Evaluations of Machine Learning-Based CYGNSS Soil Moisture Estimates against SMAP Observations

This paper presents a machine learning (ML) framework to derive a quasi-global soil moisture (SM) product by direct use of the Cyclone Global Navigation Satellite System (CYGNSS)’s high spatio-temporal resolution observations over the tropics (within ±38° latitudes) at L-band. The learning model is trained by using in-situ SM data from the International Soil Moisture Network (ISMN) sites and various space-borne ancillary data. The approach produces daily SM retrievals that are gridded to 3 km and 9 km within the CYGNSS spatial coverage. The performance of the model is independently evaluated at various temporal scales (daily, 3-day, weekly, and monthly) against Soil Moisture Active Passive (SMAP) mission’s enhanced SM products at a resolution of 9 km × 9 km. The mean unbiased root-mean-square difference (ubRMSD) between concurrent (same calendar day) CYGNSS and SMAP SM retrievals for about three years (from 2017 to 2019) is 0.044 cm3 cm−3 with a correlation coefficient of 0.66 over SMAP recommended grids. The performance gradually improves with temporal averaging and degrades over regions regularly flagged by SMAP such as dense forest, high topography, and coastlines. Furthermore, CYGNSS and SMAP retrievals are evaluated against 170 ISMN in-situ observations that result in mean unbiased root-mean-square errors (ubRMSE) of 0.055 cm3 cm−3 and 0.054 cm3 cm−3, respectively, and a higher correlation coefficient with CYGNSS retrievals. It is important to note that the proposed approach is trained over limited in-situ observations and is independent of SMAP observations in its training. The retrieval performance indicates current applicability and future growth potential of GNSS-R-based, directly measured spaceborne SM products that can provide improved spatio-temporal resolution than currently available datasets.

[1]  Nick van de Giesen,et al.  Mapping Surface Heat Fluxes by Assimilating SMAP Soil Moisture and GOES Land Surface Temperature Data , 2017 .

[2]  Yann Kerr,et al.  Development and Assessment of the SMAP Enhanced Passive Soil Moisture Product. , 2018, Remote sensing of environment.

[3]  Pia Addabbo,et al.  Simulation of TechDemoSat-1 Delay-Doppler Maps for GPS Ocean Reflectometry , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[4]  Nazzareno Pierdicca,et al.  Monitoring Freeze-Thaw State by Means of GNSS Reflectometry: An Analysis of TechDemoSat-1 Data , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Weiqiang Li,et al.  Feasibility of GNSS-R Ice Sheet Altimetry in Greenland Using TDS-1 , 2017, Remote. Sens..

[6]  A. Robock,et al.  The International Soil Moisture Network: a data hosting facility for global in situ soil moisture measurements , 2011 .

[7]  Wouter Dorigo,et al.  Characterizing Coarse‐Scale Representativeness of in situ Soil Moisture Measurements from the International Soil Moisture Network , 2013 .

[8]  Fabio Castelli,et al.  Mutual interaction of soil moisture state and atmospheric processes , 1996 .

[9]  Eric E. Small,et al.  Description of the UCAR/CU Soil Moisture Product , 2020, Remote. Sens..

[10]  Jean-Pierre Wigneron,et al.  Potential Applications of GNSS-R Observations over Agricultural Areas: Results from the GLORI Airborne Campaign , 2018, Remote. Sens..

[11]  Rashmi Shah,et al.  Demonstrating soil moisture remote sensing with observations from the UK TechDemoSat‐1 satellite mission , 2016 .

[12]  S. Seneviratne,et al.  Recent decline in the global land evapotranspiration trend due to limited moisture supply , 2010, Nature.

[13]  Jean-Pierre Wigneron,et al.  Performance of GNSS-R GLORI data for biomass estimation over the Landes forest , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[14]  Venkat Lakshmi,et al.  Use of Cyclone Global Navigation Satellite System (CyGNSS) Observations for Estimation of Soil Moisture , 2018, Geophysical Research Letters.

[15]  S. Seneviratne,et al.  Investigating soil moisture-climate interactions in a changing climate: A review , 2010 .

