Publications

Chen, J; He, T; Jiang, B; Liang, SL (2020). Estimation of all-sky all-wave daily net radiation at high latitudes from MODIS data. REMOTE SENSING OF ENVIRONMENT, 245, 111842.

Abstract
Surface all-wave net radiation (R-n) plays an important role in various land surface processes, such as agricultural, ecological, hydrological, and biogeochemical processes. Recently, remote sensing of R-n at regional and global scales has attracted considerable attention and has achieved significant advances. However, there are many issues in estimating all-sky daily average R-n at high latitudes, such as posing greater uncertainty by surface and atmosphere satellite products at high latitudes, and unavailability of real-time and accurate cloud base height and temperature parameters. In this study, we developed the LRD (length ratio of daytime) classification model using the genetic algorithm-artificial neural network (GA-ANN) to estimate all-sky daily average R-n at high latitudes. With a very high temporal repeating frequency (similar to 6 to 20 times per day) at high latitudes, data from the Moderate Resolution Imaging Spectroradiometer (MODIS) were used to test the proposed method. R-n measurements at 82 sites and top-of-atmosphere (TOA) data of MODIS from 2000 to 2017 were matched for model training and validation. Two models for estimating daily average R-n were developed: model I based on instantaneous daytime MODIS observation and model II based on instantaneous nighttime MODIS observation. Validation results of model I showed an R-2 of 0.85, an RMSE of 23.66 W/m(2), and a bias of 0.27 W/m(2), whereas these values were 0.51, 15.04 W/m(2), and -0.08 W/m(2) for model II, respectively. Overall, the proposed machine learning algorithm with the LRD classification can accurately estimate the all-sky daily average R-n at high latitudes. Mapping of R-n over the high latitudes at 1 km spatial resolution showed a similar spatial distribution to R-n estimates from the Clouds and the Earth's Radiant Energy System (CERES) product. This method has the potential for operational monitoring of spatio-temporal change of R-n at high latitudes with a long-term coverage of MODIS observations.

DOI:
10.1016/j.rse.2020.111842

ISSN:
0034-4257