Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data

作者：Shaopeng Li, Bo Jiang, Shunlin Liang, Jianghai Peng, Hui Liang, Jiakun Han, Xiuwan Yin, Yunjun Yao, Xiaotong Zhang, Jie Cheng, Xiang Zhao, Qiang Liu, Kun Jia · 发表于：International Journal of Digital Earth · 年份：2022 · DOI：10.1080/17538947.2022.2130460 · 被引用次数：17 · 研究领域：Meteorological Phenomena and Simulations、Atmospheric aerosols and clouds、Climate variability and models

The all-wave net radiation (Rn) at the land surface represents surface radiation budget and plays an important role in the Earth's energy and water cycles. Many studies have been conducted to estimate from satellite top-of-atmosphere (TOA) data using various methods, particularly the application of machine learning (ML) and deep learning (DL). However, few studies have been conducted to provide a comprehensive evaluation about various ML and DL methods in retrieving. Based on extensive in situ measurements distributed at mid-low latitudes, the corresponding Moderate Resolution Imaging Spectroradiometer (MODIS) TOA observations, and the daily from the fifth generation of European Centre for Medium-Range Weather Forecasts Reanalysis 5 (ERA5) used as a priori knowledge, this study assessed nine models for daily estimation, including six classic ML methods (random forest -RF, adaptive boosting - Adaboost, extreme gradient boosting -XGBoost, multilayer perceptron -MLP, radial basis function neural network -RBF, and support vector machine -SVM) and three DL methods (multilayer perceptron neural network with stacked autoencoders -SAE, deep belief network -DBN and residual neural network -ResNet). The validation results showed that the three DL methods were generally better than the six ML methods except XGBoost, although they all performed poorly in certain conditions such as winter days, rugged terrain, and high elevation. ResNet had the most robust performance across different lan...