Preprints
https://doi.org/10.5194/hess-2022-76
https://doi.org/10.5194/hess-2022-76
 
04 Mar 2022
04 Mar 2022
Status: a revised version of this preprint is currently under review for the journal HESS.

A robust gap-filling approach for ESA CCI soil moisture by integrating satellite observations, model-driven knowledge and spatiotemporal machine learning

Kai Liu1, Xueke Li2, Shudong Wang1, and Hongyan Zhang1 Kai Liu et al.
  • 1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
  • 2Institute at Brown for Environment and Society, Brown University, Providence, RI, 02912, USA

Abstract. Soil moisture (SM) is a critical component of the water cycle and a key ecological process connecting the soil-vegetation-atmosphere system. Spatiotemporally continuous SM is increasingly demanded for ecological and hydrological research fields. Satellite remote sensing has opened opportunities for mapping SM. Nevertheless, the continuity of SM imagery is hampered by data gaps resulting from inadequate satellite coverage and radio frequency interference. In light of this, we propose a new gap-filling approach to reconstruct daily SM time series using the European Space Agency’s Climate Change Initiative (ESA CCI). The developed approach integrates satellite observations, model-driven knowledge and machine learning algorithm that leverages both spatial and temporal domains. Taking SM in China as an example, we show high accuracy of the reconstructed SM when validated with multiple sets of in situ measurements, with a root mean square error (RMSE) and mean absolute error (MAE) of 0.09–0.14 and 0.07–0.13 cm3/cm3, respectively. Further evaluation with a 10 fold cross validation reveals a median value of the coefficient of determination (R2), RMSE, and MAE of 0.56, 0.025 cm3/cm3 and 0.019 cm3/cm3, respectively. The reconstructive performance is noticeably reduced when excluding an explanatory variable while the rest remains unchanged, as well as when removing the spatiotemporal domain strategy and the residual calibration procedure, respectively. Compared to that using satellite-derived diurnal temperature range (DTR), reconstructed SMs using bias-corrected model-derived DTRs exhibit acceptable accuracies and higher spatial coverage. Applying our gap-filling approach to long-term SM data sets (2005–2015), we show a promising result with a R2 of 0.72. A more accurate trend is achieved relative to that of the original CCI SM when assessed with in situ measurements (0.45 versus 0.23 in terms of R2). Our findings indicate the feasibility of integrating satellite observations, model-driven knowledge, and spatiotemporal machine learning for filling gaps in SM time series over short and long time scales, providing a potential avenue for applications to similar studies.

Kai Liu et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-76', Anonymous Referee #1, 21 Apr 2022
    • AC1: 'Reply on RC1', kai Liu, 07 Jul 2022
  • RC2: 'Comment on hess-2022-76', Anonymous Referee #2, 22 Jun 2022
    • AC2: 'Reply on RC2', kai Liu, 07 Jul 2022

Kai Liu et al.

Viewed

Total article views: 739 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
592 130 17 739 39 6 7
  • HTML: 592
  • PDF: 130
  • XML: 17
  • Total: 739
  • Supplement: 39
  • BibTeX: 6
  • EndNote: 7
Views and downloads (calculated since 04 Mar 2022)
Cumulative views and downloads (calculated since 04 Mar 2022)

Viewed (geographical distribution)

Total article views: 695 (including HTML, PDF, and XML) Thereof 695 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 16 Sep 2022
Download
Short summary
Remote sensing has opened opportunities for mapping spatiotemporally continuous soil moisture, but it is hampered by data gaps. We propose a robust gap-filling approach to reconstruct daily satellite soil moisture. The merit of our approach is to integrate satellite observations, model-driven knowledge and spatiotemporal machine learning. We also apply the developed approach to long-term datasets. Our study provides a potential avenue for hydrological applications.