Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion
Coastal saltmarsh wetlands are vital “blue carbon” ecosystems. Fractional vegetation cover (FVC) is a key indicator revealing the spatial distribution and growth status of vegetation. Remote sensing has proven a vital tool for FVC estimation at regional or landscape scales. Establishing a species-le...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Diversity |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-2818/17/1/3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588700247130112 |
|---|---|
| author | Jinghan Sha Zhaojun Zhuo Qingqing Zhou Yinghai Ke Mengyao Zhang Jinyuan Li Yukui Min |
| author_facet | Jinghan Sha Zhaojun Zhuo Qingqing Zhou Yinghai Ke Mengyao Zhang Jinyuan Li Yukui Min |
| author_sort | Jinghan Sha |
| collection | DOAJ |
| description | Coastal saltmarsh wetlands are vital “blue carbon” ecosystems. Fractional vegetation cover (FVC) is a key indicator revealing the spatial distribution and growth status of vegetation. Remote sensing has proven a vital tool for FVC estimation at regional or landscape scales. Establishing a species-level FVC estimation model usually requires sufficient field measurements as training/validation samples. However, field-based sample collection in wetlands is challenging because of the harsh environment. In this study, we proposed a Fractional Vegetation Cover Wasserstein Generative Adversarial Network (FVC-WGAN) model for FVC sample expansion. We chose the Yellow River Delta as the study area and utilized the time series Sentinel-2 imagery and random forest regression model for species-level FVC estimation with the assistance of FVC-WGAN-generated samples. To assess the efficacy of FVC-WGAN, we designed 13 experimental schemes using different combinations of real and generated samples. Our results show that the FVC-WGAN-generated samples had similar feature values to the real samples. Supplementing 500 real samples with generated samples can achieve good accuracy with an average RMSE < 0.1. As the number of real samples increased, the accuracies of FVC estimation improved. When the number of the generated samples was balanced with the real samples, the accuracy improved in terms of both R<sup>2</sup>, RMSE and the spatial consistency. |
| format | Article |
| id | doaj-art-62cb7a6b8dbc493d9862244249b6dbbf |
| institution | Kabale University |
| issn | 1424-2818 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diversity |
| spelling | doaj-art-62cb7a6b8dbc493d9862244249b6dbbf2025-01-24T13:29:18ZengMDPI AGDiversity1424-28182024-12-01171310.3390/d17010003Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample ExpansionJinghan Sha0Zhaojun Zhuo1Qingqing Zhou2Yinghai Ke3Mengyao Zhang4Jinyuan Li5Yukui Min6College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCollege of Resource Environment and Tourism, Capital Normal University, Beijing 100048, ChinaCoastal saltmarsh wetlands are vital “blue carbon” ecosystems. Fractional vegetation cover (FVC) is a key indicator revealing the spatial distribution and growth status of vegetation. Remote sensing has proven a vital tool for FVC estimation at regional or landscape scales. Establishing a species-level FVC estimation model usually requires sufficient field measurements as training/validation samples. However, field-based sample collection in wetlands is challenging because of the harsh environment. In this study, we proposed a Fractional Vegetation Cover Wasserstein Generative Adversarial Network (FVC-WGAN) model for FVC sample expansion. We chose the Yellow River Delta as the study area and utilized the time series Sentinel-2 imagery and random forest regression model for species-level FVC estimation with the assistance of FVC-WGAN-generated samples. To assess the efficacy of FVC-WGAN, we designed 13 experimental schemes using different combinations of real and generated samples. Our results show that the FVC-WGAN-generated samples had similar feature values to the real samples. Supplementing 500 real samples with generated samples can achieve good accuracy with an average RMSE < 0.1. As the number of real samples increased, the accuracies of FVC estimation improved. When the number of the generated samples was balanced with the real samples, the accuracy improved in terms of both R<sup>2</sup>, RMSE and the spatial consistency.https://www.mdpi.com/1424-2818/17/1/3vegetation coverageremote sensingdeep learningcoastal wetlandsample expansion |
| spellingShingle | Jinghan Sha Zhaojun Zhuo Qingqing Zhou Yinghai Ke Mengyao Zhang Jinyuan Li Yukui Min Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion Diversity vegetation coverage remote sensing deep learning coastal wetland sample expansion |
| title | Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion |
| title_full | Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion |
| title_fullStr | Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion |
| title_full_unstemmed | Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion |
| title_short | Species-Level Saltmarsh Vegetation Fractional Cover Estimation Based on Time Series Sentinel-2 Imagery with the Assistance of Sample Expansion |
| title_sort | species level saltmarsh vegetation fractional cover estimation based on time series sentinel 2 imagery with the assistance of sample expansion |
| topic | vegetation coverage remote sensing deep learning coastal wetland sample expansion |
| url | https://www.mdpi.com/1424-2818/17/1/3 |
| work_keys_str_mv | AT jinghansha specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT zhaojunzhuo specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT qingqingzhou specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT yinghaike specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT mengyaozhang specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT jinyuanli specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion AT yukuimin specieslevelsaltmarshvegetationfractionalcoverestimationbasedontimeseriessentinel2imagerywiththeassistanceofsampleexpansion |