Article Details

Abstract

To explore a classification method for aquatic vegetation applicable to domestic Gaofen data, this study systematically evaluates the spectral, index, and texture features of GF-1 WFV data for discriminating aquatic vegetation types. A random forest-based method for aquatic vegetation classification is constructed, achieving high-accuracy classification of submerged vegetation, floating-leaved/emergent vegetation, and algal blooms. The spatiotemporal evolution characteristics of aquatic vegetation in Taihu Lake over the past decade (2016—2025) are analyzed. The results show that the feature-selected random forest method using visible and near-infrared data achieves classification accuracy comparable to that of the VBI (vegetation and bloom indices) algorithm based on shortwave infrared. The overall accuracy is 92.33% and the Kappa coefficient is 0.897 8. Independent validation indicates an overall classification accuracy of 89.23% and a Kappa coefficient of 0.855 0, demonstrating stable and reliable performance. Over the past decade, the spatiotemporal variation patterns of algal blooms, submerged aquatic vegetation, and floating/emergent aquatic vegetation in Taihu Lake remain relatively stable, each exhibiting distinct characteristics: Algal blooms exhibit significant seasonal spatial migration patterns. Over the past decade, the maximum area of algal blooms fluctuates, while the past five years show a downward trend. Submerged aquatic vegetation and floating-leaved/emergent vegetation are characterized by “expanding in place”, while submerged aquatic vegetation exhibits significant ecological vulnerability.

Keywords

remote sensing; GF-1 WFV; aquatic vegetation; submerged aquatic vegetation; algal bloom; Taihu Lake

