Global downscaling of remotely sensed soil moisture using neural networks

Abstract. Characterizing soil moisture at spatiotemporal scales relevant to land surface processes (i.e., of the order of 1 km) is necessary in order to quantify its role in regional feedbacks between the land surface and the atmospheric boundary layer. Moreover, several applications such as agricultural management can benefit from soil moisture information at fine spatial scales. Soil moisture estimates from current satellite missions have a reasonably good temporal revisit over the globe (2–3-day repeat time); however, their finest spatial resolution is 9 km. NASA's Soil Moisture Active Passive (SMAP) satellite has estimated soil moisture at two different spatial scales of 36 and 9 km since April 2015. In this study, we develop a neural-network-based downscaling algorithm using SMAP observations and disaggregate soil moisture to 2.25 km spatial resolution. Our approach uses the mean monthly Normalized Differenced Vegetation Index (NDVI) as ancillary data to quantify the subpixel heterogeneity of soil moisture. Evaluation of the downscaled soil moisture estimates against in situ observations shows that their accuracy is better than or equal to the SMAP 9 km soil moisture estimates.

[1]  Sanjay Ranka,et al.  Utilizing Self-Regularized Regressive Models to Downscale Microwave Brightness Temperatures for Agricultural Land Covers in the SMAPVEX-12 Region , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Marc F. P. Bierkens,et al.  Upscaling and downscaling methods for environmental research , 2000 .

[3]  Filipe Aires,et al.  Toward an estimation of global land surface heat fluxes from multisatellite observations , 2009 .

[4]  Yann Kerr,et al.  Downscaling SMOS-Derived Soil Moisture Using MODIS Visible/Infrared Data , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Dara Entekhabi,et al.  Parameter estimation of coupled water and energy balance models based on stationary constraints of surface states , 2011 .

[6]  Bruce H. Raup,et al.  Correction: Brodzik, M.J., et al. EASE-Grid 2.0: Incremental but Significant Improvements for Earth-Gridded Data Sets. ISPRS International Journal of Geo-Information 2012, 1, 32-45 , 2014, ISPRS Int. J. Geo Inf..

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

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  Mahta Moghaddam,et al.  Soil Moisture Profiles and Temperature Data from SoilSCAPE Sites, USA , 2016 .

[10]  A. Colliandera,et al.  Development and assessment of the SMAP enhanced passive soil moisture product , 2017 .

[11]  Enrique R. Vivoni,et al.  Soil moisture downscaling across climate regions and its emergent properties , 2011 .

[12]  D. Entekhabi,et al.  The global distribution and dynamics of surface soil moisture , 2017 .

[13]  Thomas J. Jackson,et al.  A First-Order Radiative Transfer Model for Microwave Radiometry of Forest Canopies at L-Band , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Irena Hajnsek,et al.  Investigation of SMAP Fusion Algorithms With Airborne Active and Passive L-Band Microwave Remote Sensing , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[15]  T. Schmugge,et al.  Vegetation effects on the microwave emission of soils , 1991 .

[16]  Pierre Gentine,et al.  Evaluation of a simple approach for crop evapotranspiration partitioning and analysis of the water budget distribution for several crop species , 2013 .

[17]  Simon Yueh,et al.  Resolution enhancement of SMAP radiometer data using the Backus Gilbert optimum interpolation technique , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[18]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[19]  Philippe Richaume,et al.  SMOS near-real-time soil moisture product: processor overview and first validation results , 2017 .

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

[21]  Thomas J. Jackson,et al.  Observations of soil moisture using a passive and active low-frequency microwave airborne sensor during SGP99 , 2002, IEEE Trans. Geosci. Remote. Sens..

[22]  Edward J. Kim,et al.  The NAFE'06 data set: towards soil moisture retrieval at intermediate resolution , 2008 .

[23]  Günter Blöschl,et al.  On the spatial scaling of soil moisture , 1999 .

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

[25]  Jeffrey P. Walker,et al.  Towards deterministic downscaling of SMOS soil moisture using MODIS derived soil evaporative efficiency , 2008 .

[26]  Yann Kerr,et al.  Assessment of the SMAP Passive Soil Moisture Product , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Peter M. Cox,et al.  The Sensitivity of Global Climate Model Simulations to the Representation of Soil Moisture Heterogeneity , 2003 .

