loading page

A machine learning-based geostatistical downscaling method for coarse-resolution soil moisture products
  • +3
  • Yan Jin,
  • Yong Ge,
  • Yaojie Liu,
  • Yuehong Chen,
  • Haitao Zhang,
  • Gerard Heuvelink
Yan Jin
Nanjing University of Posts and Telecommunications
Author Profile
Yong Ge
Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences
Author Profile
Yaojie Liu
Nanjing University
Author Profile
Yuehong Chen
Hohai University
Author Profile
Haitao Zhang
Nanjing University of Posts and Telecommunications
Author Profile
Gerard Heuvelink
Wageningen University
Author Profile

Abstract

The land Surface Soil Moisture (SSM) products derived from microwave remote sensing have a coarse spatial resolution, therefore downscaling is required to obtain accurate SSM at high spatial resolution. An effective way to handle the stratified heterogeneity is to model for various stratifications, however the number of samples is often limited under each stratification, influencing the downscaling accuracy. In this study, a machine learning-based geostatistical model, which combines various ancillary information at fine spatial scale, is developed for spatial downscaling. The proposed support vector area-to-area regression kriging (SVATARK) model incorporates support vector regression and area-to-area kriging by considering the nonlinear relationships among variables for various stratifications. SVATARK also considers the change of support problem in the downscaling interpolation process as well as for solving the small sample size in trend prediction. The SVATARK method is evaluated in the Naqu region on the Tibetan Plateau, China to downscale the European Space Agency’s (ESA) 25-km-resolution SSM product. The 1-km-resolution SSM predictions have been produced every 8 days over a six-year period (2010-2015). Compared with other two methods, the downscaled predictions from the SVATARK method performs the best with in-situ observations, resulting in a 23.6 percent reduction in root mean square error and a 10.7 percent increase in correlation coefficient, on average. Additionally, anomalously low SSM values, an indicator of drought, had a record low anomaly in mid-July for 2015, as noted by previous studies, indicating that SVATARK could be utilized for drought monitoring.