Retrieval of Snow Depth over Arctic Sea Ice Using a Deep Neural Network

Abstract

The accurate knowledge of spatial and temporal variations of snow depth over sea ice in the Arctic basin is important for understanding the Arctic energy budget and retrieving sea ice thickness from satellite altimetry. In this study, we develop and validate a new method for retrieving snow depth over Arctic sea ice from brightness temperatures at different frequencies measured by passive microwave radiometers. We construct an ensemble-based deep neural network and use snow depth measured by sea ice mass balance buoys to train the network. First, the accuracy of the retrieved snow depth is validated with observations. The results show the derived snow depth is in good agreement with the observations, in terms of correlation, bias, root mean square error, and probability distribution. Our ensemble-based deep neural network can be used to extend the snow depth retrieval from first-year sea ice (FYI) to multi-year sea ice (MYI), as well as during the melting period. Second, the consistency and discrepancy of snow depth in the Arctic basin between our retrieval using the ensemble-based deep neural network and two other available retrievals using the empirical regression are examined. The results suggest that our snow depth retrieval outperforms these data sets.

Retrieval of Snow Depth on Arctic Sea Ice from the FY3B/MWRI

“…Trained using seven years of OIB snow depth data, the algorithm is suitable for FYI and MYI, and the bias and the RMSE relative to OIB snow depth data were 1.1 and 4 cm. In the same year, Liu et al [29] constructed an ensemble-based deep neural network to retrieve snow depth by the TB from the Special Sensor Microwave Imager/Sounder (SSMIS) and used snow depth from IMB data to train the network. The bias and RMSE between the obtained snow data and the IMB data were 0.1 and 9.8 cm, respectively.…”

Morphological approaches to understanding Antarctic Sea ice thickness

“…Recently, deep learning techniques have been applied to predicting snow depths based of remotely-sensed data. Liu et al (2019) used an ensemble-based deep neural network using brightness temperature from passive microwave radiometry to predict snow depths with higher accuracy than linear regressions. Braakmann-Folgmann and Donlon (2019) used a simple neural network with gradient ratios from microwave radiometry data to predict snow depth in the Arctic, with good comparison to OIB snow depths.…”

Downscaling Snow Depth Mapping by Fusion of Microwave and Optical Remote-Sensing Data Based on Deep Learning

“…Xiao [39] used the support vector regression (SVR) algorithm to establish a snow depth retrieval model based on different vegetation types and different snow periods, showing better accuracy and reducing "snow saturation effect". Machine learning and deep learning technology can describe the non-linear relationship between BTD and snow parameters, and overcome the limitations of a linear algorithm in different areas [40,41]. Although the machine learning technology has a wide range of applications and high accuracy, there is no detailed snow physical model involved in the retrieval process [42], thus the interpretability of the results is poor.…”