1. Prediction of Active Microwave Backscatter Over Snow-Covered Terrain Across Western Colorado Using a Land Surface Model and Support Vector Machine Regression
- Author
-
Jong-Min Park, Hans Lievens, and Barton A. Forman
- Subjects
Technology ,Atmospheric Science ,010504 meteorology & atmospheric sciences ,Geophysics. Cosmic physics ,0211 other engineering and technologies ,C-BAND SAR ,02 engineering and technology ,LEARNING PREDICTIONS ,01 natural sciences ,Remote Sensing ,Engineering ,NASA land information system (LIS) ,Snow ,CLIMATE-CHANGE ,BRIGHTNESS TEMPERATURE ,SEASONAL SNOW ,synthetic aperture radar (SAR) ,Ocean engineering ,Geography, Physical ,Physical Sciences ,SIR-C/X-SAR ,support vector machine (SVM) ,Land surface model ,Synthetic aperture radar ,Backscatter ,Mean squared error ,ERS-1 SAR DATA ,TIME-SERIES ,Terrain ,WET-SNOW ,snow-covered terrain ,Land surface ,Training ,Computers in Earth Sciences ,Imaging Science & Photographic Technology ,TC1501-1800 ,021101 geological & geomatics engineering ,0105 earth and related environmental sciences ,Remote sensing ,Science & Technology ,Support vector machines ,QC801-809 ,Training (meteorology) ,Engineering, Electrical & Electronic ,Snowpack ,Support vector machine ,Physical Geography ,WATER EQUIVALENT - Abstract
The main objective of this article is to develop a physically constrained support vector machine (SVM) to predict C-band backscatter over snow-covered terrain as a function of geophysical inputs that reasonably represent the relevant characteristics of the snowpack. Sentinel-1 observations, in conjunction with geophysical variables from the Noah-MP land surface model, were used as training targets and input datasets, respectively. Robustness of the SVM prediction was analyzed in terms of training targets, training windows, and physical constraints related to snow liquid water content. The results showed that a combination of ascending and descending overpasses yielded the highest coverage of prediction (15.2%) while root mean square error (RMSE) ranged from 2.06 to 2.54 dB and unbiased RMSE ranged from 1.54 to 2.08 dB, but that the combined overpasses were degraded compared with ascending-only and descending-only training target sets due to the mixture of distinctive microwave signals during different times of the day (i.e., 6 A.M. versus 6 P.M. local time). Elongation of the training window length also increased the spatial coverage of prediction (given the sparsity of the training sets), but resulted in introducing more random errors. Finally, delineation of dry versus wet snow pixels for SVM training resulted in improving the accuracy of predicted backscatter relative to training on a mixture of dry and wet snow conditions. The overall results suggest that the prediction accuracy of the SVM was strongly linked with the first-order physics of the electromagnetic response of different snow conditions. ispartof: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING vol:14 pages:2403-2417 ispartof: location:United States status: published
- Published
- 2022