Estimating Aboveground Biomass Using Sentinel-2 MSI Data and Ensemble Algorithms for Grassland in the Shengjin Lake Wetland, China

Chunhua Li,Wenbin Xu,Lizhi Zhou

doi:10.3390/rs13081595

Chunhua Li, Wenbin Xu + Show 1 more

Open Access

https://doi.org/10.3390/rs13081595

Copy DOI

Abstract

Wetland vegetation aboveground biomass (AGB) directly indicates wetland ecosystem health and is critical for water purification, carbon cycle, and biodiversity conservation. Accurate AGB estimation is essential for the monitoring and supervision of ecosystems, especially in seasonal floodplain wetlands. This paper explored the capability of spectral and texture features from the Sentinel-2 Multispectral Instrument (MSI) for modeling grassland AGB using random forest (RF) and extreme gradient boosting (XGBoost) algorithms in Shengjin Lake wetland (a Ramsar site). We use five-fold cross-validation to verify the model effectiveness. The results indicated that the RF and XGBoost models had a robust and efficient performance (with root mean square error (RMSE) of 126.571 g·m−2 and R2 of 0.844 for RF, RMSE of 112.425 g·m−2 and R2 of 0.869 for XGBoost), and the XGBoost models, by contrast, performed better. Both traditional and red-edge vegetation indices (VIs) obtained satisfactory results of AGB estimation (RMSE = 127.936 g·m−2, RMSE = 125.879 g·m−2 in XGBoost models, respectively), with the red-edge VIs contributed more to the AGB models. Moreover, we selected eight gray-level co-occurrence matrix (GLCM) textures calculated by four processing window sizes using the mean value of four offsets, and further analyzed the results of three analysis sets. Textures derived from traditional and red-edge bands using a 7 × 7 window size performed better in biomass estimation. This finding suggested that textures derived from the traditional bands were as important as the red-edge bands. The introduction of textures moderately improved the accuracy of modeling AGB, whereas the use of textures alo ne was not satisfactory. This research demonstrated that using the Sentinel-2 MSI and the two ensemble algorithms is an effective method for long-term dynamic monitoring and assessment of grass AGB in seasonal floodplain wetlands, which can support sustainable management and carbon accounting of wetland ecosystems.

Highlights

For the random forest (RF) models, the results showed that textures calculated on a 3 × 3 window size for different analysis sets performed worst in aboveground biomass (AGB) estimation according to the five-fold cross-validated of root mean square error (RMSE), R2, and CV-RMSE values
On the other hand, when using XGBoost algorithm, these results suggested that all models of textures calculated on a 7 × 7 window size for different analysis sets performed best for estimating AGB with the lowest RMSE, CV-RMSE, and the highest R2 values
For the analysis set 3, all XGBoost models of different window sizes yielded the best performance when compared to the other analysis sets, and it was found the highest accuracy for 7 × 7 window size, with an RMSE of 127.578 g·m−2, R2 of 0.849, and CV-RMSE of 0.133

Summary

Introduction

Wetlands are often transitional regions between terrestrial and aquatic ecosystems and serve extensive ecosystem functions, such as flooding and erosion reduction, ecological purification and protection, biodiversity conservation, and carbon storage [1,2,3]. Vegetation is a key component of wetland ecosystems and contributes to maintain ecosystem structure and function [4,5]. The biomass of wetland vegetation excellently indicates ecosystem health and has great significance in the global carbon cycle as an important parameter for evaluating the carbon sequestration capacity of wetlands [6,7]. Regional vegetation biomass changes are related to wetland ecosystem functional characteristics and carbon balance [8,9]. Accurate estimating for vegetation biomass is the basis of Remote Sens.

Results

Discussion

Conclusion