期刊
REMOTE SENSING OF ENVIRONMENT
卷 274, 期 -, 页码 -出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.rse.2022.112999
关键词
Transfer learning; Machine learning; VIIRS; Downward shortwave radiation; Radiative transfer; Solar energy
资金
- NASA [80NSSC18K0620, 80NSSC21K0701]
This study introduces the concept of transfer learning and applies it to estimate global downward shortwave radiation using a neural network combined with radiative transfer simulations and ground measurements. The proposed method achieves accurate estimates with only top-of-atmosphere and surface albedo inputs. The results show high accuracy in both instantaneous and daily estimates, outperforming traditional ML models and physics models.
In recent years, machine learning (ML) has been successfully used in estimating downward shortwave radiation (DSR). To achieve global estimations, traditional ML models need sufficient ground measurements covering various atmospheric and surface conditions globally, which is difficult to accomplish. Training on the simulated data of a radiative transfer model (RTM) is a possible solution, but widely used RTMs ignore some complex cloud conditions which brings bias to simulations. In this study, a neural network applied with the transfer-learning (TL) concept is introduced to utilize both radiative transfer simulations and ground measurement data, achieving global DSR estimation with only top-of-atmosphere and surface albedo at local solar noon as inputs. The proposed method estimates both instantaneous and daily DSR from Visible Infrared Imaging Radiometer Suite (VIIRS) data at 750-m resolution, and both the estimates are validated by 40 independent stations globally. The root mean-square error and relative root mean square error of instantaneous DSR validation over 25 Baseline Surface Radiation Network, seven Surface Radiation Network, and eight Greenland Climate Network stations in 2013 were 91.2 (16.1%), 106.3 (18.3%), 75.0 (24.2%) W/m2, respectively, and the daily validation achieved 30.8 (15.5%), 33.5 (17.6%), and 31.3 (14.4) W/m2, respectively. The proposed method presents significant high accuracy over polar regions and similar performances over other areas compared with traditional ML models, physics models (e.g., look-up tables and direct estimations), and existing DSR products. The algorithm is also applied to VIIRS swath data to test its global efficacy. Instantaneous mapping captures the spatial pattern of the cloud-mask product, and daily mapping shows spatial patterns similar to the Clouds and the Earth's Radiant Energy System Synoptic TOA and surface fluxes and clouds product, but with more detail. Further analysis indicates that model performance is less sensitive to the quantity of training data after TL has been incorporated. This study demonstrates the advantages of TL on boosting both the generality and accuracy of DSR estimation, which can potentially be applied to other variable retrievals.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据