4.7 Article

Comparison and assessment of NDVI time series for seasonal wetland classification

Journal

INTERNATIONAL JOURNAL OF DIGITAL EARTH
Volume 11, Issue 11, Pages 1103-1131

Publisher

TAYLOR & FRANCIS LTD
DOI: 10.1080/17538947.2017.1375563

Keywords

NDVI time series; seasonal wetland; Poyang Lake; satellite image time series

Funding

  1. Major Special Project - the China High-Resolution Earth Observation System [30-Y20A37-9003-15/17]
  2. National Natural Science Foundation of China [41271423]

Ask authors/readers for more resources

Satellite-based wetland mapping faces challenges due to the high spatial heterogeneity and dynamic characteristics of seasonal wetlands. Although normalized difference vegetation index (NDVI) time series (NTS) shows great potential in land cover mapping and crop classification, the effectiveness of various NTS with different spatial and temporal resolution has not been evaluated for seasonal wetland classification. To address this issue, we conducted comparisons of those NTS, including the moderate-resolution imaging spectroradiometer (MODIS) NTS with 500m resolution, NTS fused with MODIS and Landsat data (MOD_LC8-NTS), and HJ-1 NDVI compositions (HJ-1-NTS) with finer resolution, for wetland classification of Poyang Lake. Results showed the following: (1) the NTS with finer resolution was more effective in the classification of seasonal wetlands than that of the MODIS-NTS with 500-m resolution and (2) generally, the HJ-1-NTS performed better than that of the fused NTS, with an overall accuracy of 88.12% for HJ-1-NTS and 83.09% for the MOD_LC8-NTS. Future work should focus on the construction of satellite image time series oriented to highly dynamic characteristics of seasonal wetlands. This study will provide useful guidance for seasonal wetland classification, and benefit the improvements of spatiotemporal fusion models.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Environmental Sciences

Estimating Satellite-Derived Bathymetry (SDB) with the Google Earth Engine and Sentinel-2

Dimosthenis Traganos, Dimitris Poursanidis, Bharat Aggarwal, Nektarios Chrysoulakis, Peter Reinartz

REMOTE SENSING (2018)

Article Environmental Sciences

Towards Global-Scale Seagrass Mapping and Monitoring Using Sentinel-2 on Google Earth Engine: The Case Study of the Aegean and Ionian Seas

Dimosthenis Traganos, Bharat Aggarwal, Dimitris Poursanidis, Konstantinos Topouzelis, Nektarios Chrysoulakis, Peter Reinartz

REMOTE SENSING (2018)

Article Environmental Sciences

Construction of High Spatial-Temporal Water Body Dataset in China Based on Sentinel-1 Archives and GEE

Yang Li, Zhenguo Niu, Zeyu Xu, Xin Yan

REMOTE SENSING (2020)

Review Environmental Sciences

Towards a comprehensive and consistent global aquatic land cover characterization framework addressing multiple user needs

Panpan Xu, Martin Herold, Nandin-Erdene Tsendbazar, Jan G. P. W. Clevers

REMOTE SENSING OF ENVIRONMENT (2020)

Article Geography, Physical

Assessing the ecological vulnerability of protected areas by using Big Earth Data

Yaomin Zheng, Shudong Wang, Yue Cao, Jinlian Shi, Yi Qu, Liping Li, Tianjie Zhao, Zhenguo Niu, Rui Yang, Peng Gong

Summary: A novel degree of ecological vulnerability index based on Big Earth Data was developed to assess the ecological vulnerability of global protected areas, showing relatively stable spatial patterns between 2001 and 2015. The Caspian Sea basin exhibited high ecological vulnerability, while the Black Sea basin showed low ecological vulnerability. Strengthening international cooperation is crucial in addressing ecological and resource bottlenecks in these significant international basins.

INTERNATIONAL JOURNAL OF DIGITAL EARTH (2021)

Article Environmental Sciences

Hierarchical Urban Land Mappings and Their Distribution with Physical Medium Environments Using Time Series of Land Resource Images in Beijing, China (1981-2021)

Tao Pan, Wenhui Kuang, Ruoyi Pan, Zhenguo Niu, Yinyin Dou

Summary: This study established a remote-sensing methodology of hierarchical urban land mapping to investigate the urban land changes in Beijing from 1981 to 2021. The results showed that there was a significant increase in impervious surface area during the urban expansion, but greening in the city was still observed. Moreover, the newly expanded urban regions had a lower proportion of impervious surface area and a higher vegetation coverage compared to the old urban regions, indicating a higher quality of life during urban expansion.

