Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data
Sensors · 29.02.2024 · 24 (5) · 1587
DOI: 10.3390/s24051587 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.02.2024. Verfasst von Kristofer Lasko und 2 weiteren Autor:innen. Beteiligte Einrichtung: Geospatial Research Laboratory, Engineer Research and Development Center, 7701 Telegraph Road, Bldg 2592, Alexandria, VA 22315, USA. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 112 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Army Engineer Research and Development Center, U.S. Army Corps of Engineers, Engineer Research and Development Center (ERDC).
Abstract (Originalsprache)
A near-global framework for automated training data generation and land cover classification using shallow machine learning with low-density time series imagery does not exist. This study presents a methodology to map nine-class, six-class, and five-class land cover using two dates (winter and non-winter) of a Sentinel-2 granule across seven international sites. The approach uses a series of spectral, textural, and distance decision functions combined with modified ancillary layers (such as global impervious surface and global tree cover) to create binary masks from which to generate a balanced set of training data applied to a random forest classifier. For the land cover masks, stepwise threshold adjustments were applied to reflectance, spectral index values, and Euclidean distance layers, with 62 combinations evaluated. Global (all seven scenes) and regional (arid, tropics, and temperate) adaptive thresholds were computed. An annual 95th and 5th percentile NDVI composite was used to provide temporal corrections to the decision functions, and these corrections were compared against the original model. The accuracy assessment found that the regional adaptive thresholds for both the two-date land cover and the temporally corrected land cover could accurately map land cover type within nine-class (68.4% vs. 73.1%), six-class (79.8% vs. 82.8%), and five-class (80.1% vs. 85.1%) schemes. Lastly, the five-class and six-class models were compared with a manually labeled deep learning model (Esri), where they performed with similar accuracies (five classes: Esri 80.0 ± 3.4%, region corrected 85.1 ± 2.9%). The results highlight not only performance in line with an intensive deep learning approach, but also that reasonably accurate models can be created without a full annual time series of imagery.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Geospatial Research Laboratory, Engineer Research and Development Center, 7701 Telegraph Road, Bldg 2592, Alexandria, VA 22315, USA.
ORCID-Profile: Kristofer Lasko
Förderung
- U.S. Army Engineer Research and Development Center
- U.S. Army Corps of Engineers, Engineer Research and Development Center (ERDC)
Zitieren
APA
Lasko, K., O'Neill, F. D., & Sava, E. (2024). Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data. Sensors, 24(5), 1587. https://doi.org/10.3390/s24051587
Vancouver
Lasko K, O'Neill FD, Sava E. Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data. Sensors. 2024;24(5):1587. doi:10.3390/s24051587
BibTeX
@article{Lasko2024,
author = {Lasko, Kristofer and O'Neill, Francis D and Sava, Elena},
title = {Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data},
journal = {Sensors},
year = {2024},
volume = {24},
number = {5},
pages = {1587},
doi = {10.3390/s24051587}
}
EUVIMED