eprintid: 4349
rev_number: 9
eprint_status: archive
userid: 421
dir: disk0/00/00/43/49
datestamp: 2020-12-31 01:54:55
lastmod: 2020-12-31 01:54:55
status_changed: 2020-12-31 01:54:55
type: conference_item
metadata_visibility: show
creators_name: Bui, Ba Nam
creators_name: Phan, Anh
creators_name: Nguyen, Thi Nhat Thanh
creators_id: nambb@fimo.edu.vn
creators_id: anhp@fimo.edu.vn
creators_id: thanhntn@vnu.edu.vn
title: Land-Cover Mapping from Sentinel Time-Series Imagery on the Google Earth Engine: A Case Study for Hanoi
ispublished: pub
subjects: IT
divisions: FIMO
abstract: Over the past decade, satellite image processing is an overwhelming bulk of work. Recently, with rapid development in information technology, Google released Google Earth Engine (GEE), which is a powerful cloud computing platform, to help to improve the performance of geospatial big data archives and processing. In this study, we deployed a machine learning model to evaluate the capability of time series Sentinel imagery (Sentinel 2 A/B and Sentinel 1A) in landcover mapping for Hanoi in 2019. First, we evaluated several traditional machine learning models, as a result, XGBoost classifier stands
out as the best model with 86% overall accuracy (OA). As Hanoi is a frequent cloud-covered area, the combination of optical data and radar data helps to improve the quality of the landcover map in 2019. The use of GEE has made it easier and faster through the provided JavaScript API when ensuring high accuracy.
date_type: published
full_text_status: public
pres_type: paper
event_title: 2020 7th NAFOSTED Conference on Information and Computer Science (NICS)
event_type: conference
refereed: TRUE
citation:   Bui, Ba Nam and Phan, Anh and Nguyen, Thi Nhat Thanh   Land-Cover Mapping from Sentinel Time-Series Imagery on the Google Earth Engine: A Case Study for Hanoi.  In: 2020 7th NAFOSTED Conference on Information and Computer Science (NICS).     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4349/1/final_paper.pdf