RESUMO
In the context of global warming, there is a substantial demand for accurate and cost-effective assessment and comprehensive understanding of forest above-ground biomass (AGB) dynamics. The timeliness and low cost of optical remote sensing data enable the mapping of large-scale forest AGB dynamics. However, mapping forest AGB with optical remote sensing data presents challenges primarily due to data uncertainty and the complex nature of the forest environment. Previous studies have demonstrated the potential of meteorological data in enhancing forest AGB mapping. To accurately capture the dynamics of forest AGB, we initially acquired Landsat datasets, digital elevation model (DEM), and meteorological datasets (temperature, humidity, and precipitation) from 2010 to 2020 in Changsha-Zhuzhou-Xiangtan urban agglomeration (CZT) located in Hunan Province, China. Spectral variables (SVs), including spectral bands and vegetation indices, were extracted from Landsat images, while meteorological variables (MVs) were derived from the monthly meteorological data using the Savitzky-Golay (S-G) filtering algorithm. Additionally, terrain variables (TVs) were also extracted from the DEM data. Three modelling models, multiple linear regression (MLR), K nearest neighbor (KNN) and random forest (RF), were developed for mapping the dynamics of forest AGB in CZT. The result revealed that MVs have the potential to improve forest AGB mapping. Integration of MVs into the models resulted in a significant reduction in root mean square error (RMSE) ranging from 32.85 % to 19.25 % compared to utilizing only SVs. However, minimal improvement was observed with the inclusion of TVs due to negligible topographic relief within the study area. An upward trend of forest AGB in CZT was observed during this period, which can be attributed to the effective implementation of government environmental protection policies. It is confirmed that the meteorological data has significant contribution to forest AGB mapping, thereby endorsing advancements in forest resource monitoring and management programs.
RESUMO
Normally, forest quality (FQ) and site quality (SQ) play an important role in evaluating actual and potential forest productivity. Traditionally, these assessment indices (FQ and SQ) are mainly based on forest parameters extracted from ground measurement (forest height, age, density, forest stem volume (FSV), and DBH), which is labor-intensive and difficult to access in certain remote forest areas. Recently, remote sensing images combined with a small number of samples were gradually applied to map forest parameters because of the various advantages of remote sensing technology, such as low cost, spatial coverage, and high efficiency. However, FQ and SQ related to forest parameters are rarely estimated using remote sensing images and machine learning models. In this study, the Sentinel images and ground samples of planted Chinese fir forest located in the ecological "green-core" area of Changzhutan urban cluster, were initially employed to explore the feasibility of mapping the FQ and SQ. And then, four types of alternative variables (backscattering coefficients (VV and VH), multi-spectral bands, vegetation indices, and texture characteristics) were extracted from Sentinel-1A and Sentinel-2A images, respectively. After selecting variables using a stepwise regression model, three machine learning models (SVR, RF, and KNN) were employed to estimate various forest parameters. Finally, the FQ of the study region was directly mapped by the weights sum of related factors extracted by the factor analysis method, and the SQ was also extracted using mapped forest height and age. The results illustrated that the accuracy of estimated forest parameters (DBH, H, and Age) was significantly higher than FSV, FCC, and Age and the largest and smallest rRMSEs were observed from FSV (0.38~0.40) and forest height (0.20~0.21), respectively. Using mapped forest parameters, it also resulted that the rRMSEs of estimated FQ and SQ were 0.19 and 0.15, respectively. Furthermore, after normalization and grading, the grades of forest quality were mainly concentrated in grades I, II, and III in the study region. Though the accuracy of mapping FQ and SQ is limited by the saturation phenomenon, it is significantly proved that using machine learning models and Sentinel images has great potential to indirectly map FQ and SQ.