Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning
Land cover classification data have a very important practical application value, and long time series land cover classification datasets are of great significance studying environmental changes, urban changes, land resource surveys, hydrology and ecology. At present, the starting point of continuou...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs11141639 https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4 |
id |
ftdoajarticles:oai:doaj.org/article:2f980be7bb374beb9697001cadb7ffd4 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:2f980be7bb374beb9697001cadb7ffd4 2023-05-15T18:40:33+02:00 Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning Haoyu Wang Xiang Zhao Xin Zhang Donghai Wu Xiaozheng Du 2019-07-01T00:00:00Z https://doi.org/10.3390/rs11141639 https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4 EN eng MDPI AG https://www.mdpi.com/2072-4292/11/14/1639 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs11141639 https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4 Remote Sensing, Vol 11, Iss 14, p 1639 (2019) time series land cover classification Bi-LSTM quantitative remote sensing Science Q article 2019 ftdoajarticles https://doi.org/10.3390/rs11141639 2022-12-31T10:53:36Z Land cover classification data have a very important practical application value, and long time series land cover classification datasets are of great significance studying environmental changes, urban changes, land resource surveys, hydrology and ecology. At present, the starting point of continuous land cover classification products for many years is mostly after the year 2000, and there is a lack of long-term continuously annual land cover classification products before 2000. In this study, a long time series classification data extraction model is established using a bidirectional long-term and short-term memory network (Bi-LSTM). In the model, quantitative remote sensing products combined with DEM, nighttime lighting data, and latitude and longitude elevation data were used. We applied this model in China and obtained China’s 1982−2017 0.05° land cover classification product. The accuracy assessment results of the test data show that the overall accuracy is 84.2% and that the accuracies of wetland, water, glacier, tundra, city and bare soil reach 92.1%, 92.0%, 94.3%, 94.6% and 92.4%, respectively. For the first time, this study used a variety of long time series data, especially quantitative remote sensing products, for the classification of features. At the same time, it also acquired long time series land cover classification products, including those from the year 2000. This study provides new ideas for the establishment of higher-resolution long time series land cover classification products. Article in Journal/Newspaper Tundra Directory of Open Access Journals: DOAJ Articles Remote Sensing 11 14 1639 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
time series land cover classification Bi-LSTM quantitative remote sensing Science Q |
spellingShingle |
time series land cover classification Bi-LSTM quantitative remote sensing Science Q Haoyu Wang Xiang Zhao Xin Zhang Donghai Wu Xiaozheng Du Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
topic_facet |
time series land cover classification Bi-LSTM quantitative remote sensing Science Q |
description |
Land cover classification data have a very important practical application value, and long time series land cover classification datasets are of great significance studying environmental changes, urban changes, land resource surveys, hydrology and ecology. At present, the starting point of continuous land cover classification products for many years is mostly after the year 2000, and there is a lack of long-term continuously annual land cover classification products before 2000. In this study, a long time series classification data extraction model is established using a bidirectional long-term and short-term memory network (Bi-LSTM). In the model, quantitative remote sensing products combined with DEM, nighttime lighting data, and latitude and longitude elevation data were used. We applied this model in China and obtained China’s 1982−2017 0.05° land cover classification product. The accuracy assessment results of the test data show that the overall accuracy is 84.2% and that the accuracies of wetland, water, glacier, tundra, city and bare soil reach 92.1%, 92.0%, 94.3%, 94.6% and 92.4%, respectively. For the first time, this study used a variety of long time series data, especially quantitative remote sensing products, for the classification of features. At the same time, it also acquired long time series land cover classification products, including those from the year 2000. This study provides new ideas for the establishment of higher-resolution long time series land cover classification products. |
format |
Article in Journal/Newspaper |
author |
Haoyu Wang Xiang Zhao Xin Zhang Donghai Wu Xiaozheng Du |
author_facet |
Haoyu Wang Xiang Zhao Xin Zhang Donghai Wu Xiaozheng Du |
author_sort |
Haoyu Wang |
title |
Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
title_short |
Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
title_full |
Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
title_fullStr |
Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
title_full_unstemmed |
Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning |
title_sort |
long time series land cover classification in china from 1982 to 2015 based on bi-lstm deep learning |
publisher |
MDPI AG |
publishDate |
2019 |
url |
https://doi.org/10.3390/rs11141639 https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4 |
genre |
Tundra |
genre_facet |
Tundra |
op_source |
Remote Sensing, Vol 11, Iss 14, p 1639 (2019) |
op_relation |
https://www.mdpi.com/2072-4292/11/14/1639 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs11141639 https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4 |
op_doi |
https://doi.org/10.3390/rs11141639 |
container_title |
Remote Sensing |
container_volume |
11 |
container_issue |
14 |
container_start_page |
1639 |
_version_ |
1766229937307516928 |