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

[29]  C. Körner,et al.  Soil moisture effects determine CO2 responses of grassland species , 2000, Oecologia.

[30]  Irena Hajnsek,et al.  Physically-based active-passive modelling and retrieval for SMAP soil moisture inversion algorithm , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

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

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

[33]  T. Jackson,et al.  Field observations of soil moisture variability across scales , 2008 .

[34]  Dara Entekhabi,et al.  Equivalent steady soil moisture profile and the time compression approximation in water balance modeling , 1994 .

[35]  I. Rodríguez‐Iturbe,et al.  Ecohydrology of Water-Controlled Ecosystems: Soil Moisture and Plant Dynamics , 2005 .

[36]  F. Aires,et al.  A global dynamic long-term inundation extent dataset at high spatial resolution derived through downscaling of satellite observations , 2017 .

[37]  Naftali Lazarovitch,et al.  A review of approaches for evapotranspiration partitioning , 2014 .

[38]  F. Aires,et al.  A joint analysis of modeled soil moisture fields and satellite observations , 2013 .

[39]  Stephen P. Good,et al.  Global synthesis of vegetation control on evapotranspiration partitioning , 2014 .

[40]  Sidharth Misra,et al.  Spatial Downscaling of SMAP Soil Moisture Using MODIS Land Surface Temperature and NDVI During SMAPVEX15 , 2017, IEEE Geoscience and Remote Sensing Letters.

[41]  Guido Daniel Salvucci,et al.  An approximate solution for steady vertical flux of moisture through an unsaturated homogeneous soil , 1993 .

[42]  Adriano Camps,et al.  A Downscaling Approach for SMOS Land Observations: Evaluation of High-Resolution Soil Moisture Maps Over the Iberian Peninsula , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[43]  J. L. Hatfield.  Upscaling and Downscaling Methods for Environmental Research , 2001 .

[44]  Ahmad Al Bitar,et al.  A sequential model for disaggregating near-surface soil moisture observations using multi-resolution thermal sensors , 2009 .

[45]  John Kochendorfer,et al.  U.S. Climate Reference Network Soil Moisture and Temperature Observations , 2013 .

[46]  Alon Ben-Gal,et al.  A review of approaches for evapotranspiration partitioning , 2013 .

[47]  Yann Kerr,et al.  A downscaling method for distributing surface soil moisture within a microwave pixel: Application to the Monsoon '90 data , 2006 .

[48]  Pierre Gentine,et al.  Impact of Soil Moisture–Atmosphere Interactions on Surface Temperature Distribution , 2013 .

[49]  Massimo Menenti,et al.  S-SEBI: A simple remote sensing algorithm to estimate the surface energy balance , 2000 .

[50]  Dara Entekhabi,et al.  The Diurnal Behavior of Evaporative Fraction in the Soil-Vegetation-Atmospheric Boundary Layer Continuum , 2011 .

[51]  Bruce H. Raup,et al.  EASE-Grid 2.0: Incremental but Significant Improvements for Earth-Gridded Data Sets , 2012, ISPRS Int. J. Geo Inf..

[52]  Filipe Aires,et al.  Soil moisture retrieval from multi‐instrument observations: Information content analysis and retrieval methodology , 2013 .

[53]  Philippe Richaume,et al.  Soil Moisture Retrieval Using Neural Networks: Application to SMOS , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[54]  Filipe Aires,et al.  Soil moisture retrieval from AMSR-E and ASCAT microwave observation synergy. Part 2: Product evaluation , 2017 .

[55]  Dara Entekhabi,et al.  Analysis of evaporative fraction diurnal behaviour , 2007 .

[56]  Binayak P. Mohanty,et al.  Development of a deterministic downscaling algorithm for remote sensing soil moisture footprint using soil and vegetation classifications , 2013 .

[57]  Matthew F. McCabe,et al.  Scaling characteristics of spatial patterns of soil moisture from distributed modelling , 2007 .

[58]  Dawei Han,et al.  Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application , 2013, Water Resources Management.

[59]  C. Prigent,et al.  Synergistic multi‐wavelength remote sensing versus a posteriori combination of retrieved products: Application for the retrieval of atmospheric profiles using MetOp‐A , 2012 .