References

1. [1] Wang J M，Cai Y，KE C Q，et al. Simultaneous Monitoring of Algal Bloom and Aquatic Vegetation in Eutrophic Shallow Lakes of the Middle and Lower Yangtze River Basin Using Deep Learning [J/OL].Limnologica，2025，114：126280.https://doi.org/10.1016/j.limno.2025.126280.
2. [2] Yu Haicheng, Lv Tian, Wang Huiyuan, etc A preliminary scheme for a classification system of aquatic vegetation in China [J]. Chinese Science: Life Sciences, 2022, 52 (9): 1335-1355
3. [3] Rowan G S L，Kalacska M. A Review of Remote Sensing of Submerged Aquatic Vegetation for Non-Specialists [J/OL].Remote Sensing，2021，13（4）：623.https://doi.org/10.3390/rs13040623.
4. [4] Du Y C，Zhao H，Li J S，et al. Cyanobacterial Blooms Prediction in China's Large Hypereutrophic Lakes Based on MODIS Observations and Bayesian Theory [J/OL].Journal of hazardous materials，2024，480：136057.https://doi.org/10.1016/j.jhazmat.2024.136057.
5. [5] Liu J Y，Hou X J，Huang H B，et al. Transformation of Aquatic Vegetation in Chinese Lakes from 1988 to 2023 [J/OL].Remote Sensing of Environment，2025，330：114999.https://doi.org/10.1016/j.rse.2025.114999.
6. [6] Pu Jing Research on Identification of Algae Blossoms and Aquatic Vegetation in China Based on Multi source Remote Sensing Images [D]. Changchun: Changchun Normal University, 2022
7. [7] Dai Y H，Feng L，Hou X J，et al. An automatic Classification Algorithm for Submerged Aquatic Vegetation in Shallow Lakes Using Landsat Imagery [J/OL].Remote Sensing of Environment，2021，260：112459.https://doi.org/10.1016/j.rse.2021.112459.
8. [8] Piaser E，Villa P. Evaluating Capabilities of Machine Learning Algorithms for Aquatic Vegetation Classification in Temperate Wetlands Using Multi-temporal Sentinel-2 Data [J/OL].International Journal of Applied Earth Observation and Geoinformation，2023，117：103202.https://doi.org/10.1016/j.jag.2023.103202.
9. [9] Huang Linsheng, Ni Guigao, Wang Kang, etc Long term remote sensing monitoring of temporal and spatial evolution of aquatic vegetation and algal blooms in shallow lakes: taking Changdang Lake in the Taihu Lake Lake Basin as an example (1985-2021) [J]. Lake Science, 2025, 37 (2): 368-378
10. [10] Luo Juhua, Yang Jingzhi Cheng, Duan Hongtao, etc Progress in Remote Sensing Monitoring of Aquatic Vegetation in Shallow Lakes [J]. Journal of Remote Sensing, 2022, 26 (1): 68-76
11. [11] Oyama Y，Matsushita B，Fukushima T. Distinguishing Surface Cyanobacterial Blooms and Aquatic Macrophytes Using Landsat/TM and ETM+Shortwave Infrared Bands [J].Remote Sensing of Environment，2014，157：35-47.
12. [12] Zhu Qing, Li Junsheng, Zhang Fangfang, etc Recognition of blue-green algal blooms and aquatic plants in the Taihu Lake Lake based on coastal zone hyperspectral imager image [J]. Remote Sensing Technology and Application, 2016, 31 (5): 879-885
13. [13] Shi Hao, Zhang Ting, Li Xuwen, etc Dynamic monitoring of submerged vegetation distribution in the northern bay of the Taihu Lake Lake in spring based on multi satellite remote sensing images [J]. Environmental Monitoring and Early Warning, 2016, 8 (1): 13-18
14. [14] Yang Zhixuan, Li Yunxiang, Zhu Guangwei, et al. Analysis of factors affecting the change of cyanobacteria bloom area in the Taihu Lake Lake from 2003 to 2023 [J]. Lake Science, 2025, 37 (3): 734-751
15. [15] Li Junsheng, Wu Di, Wu Yuanfeng, etc Identification of water blooms and aquatic higher plants in the Taihu Lake Lake based on measured spectral data [J]. Lake Science, 2009, 21 (2): 215-222
16. [16] Liang Q C，Zhang Y H，Ma R H，et al. A MODIS-Based Novel Method to Distinguish Surface Cyanobacterial Scums and Aquatic Macrophytes in Lake Taihu [J/OL].Remote Sensing，2017，9（2）：133.https://doi.org/10.3390/rs9020133.
17. [17] Luo J H，Ni G G，Zhang Y L，et al. A New Technique for Quantifying Algal Bloom， Floating/Emergent and Submerged Vegetation In Eutrophic Shallow Lakes Using Landsat Imagery [J/OL].Remote Sensing of Environment，2023，287：113480.https://doi.org/10.1016/j.rse.2023.113480.
18. [18] Yan F L，Li Y Z，Fan X T，et al. Estimating Chlorophyll-a Concentrations in Optically Shallow Waters Using Gaofen-1 Wide-Field-of-View （GF-1 WFV） Datasets from Lake Taihu, China [J/OL].Remote Sensing，2025，17（7）：1299.https://doi.org/10.3390/rs17071299.
19. [19] Luo J H，Ma R H，Duan H T，et al. A New Method for Modifying Thresholds in the Classification of Tree Models for Mapping Aquatic Vegetation in Taihu Lake with Satellite Images [J].Remote Sensing，2014，6（8）：7442-7462.
20. [20] Breiman L. Random forests [J].Machine Learning，2001，45：5-32.
21. [21] Wang Shuai, Xu Hanqiu, Shi Tingting Inversion of tassel transformation coefficients for GF-1 WFV2 sensor data [J]. Advances in Earth Sciences, 2018, 33 (6): 641-652

Funding

National Key Research and Development Project (2022YFC330160200); Jointly funded by the Natural Science Foundation of China (40701126)

About the authors

Li Yun (2001-), female, Han ethnicity, from Jinan, Shandong, currently pursuing a master's degree in disaster and environmental remote sensing; Corresponding author: Yan Fuli (1973-), male, Han ethnicity, from Qixia, Shandong, associate researcher, doctoral student, research direction: disaster and environmental remote sensing.