Estimating Urban Vegetation Biomass from Sentinel-2A Image Data

Abstract

Urban vegetation biomass is a key indicator of the carbon storage and sequestration capacity and ecological effect of an urban ecosystem. Rapid and effective monitoring and measurement of urban vegetation biomass provide not only an understanding of urban carbon circulation and energy flow but also a basis for assessing the ecological function of urban forest and ecology. In this study, field observations and Sentinel-2A image data were used to construct models for estimating urban vegetation biomass in the case study of the east Chinese city of Xuzhou. Results show that (1) Sentinel-2A data can be used for urban vegetation biomass estimation; (2) compared with the Boruta based multiple linear regression models, the stepwise regression models—also multiple linear regression models—achieve better estimations (RMSE = 7.99 t/hm2 for low vegetation, 45.66 t/hm2 for broadleaved forest, and 6.89 t/hm2 for coniferous forest); (3) the models for specific vegetation types are superior to the models for all-type vegetation; and (4) vegetation biomass is generally lowest in September and highest in January and December. Our study demonstrates the potential of the free Sentinel-2A images for urban ecosystem studies and provides useful insights on urban vegetation biomass estimation with such satellite remote sensing data.

Modeling Soil Moisture from Multisource Data by Stepwise Multilinear Regression: An Application to the Chinese Loess Plateau

“…Type2 from the University of Maryland (UMD) land cover classification scheme (with 16 different cover types) [97], the land cover data were reclassified here into three categories, namely croplands, forest, and shrublands, as well as other land covers in the study area (Table 2). With regard to the variable of land cover (a categorical variable), with other land covers as reference (row in the orange color background in Table 2), the remaining two land cover types (LC1 and LC2, rows in the green color background in Table 2) were integrated as dummy variables in the modeling procedure (with only two values; 0 and 1) [98,99].…”

“…The next step is to determine the actual set of variables used from 34 candidate variables (12 quantitative variables and 22 dummy variables) in the final regression. SMLR is routinely used for finding important variables while multicollinearity among variables often undermines its performance [98,112]. To select variables without multicollinearity, the general MLR model was first applied using calibration samples with 34 independent variables for each period (monthly, seasonal, and annual data) (Figure 4).…”

Optimization of Modelling Population Density Estimation Based on Impervious Surfaces

“…The correlation analysis provided the basis for modelling. Furthermore, to quantitatively characterise the multicollinearity, it was checked according to a rule of thumb stating that a variance inflation factor (VIF) value above 10 rules out the variable because of the high multicollinearity [52].…”

“…As the validated model can be applied for the population estimation, it is vital to test the model fit. In this study, the model fit between the predicted and true population density at the township scale was examined using the residual-based adjusted R 2 , relative mean square error (RMSE), and the mean average error (MAE) [52].…”

Land-Cover and Elevation-Based Mapping of Aboveground Carbon in a Tropical Mixed-Shrub Forest Area in West Java, Indonesia

“…Remote sensing methods are more advanced and combine ground measurement data with a wide range of both optical and microwave remote sensing data (e.g., [8,9]). The latter methods include a simple lookup table method that links ground measurement data to a land-cover map that is generated from satellite image classification (e.g., [10]), regression model development using different spectral variables and indices derived from satellite image data as predictors (e.g., [11,12]), a combination of regression modeling and kriging interpolation (e.g., [13]), and the application of LiDAR (light detection and ranging) (e.g., [14,15]) and RADAR (radio detection and ranging) (e.g., [16]) data. Developing an efficient method with an acceptable level of accuracy is a considerable challenge, particularly in countries and regions with limited resources, with limited access to high-resolution and high-quality remote sensing data.…”