REMOTE SENSING (2022)

Article Environmental Sciences

Assessing a Prototype Database for Comprehensive Global Aquatic Land Cover Mapping

Panpan Xu, Nandin-Erdene Tsendbazar, Martin Herold, Jan G. P. W. Clevers

Summary: This study assessed the effectiveness of using existing global datasets to develop a comprehensive and user-oriented GALC database, identifying limitations in current datasets for comprehensive GALC mapping. The results revealed errors and shortcomings in certain maps, highlighting areas for improvement in future GALC characterization.

REMOTE SENSING (2021)

Article Environmental Sciences

A Novel Workflow for Seasonal Wetland Identification Using Bi-Weekly Multiple Remote Sensing Data

Liwei Xing, Zhenguo Niu, Cuicui Jiao, Jing Zhang, Shuqing Han, Guodong Cheng, Jianzhai Wu

Summary: Accurate wetland mapping is essential for their protection and management. In this study, a novel method using seasonal rules was proposed to generate reliable seasonal wetland maps. Sentinel-1 and Sentinel-2 data were used to generate a 15-day image time series, and the random forest algorithm was used for image classification. The method was able to accurately identify seasonal wetland types and provide accurate data for wetland protection decision-making.

REMOTE SENSING (2022)

Article Ecology

Response of China's Wetland NDVI to Climate Changes

Xin Yan, Rui Wang, Zhenguo Niu

Summary: This study explored the response of wetland vegetation to climate change in China using various datasets and found that wetland vegetation exhibited a downward trend after 2004. The study also revealed a correlation between wetland vegetation NDVI and precipitation or temperature. The impacts of climate change on wetland vegetation and the complexity of their response were discussed.

WETLANDS (2022)

Article Environmental Sciences

Improving the characterization of global aquatic land cover types using multi-source earth observation data

Panpan Xu, Nandin-Erdene Tsendbazar, Martin Herold, Jan G. P. W. Clevers, Linlin Li

Summary: This study evaluates the potential of multi-source freely available Earth Observation (EO) data for improving the characterization of aquatic land cover globally. Results show that the combination of different data sources can enhance the classification performance of water and vegetation types in aquatic areas. However, single-sensor data has limitations in discriminating mixed and spectrally similar types.

REMOTE SENSING OF ENVIRONMENT (2022)

Article Environmental Sciences

Dynamic Changes and Driving Forces of Alpine Wetlands on the Qinghai-Tibetan Plateau Based on Long-Term Time Series Satellite Data: A Case Study in the Gansu Maqu Wetlands

Bo Zhang, Zhenguo Niu, Dongqi Zhang, Xuanlin Huo

Summary: This study examined the evolution characteristics and driving forces of alpine wetlands in the Maqu wetlands located in the eastern part of the Qinghai-Tibet Plateau. The results showed a decrease in wetland area, with wetlands transitioning from wet to dry. Temperature and precipitation were identified as the main driving forces of these changes.

REMOTE SENSING (2022)

Article Multidisciplinary Sciences

Global long term daily 1 km surface soil moisture dataset with physics informed machine learning

Qianqian Han, Yijian Zeng, Lijie Zhang, Chao Wang, Egor Prikaziuk, Zhenguo Niu, Bob Su

Summary: This study uses physics-informed machine learning to generate a global, long-term, spatially continuous high resolution dataset of surface soil moisture. The dataset provides surface soil moisture (0-5 cm) at 1 km spatial and daily temporal resolution over the period 2000-2020. The performance of the dataset is evaluated and it can support investigations of climate extremes and long-term trend analysis.

SCIENTIFIC DATA (2023)

Article Engineering, Electrical & Electronic

Reliability Evaluation and Migration of Wetland Samples

Xin Yan, Zhenguo Niu

Summary: Sample acquisition and updating are crucial yet time-consuming steps in wetland classification and mapping research. This study evaluated the reliability of historical samples from the perspective of water inundation frequency, and proposed three sample migration methods for wetland classification experiment in the Tibetan Plateau. The relationship between the number of samples and classification accuracy was also analyzed in this research.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2021)

No Data Available