining and -forest area. Among the land classifications by multi-source remote sensing, the combined variables spectral band + index + topography + SAR result in the highest accuracy, but the overall improvement is limited. The method proposed is applicable to remotely sensed images at different scales and using sensors under complex terrain conditions. The use of GEE cloud computing platform enabled rapid analysis of remotely sensed data to produce land cover maps with high-accuracy and a long time series.

Keywords

  • Google Earth Engine, Sample migration, Land classification, multi-source remote sensing, spontaneous forest, machine learning, AI earth
Original languageEnglish
Article number2149
JournalLand
Volume12
Issue number12
Early online date11 Dec 2023
DOIs
Publication statusPublished - Dec 2023

Total downloads

No data available
View graph of relations