[60]  Mingyan Liu,et al.  A Wireless Soil Moisture Smart Sensor Web Using Physics-Based Optimal Control: Concept and Initial Demonstrations , 2010, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[61]  Murugesu Sivapalan,et al.  Scale issues in hydrological modelling , 1995 .

[62]  Christoph Rüdiger,et al.  Intercomparison of Alternate Soil Moisture Downscaling Algorithms Using Active–Passive Microwave Observations , 2017, IEEE Geoscience and Remote Sensing Letters.

[63]  Dara Entekhabi,et al.  An Algorithm for Merging SMAP Radiometer and Radar Data for High-Resolution Soil-Moisture Retrieval , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[64]  Sanjay Ranka,et al.  Disaggregation of Remotely Sensed Soil Moisture in Heterogeneous Landscapes Using Holistic Structure-Based Models , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[65]  T. Jackson,et al.  Estimating surface soil moisture from SMAP observations using a Neural Network technique. , 2018, Remote sensing of environment.

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

[67]  Murugesu Sivapalan,et al.  Scale issues in hydrological modelling: A review , 1995 .

[68]  Lifeng Luo,et al.  Contribution of land surface initialization to subseasonal forecast skill: First results from a multi‐model experiment , 2010 .

[69]  Jean-Christophe Calvet,et al.  In situ soil moisture observations for the CAL/VAL of SMOS: the SMOSMANIA network , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[70]  Binayak P. Mohanty,et al.  An unmixing algorithm for remotely sensed soil moisture , 2013 .

[71]  David J. Harding,et al.  Amazon forests maintain consistent canopy structure and greenness during the dry season , 2014, Nature.

[72]  F. Aires,et al.  Soil moisture retrieval from AMSR-E and ASCAT microwave observation synergy. Part 1: Satellite data analysis , 2016 .

[73]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[74]  Yann Kerr,et al.  A Simple Method to Disaggregate Passive Microwave-Based Soil Moisture , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[75]  Adriano Camps,et al.  A Change Detection Algorithm for Retrieving High-Resolution Soil Moisture From SMAP Radar and Radiometer Observations , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[76]  Thomas J. Jackson,et al.  Active–Passive Soil Moisture Retrievals During the SMAP Validation Experiment 2012 , 2016, IEEE Geoscience and Remote Sensing Letters.

[77]  Hubert H. G. Savenije,et al.  The effect of spatial throughfall patterns on soil moisture patterns at the hillslope scale , 2012 .

[78]  Ahmad Al Bitar,et al.  Self-calibrated evaporation-based disaggregation of SMOS soil moisture: An evaluation study at 3 km and 100 m resolution in Catalunya, Spain , 2013 .

[79]  Simon Dadson,et al.  High-resolution global topographic index values for use in large-scale hydrological modelling. , 2015 .

[80]  Niko E. C. Verhoest,et al.  A review of spatial downscaling of satellite remotely sensed soil moisture , 2017 .

[81]  T. Jackson,et al.  III. Measuring surface soil moisture using passive microwave remote sensing , 1993 .

[82]  Irena Hajnsek,et al.  A Network of Terrestrial Environmental Observatories in Germany , 2011 .

[83]  Scott M. Devine,et al.  Soil moisture depletion under simulated drought in the Amazon: impacts on deep root uptake. , 2010, The New phytologist.

[84]  Yann Kerr,et al.  A combined modeling and multispectral/multiresolution remote sensing approach for disaggregation of surface soil moisture: application to SMOS configuration , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[85]  Thomas Jagdhuber,et al.  Physically-based retrieval of SMAP active-passive measurements covariation and vegetation structure parameters , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[86]  刘鹄,et al.  “Ecohydrology of Water-controlled Ecosystems—Soil Moisture and Plant Dynamics”评介 , 2006 .

[87]  Ahmad Al Bitar,et al.  Copula-Based Downscaling of Coarse-Scale Soil Moisture Observations With Implicit Bias Correction , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[88]  C. Albergel,et al.  From near-surface to root-zone soil moisture using an exponential filter: an assessment of the method based on in-situ observations and model simulations , 2008 .

[89]  Filipe Aires,et al.  Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence. , 2017, Biogeosciences.

[90]  Filipe Aires,et al.  Statistical retrieval of surface and root zone soil moisture using synergy of multi-frequency remotely-sensed observations , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).