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

Ke Zhou,Shenglan Zhang,Xiaobo Deng,Hao Wang,Hailei Liu,Stefania Bonafoni

doi:10.1155/2020/8887364

Abstract

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 (Tair) 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 Tair estimation. The performance of each model and the temporal and spatial distribution of the estimated Tair errors were analyzed. The results showed that the XGB model had better overall performance, with R2 of 0.902, bias of −0.087°C, and root-mean-square error of 1.946°C. The spatial variation characteristics of the Tair error of the XGB method were less obvious than those of the other methods. The XGB model can provide more stable and high-precision Tair for a large-scale Tair estimation over China and can serve as a reference for Tair estimation based on machine-learning models.

Highlights

Air temperature (Tair) is one of the basic meteorological observation parameters [1,2,3] and is of great concern in scientific disciplines like hydrology, meteorology, and environmental science
Correlation analysis was performed to analyze the linear relationship between Tair and BT12, BT13, global forecast system (GFS) PWV, GFS RH, digital elevation model (DEM), longitude (LONG), latitude (LAT), and Julian day (JD)
The Pearson correlation coefficient only described the linear correlation between two variables; it could not identify the nonlinear relationship between two variables. erefore, the variable importance of the random forest (RF) algorithm was analyzed (Figure 4(b)). e RF algorithm modeled the nonlinear relationship well. e GFS h precipitable water vapor (GFS PWV) was identified as the most important variable for Tair estimation in the RF model, while the GFS RH and BT12 played important roles than other predictors. erefore, PWV and RH were used as inputs to effectively improve the accuracy of Tair estimation, which was consistent with the previous study [65]

Summary

Introduction

Air temperature (Tair) is one of the basic meteorological observation parameters [1,2,3] and is of great concern in scientific disciplines like hydrology, meteorology, and environmental science. It influences most land-surface processes, such as photosynthesis and land-surface evapotranspiration [4]. E summer Tair value in China is generally above 20°C, except in the high-altitude regions (e.g., Qinghai-Tibet Plateau). Is study focuses on the issue of summer Tair estimation in China using Advanced Geostationary Radiation Imager (AGRI) data. Large-scale Tair data are mainly obtained by interpolation from the data collected by surface meteorological stations. Summer heat waves have a major impact on agricultural food production, as well as the use of water and electricity [7]. is study focuses on the issue of summer Tair estimation in China using Advanced Geostationary Radiation Imager (AGRI) data.

Methods

Results

Conclusion