Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning

• Published in: Remote Sensing
• Main Authors: Haoyu Wang, Xiang Zhao, Xin Zhang, Donghai Wu, Xiaozheng Du
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2019
• Subjects: time series; land cover classification; Bi-LSTM; quantitative remote sensing; Science; Q; Tundra
• Online Access: https://doi.org/10.3390/rs11141639; https://doaj.org/article/2f980be7bb374beb9697001cadb7ffd4

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.