Remote sensing inversion of grassland aboveground biomass based on high accuracy surface modeling

Accurate and effective accounting of grassland aboveground biomass (AGB) is essential for grassland carbon storage accounting and pastoral agriculture sustainability. In this study, we combined AGB field survey data and remote sensing data to build a suitable model to estimate the grassland AGB in the Three-River Source Region (TRSR) of China. Three machine learning models were used to simulate the grassland AGB from 2001 to 2019, including support vector machine (SVM), random forest (RF), and high accuracy surface modeling (HASM). The results show that (1) the HASM achieved better results than the RF and SVM models (R-2 = 0.8459 > 0.72 > 0.5858; RMSE = 29 < 41 < 56), and the HASM results reproduce the spatial distribution characteristics of the biomass well. The subsequent spatiotemporal analysis of the AGB conducted in this study was based on the results of the HASM. (2) The highest AGB was located in the eastern and central-southern parts of the TRSR, and the lowest AGB was distributed in the western region. (3) The overall change in the AGB revealed that the percentage of the area that experienced a significant increase in AGB (21%) was larger than that of the area that experienced a significant decrease (13%), and the stable areas accounted for 66% of the total area. The grassland AGB increased by 1 g/m(2)/yr during 2001-2019. (4) The factors driving the changes in the AGB were analyzed. Overall, the warm and wet climate conditions promoted grass growth in most regions of the TRSR. (5) However, the biomass decreased in some regions with warm and wet conditions. For example, overgrazing and increased populations of grazing led to significant biomass decreases in the towns of Ziketang and Heka in Xinghai County. In this study, the grassland AGB was simulated based on the HASM model, with a high accuracy and a spatial resolution of 500 m. The results of this study provide a scientific basis for grassland resource protection and the highly effective implementation of grassland restoration projects in China.

Automated summary

Accurate and effective accounting of grassland aboveground biomass (AGB) is essential for grassland carbon storage accounting and pastoral agriculture sustainability. In this study, three machine learning models were used to simulate grassland AGB in the Three-River Source Region of China, with HASM model achieving the best results. The analysis revealed that the highest AGB was located in the eastern and central-southern parts of the TRSR, while the overall trend showed an increase in AGB, attributed to warm and wet climate conditions promoting grass growth in most regions.