Mapping Phragmites australis Aboveground Biomass in the Momoge Wetland Ramsar Site Based on Sentinel-1/2 Images

Zhao, Youpeng; Mao, Dehua; Zhang, Dongyou; Wang, Zongming; Du, Baojia; Yan, Hengqi; Qiu, Zhiqiang; Feng, Kaidong; Wang, Jingfa; Jia, Mingming

doi:10.3390/rs14030694

Cited by 15 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Tao’er and Erlongtao Rivers flow through the area. The plant and animal resources in the reserve are rich, with more than 600 species of seed plants, including herbaceous species such as reeds, small-leafed adults, moss grasses, and fragrant cattails, which have a high population density and biomass, are the dominant species in the reserve, and are distributed in slightly different areas ( Zhao et al., 2022 ).…”

Section: Methodsmentioning

confidence: 99%

Response of vegetation variation to climate change and human activities in semi-arid swamps

et al. 2022

View full text Add to dashboard Cite

Vegetation is a sensitive factor in marsh ecosystems, which can provide nesting sites, foraging areas, and hiding places for waterfowl and can affect their survival environment. The Jilin Momoge National Nature Reserve, which consists of large areas of marshes, is located in the semi-arid region of northeast China and is an important stopover site for the critically endangered species of the Siberian Crane (Grus leucogeranus). Global climate change, extreme droughts and floods, and large differences in evaporation and precipitation in this region can cause rapid vegetation succession. In recent years, increased grain production and river-lake connectivity projects carried out in this area to increase grain outputs and restore wetlands have caused significant changes in the hydrological and landscape patterns. Therefore, research on the response of variation trends in vegetation patterns to the main driving factors (climate change and human activities) is critical for the conservation of the Siberian Crane. Based on the Google Earth Engine (GEE) platform, we obtained and processed the Normalized difference vegetation index (NDVI) data of the study area during the peak summer vegetation period for each year from 1984 to 2020, estimated the annual vegetation cover using Maximum value composites (MVC) method and the image dichotomy method, calculated and analyzed the spatial and temporal trends of vegetation cover, explored the response of vegetation cover change in terms of climate change and human activities, and quantified the relative contribution of both. The results revealed that first, from the spatial and temporal changes, the average annual growth rate of regional vegetation was 0.002/a, and 71.14% of the study area was improved. The vegetation cover showed a trend of degradation and then recovery, in which the percentage of high vegetation cover area decreased from 51.22% (1984–2000) to 28.33% (2001–2005), and then recovered to 55.69% (2006–2020). Second, among climate change factors, precipitation was more correlated with the growth of vegetation in the study area than temperature, and the increase in precipitation during the growing season could promote the growth of marsh vegetation in the Momoge Reserve. Third, overall, human activities have contributed to the improvement of vegetation cover in the study area with the implementation of important ecological projects, such as the return of farmland to wetlands, the return of grazing to grass, and the connection of rivers and lakes. Fourth, climate change and human activities jointly drive vegetation change, but the contribution of human activities in both vegetation improvement and degradation areas (85.68% and 78.29%, respectively) is higher than that of climate change (14.32% and 21.71%, respectively), which is the main reason for vegetation improvement or degradation in the study area. The analysis of vegetation pattern change within an intensive time series in semi-arid regions can provide a reference and basis for studying the driving factors in regions with rapid changes in vegetation and hydrological conditions.

show abstract

Section: Methodsmentioning

confidence: 99%

Response of vegetation variation to climate change and human activities in semi-arid swamps

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Numerous studies revealed that backscatter coefficients of SAR were crucial for AGB retrieval [13,17]. Difference (VH − VV), sum (VH + VV), and radar texture information are also significant in AGB retrieval [17,[46][47][48]. Hence, we obtained radar backscatter coefficients, differences (VH − VV), sums (VH + VV), and radar texture information from S-1.…”

