Estimating Surface Downward Longwave Radiation Using Machine Learning Methods

• Published in: Atmosphere
• Main Authors: Chunjie Feng, Xiaotong Zhang, Yu Wei, Weiyu Zhang, Ning Hou, Jiawen Xu, Kun Jia, Yunjun Yao, Xianhong Xie, Bo Jiang, Jie Cheng, Xiang Zhao
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2020
• Subjects: downward longwave radiation; machine learning; GBRT; energy budget; random forest; Meteorology. Climatology; QC851-999; Tundra
• Online Access: https://doi.org/10.3390/atmos11111147; https://doaj.org/article/c16bbea363a34c6b9c7fabf93e6350e8

The downward longwave radiation ( L d , 4–100 μm) is a major component of research for the surface radiation energy budget and balance. In this study, we applied five machine learning methods, namely artificial neural network (ANN), support vector regression (SVR), gradient boosting regression tree (GBRT), random forest (RF), and multivariate adaptive regression spline (MARS), to estimate L d using ground measurements collected from 27 Baseline Surface Radiation Network (BSRN) stations. L d measurements in situ were used to validate the accuracy of L d estimation models on daily and monthly time scales. A comparison of the results demonstrated that the estimates on the basis of the GBRT method had the highest accuracy, with an overall root-mean-square error (RMSE) of 17.50 W m −2 and an R value of 0.96 for the test dataset on a daily time scale. These values were 11.19 W m −2 and 0.98, respectively, on a monthly time scale. The effects of land cover and elevation were further studied to comprehensively evaluate the performance of each machine learning method. All machine learning methods achieved better results over the grass land cover type but relatively worse results over the tundra. GBRT, RF, and MARS methods were found to show good performance at both the high- and low-altitude sites.