The normalization of LST relative to environmental parameters is of great importance in various environmental applications. The purpose of this study was to develop a new approach for LST normalization relative to env...The normalization of LST relative to environmental parameters is of great importance in various environmental applications. The purpose of this study was to develop a new approach for LST normalization relative to environmental variables. These included topographic variables (i.e. solar irradiance and near-surface temperature lapse rate (NSTLR)) as well as biophysical properties (i.e. vegetation,wetness,and albedo). The study was conducted in two phases,namely (1) using global and (2) local optimization strategies to calculate the regression coefficients of environmental variables in the partial least squares regression (PLSR) and build the non-linear linking model in the random forest regression (RFR). The RMSEs between actual LST and modeled LST based on the global and local optimization strategies using PLSR (RFR) were 2.202 (0.935) and 0.939 (0.835) °C,respectively. The results showed that RFR had higher efficiency than PLSR in normalizing LST. Moreover,the local optimization method outperformed the global optimization method in terms of normalization accuracy. The results of this study could be very useful in many environmental applications such as identifying thermal anomalies,and surface anthropogenic heat island modeling.展开更多
文摘The normalization of LST relative to environmental parameters is of great importance in various environmental applications. The purpose of this study was to develop a new approach for LST normalization relative to environmental variables. These included topographic variables (i.e. solar irradiance and near-surface temperature lapse rate (NSTLR)) as well as biophysical properties (i.e. vegetation,wetness,and albedo). The study was conducted in two phases,namely (1) using global and (2) local optimization strategies to calculate the regression coefficients of environmental variables in the partial least squares regression (PLSR) and build the non-linear linking model in the random forest regression (RFR). The RMSEs between actual LST and modeled LST based on the global and local optimization strategies using PLSR (RFR) were 2.202 (0.935) and 0.939 (0.835) °C,respectively. The results showed that RFR had higher efficiency than PLSR in normalizing LST. Moreover,the local optimization method outperformed the global optimization method in terms of normalization accuracy. The results of this study could be very useful in many environmental applications such as identifying thermal anomalies,and surface anthropogenic heat island modeling.