Section: Obtainment Of Relevant Variablesmentioning

confidence: 99%

“…Some variables have a low correlation with AGB, or these variables may be co-dependent. To overcome the challenge of selecting the fewest predictors with the best predictive power and to help in the interpretation of the final model, backward feature elimination (BFE) was used to select appropriate variables [47,52]. Variables used in 16 AGB models are shown in Table 3.…”

Section: Selection Of Variables Used In Agb Modelingmentioning

confidence: 99%

Estimation of Above-Ground Biomass for Pinus densata Using Multi-Source Time Series in Shangri-La Considering Seasonal Effects

Chen,

He,

Zhang

et al. 2023

Forests

View full text Add to dashboard Cite

Forest above-ground biomass (AGB) is the basis of terrestrial carbon storage estimation, and making full use of the seasonal characteristics of remote sensing imagery can improve the estimation accuracy. In this study, we used multi-source time series and sample plots with the Random Forest (RF) model to estimate the AGB. The sources included Sentinel-1 (S-1), Sentinel-2 (S-2), and the S-1 and S-2 combination (S-1S-2). Time series included single season, annual, and multi-season. This study aims to (1) explore the optimal image acquisition season to estimate AGB; (2) determine whether the ability to estimate the AGB of multi-seasonal imagery exceeded that of annual and single-season imagery; (3) discover the sensitivity of different data to AGB according to phenological conditions. The results showed that: (1) images acquired in autumn were more useful for AGB estimation than spring, summer, and winter; (2) the S-1 multi-seasonal AGB model had higher accuracy than the annual or single-season one; (3) in autumn and spring, S-1 had higher estimation accuracy than S-2, and in autumn and spring, estimation accuracy from S-1S-2 was higher than that from S-1 and S-2; (4) in 16 AGB estimation models, the best estimation accuracy was achieved by the autumn AGB model from S-1S-2 (R2 = 0.90, RMSE = 16.26 t/ha, p = 0.82, and rRMSE = 18.97). This study could be useful to identify the optimal image acquisition season for AGB estimation, thus reducing the economic cost of image acquisition and improving the estimation accuracy.

show abstract

“…Tian et al [16] used random forest to classify the vegetation of wetlands in arid areas of Xinjiang. L. F. Ruiz et al [17][18][19][20][21] used Sentinel-1 images to classify wetland types.…”

Section: Introductionmentioning

confidence: 99%

Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer

et al. 2023

View full text Add to dashboard Cite

Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct a wetland classification study for coastal wetlands in Yancheng, Jiangsu, China. After preprocessing the Sentinel data, nine classification objects (construction land, Spartina alterniflora (S. alterniflora), Suaeda salsa (S. salsa), Phragmites australis (P. australis), farmland, river system, aquaculture and tidal falt) were identified based on the previous literature and remote sensing images. Moreover, mAcc, mIoU, aAcc, Precision, Recall and F-1 score were chosen as evaluation indicators. This study explores the potential and effectiveness of multiple methods, including data image processing, machine learning and deep learning. The results indicate that SegFormer is the best model for wetland classification, efficiently and accurately extracting small-scale features. With mIoU (0.81), mAcc (0.87), aAcc (0.94), mPrecision (0.901), mRecall (0.876) and mFscore (0.887) higher than other models. In the face of unbalanced wetland categories, combining CrossEntropyLoss and FocalLoss in the loss function can improve several indicators of difficult cases to be segmented, enhancing the classification accuracy and generalization ability of the model. Finally, the category scale pie chart of Yancheng Binhai wetlands was plotted. In conclusion, this study achieves an effective segmentation of Yancheng coastal wetlands based on the semantic segmentation method of deep learning, providing technical support and reference value for subsequent research on wetland values.

show abstract

Mapping Phragmites australis Aboveground Biomass in the Momoge Wetland Ramsar Site Based on Sentinel-1/2 Images

Cited by 15 publications

References 46 publications

Response of vegetation variation to climate change and human activities in semi-arid swamps

Response of vegetation variation to climate change and human activities in semi-arid swamps

Estimation of Above-Ground Biomass for Pinus densata Using Multi-Source Time Series in Shangri-La Considering Seasonal Effects

Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer

Contact Info

Product

Resources

About