[16]  Joel T. Johnson,et al.  Time-Series Retrieval of Soil Moisture Using CYGNSS , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Shuanggen Jin,et al.  Pan-tropical soil moisture mapping based on a three-layer model from CYGNSS GNSS-R data , 2020 .

[18]  Huadong Guo,et al.  Linking observation, modelling and satellite-based estimation of global land evapotranspiration , 2020 .

[19]  Eric E. Small,et al.  Soil Moisture Sensing Using Spaceborne GNSS Reflections: Comparison of CYGNSS Reflectivity to SMAP Soil Moisture , 2018 .

[20]  Jiancheng Shi,et al.  The Soil Moisture Active Passive (SMAP) Mission , 2010, Proceedings of the IEEE.

[21]  Philip Jales,et al.  Spaceborne GNSS-Reflectometry on TechDemoSat-1: Early Mission Operations and Exploitation , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  Kelly K. Caylor,et al.  Validation of SMAP surface soil moisture products with core validation sites , 2017, Remote Sensing of Environment.

[23]  Marvin N. Wright,et al.  SoilGrids250m: Global gridded soil information based on machine learning , 2017, PloS one.

[24]  J. Pekel,et al.  High-resolution mapping of global surface water and its long-term changes , 2016, Nature.

[25]  Adriano Camps,et al.  Tutorial on Remote Sensing Using GNSS Bistatic Radar of Opportunity , 2014, IEEE Geoscience and Remote Sensing Magazine.

[26]  Rajeswari Balasubramaniam,et al.  A New Paradigm in Earth Environmental Monitoring with the CYGNSS Small Satellite Constellation , 2018, Scientific Reports.

[27]  Matthias Drusch,et al.  Global Automated Quality Control of In Situ Soil Moisture Data from the International Soil Moisture Network , 2013 .

[28]  W. Wagner,et al.  Soil as a natural rain gauge: Estimating global rainfall from satellite soil moisture data , 2014 .

[29]  Ali Cafer Gürbüz,et al.  Machine Learning-Based CYGNSS Soil Moisture Estimates over ISMN sites in CONUS , 2020, Remote. Sens..

[30]  Ali Cafer Gürbüz,et al.  High Spatio-Temporal Resolution CYGNSS Soil Moisture Estimates Using Artificial Neural Networks , 2019, Remote. Sens..

[31]  Karl Schneider,et al.  Patterns and scaling properties of surface soil moisture in an agricultural landscape: An ecohydrological modeling study , 2013 .

[32]  Bo Zhang,et al.  Waveform-based spaceborne GNSS-R wind speed observation: Demonstration and analysis using UK TechDemoSat-1 data , 2018 .

[33]  M. Martín-Neira A pasive reflectometry and interferometry system (PARIS) application to ocean altimetry , 1993 .

[34]  Arnaud Mialon,et al.  SMOS-IC: An Alternative SMOS Soil Moisture and Vegetation Optical Depth Product , 2017, Remote. Sens..

[35]  Weiqiang Li,et al.  Measuring Greenland Ice Sheet Melt Using Spaceborne GNSS Reflectometry From TechDemoSat‐1 , 2020, Geophysical Research Letters.

[36]  Nazzareno Pierdicca,et al.  Analysis of CYGNSS Data for Soil Moisture Retrieval , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[37]  Yann Kerr,et al.  The SMOS Mission: New Tool for Monitoring Key Elements ofthe Global Water Cycle , 2010, Proceedings of the IEEE.

[38]  Nereida Rodriguez-Alvarez,et al.  Classifying Inundation in a Tropical Wetlands Complex with GNSS-R , 2019, Remote. Sens..

[39]  Hyuk Park,et al.  Sensitivity of GNSS-R Spaceborne Observations to Soil Moisture and Vegetation , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[40]  Zhigang Sun,et al.  Comprehensive Evaluation of Using TechDemoSat-1 and CYGNSS Data to Estimate Soil Moisture over Mainland China , 2020, Remote. Sens..