Comparison of Machine-Learning Algorithms for Near-Surface Air-Temperature Estimation from FY-4A AGRI Data

Six machine-learning approaches, including multivariate linear regression (MLR), gradient boosting decision tree, k-nearest neighbors, random forest, extreme gradient boosting (XGB), and deep neural network (DNN), were compared for near-surface air-temperature (T-air) estimation from the new generation of Chinese geostationary meteorological satellite Fengyun-4A (FY-4A) observations. The brightness temperatures in split-window channels from the Advanced Geostationary Radiation Imager (AGRI) of FY-4A and numerical weather prediction data from the global forecast system were used as the predictor variables for T-air estimation. The performance of each model and the temporal and spatial distribution of the estimated T-air errors were analyzed. The results showed that the XGB model had better overall performance, with R-2 of 0.902, bias of -0.087 degrees C, and root-mean-square error of 1.946 degrees C. The spatial variation characteristics of the T-air error of the XGB method were less obvious than those of the other methods. The XGB model can provide more stable and high-precision T-air for a large-scale T-air estimation over China and can serve as a reference for T-air estimation based on machine-learning models.