Water Resources Management

, Volume 27, Issue 8, pp 3127–3144 | Cite as

Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application

  • Prashant K. Srivastava
  • Dawei Han
  • Miguel Rico Ramirez
  • Tanvir Islam


Many hydrologic phenomena and applications such as drought, flood, irrigation management and scheduling needs high resolution satellite soil moisture data at a local/regional scale. Downscaling is a very important process to convert a coarse domain satellite data to a finer spatial resolution. Three artificial intelligence techniques along with the generalized linear model (GLM) are used to improve the spatial resolution of Soil Moisture and Ocean Salinity (SMOS) derived soil moisture, which is currently available at a very coarse scale of ~40 Km. Artificial neural network (ANN), support vector machine, relevance vector machine and generalized linear models are chosen for this study to integrate the Moderate Resolution Imaging Spectroradiometer (MODIS) Land Surface Temperature (LST) with the SMOS derived soil moisture. Soil moisture deficit (SMD) derived from a hydrological model called PDM (Probability Distribution Model) is used for the downscaling performance evaluation. The statistical evaluation has also been made with the day-time and night-time MODIS LST differences with the mean day and night-time PDM SMD data for the selection of effective MODIS products. The accuracy and robustness of all the downscaling algorithms are discussed in terms of their assumptions and applicability. The statistical performance indices such as R 2 , %Bias and RMSE indicates that the ANN (R 2 = 0.751, %Bias = −0.628 and RMSE = 0.011), RVM (R 2 = 0.691, %Bias = 1.009 and RMSE = 0.013), SVM (R 2 = 0.698, %Bias = 2.370 and RMSE = 0.013) and GLM (R 2 = 0.698, %Bias = 1.009 and RMSE = 0.013) algorithms on the whole are relatively more skillful to downscale the variability of the soil moisture in comparison to the non-downscaled data (R 2 = 0.418 and RMSE = 0.017) with the outperformance of ANN algorithm. The other attempts related to growing and non-growing seasons have been used in this study to reveal that season based downscaling is even better than continuous time series with fairly high performance statistics.


Soil moisture SMOS Soil moisture deficit Artificial intelligence Support vector machine Relevance vector machine Artificial neural network Generalized linear models 



The authors would like to thank the Commonwealth Scholarship Commission, British Council, United Kingdom and Ministry of Human Resource Development, Government of India for providing the necessary support and funding for this research. The authors are highly thankful to the European Space Agency for providing the SMOS data. The authors would like to acknowledge the British Atmospheric Data Centre, United Kingdom for providing the ground observation datasets. The authors also acknowledge the Advanced Computing Research Centre at University of Bristol for providing the access to supercomputer facility (The Blue Crystal).


  1. Al-Shrafany D, Rico-Ramirez M, Han D (2012a) Calibration of roughness parameters using rainfall runoff water balance for satellite soil moisture retrieval. J Hydrol Eng 17:704–714. doi: 10.1061/(ASCE)HE.1943-5584.0000508 CrossRefGoogle Scholar
  2. Al-Shrafany D, Rico-Ramirez M, Han D, Bray M (2012b) Comparative assessment of soil moisture estimation from land surface model and satellite remote sensing based on catchment water balance. Met Apps. doi: 10.1002/met.1357
  3. Anderson JA, Davis J (1995) An introduction to neural networks, vol 1. MIT Press, Cambridge, MAGoogle Scholar
  4. Bishop CM, Tipping ME (2000) Variational relevance vector machines. Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence. Morgan Kaufmann Publishers IncGoogle Scholar
  5. Caputo B, Sim K, Furesjo F, Smola A (2002) Appearance-based Object Recognition using SVMs: which Kernel Should I Use?. In Proc of NIPS workshop on Statistical methods for computational experiments in visual processing and computer vision, Whistler (Vol. 2002)Google Scholar
  6. Carlson T (2007) An overview of the“ triangle method” for estimating surface evapotranspiration and soil moisture from satellite imagery. Sensors 7(8):1612–1629CrossRefGoogle Scholar
  7. Foody G (2008) RVM–based multi–class classification of remotely sensed data. Int J Remote Sens 29(6):1817–1823CrossRefGoogle Scholar
  8. Gao J (2008) Digital analysis of remotely sensed imagery. McGraw-Hill ProfessionalGoogle Scholar
  9. Ghosh S, Mujumdar P (2008) Statistical downscaling of GCM simulations to streamflow using relevance vector machine. Adv Water Resour 31(1):132–146CrossRefGoogle Scholar
  10. Goward SN, Xue Y, Czajkowski KP (2002) Evaluating land surface moisture conditions from the remotely sensed temperature/vegetation index measurements: an exploration with the simplified simple biosphere model. Remote Sens Environ 79(2):225–242CrossRefGoogle Scholar
  11. Han D, Cluckie I (2004) Support vector machines identification for runoff modeling. In: pp 21–24Google Scholar
  12. Han D, Yang Z (2001) River flow modelling using support vector machines. In: pp 494–499Google Scholar
  13. Han D, Kwong T, Li S (2007) Uncertainties in real–time flood forecasting with neural networks. Hydrol Process 21(2):223–228CrossRefGoogle Scholar
  14. Ishak A, Remesan R, Srivastava P, Islam T, Han D (2013) Error correction modelling of wind speed through hydro-meteorological parameters and mesoscale model: a hybrid approach. Water Resour Manag 27(1):1–23. doi: 10.1007/s11269-012-0130-1 CrossRefGoogle Scholar
  15. Islam T, Rico-Ramirez MA, Han D, Srivastava PK (2012) Artificial intelligence techniques for clutter identification with polarimetric radar signatures. Atmos Res 109–110:95–113. doi: 10.1016/j.atmosres.2012.02.007 CrossRefGoogle Scholar
  16. Jackson TJ (1993) III. Measuring surface soil moisture using passive microwave remote sensing. Hydrol Process 7(2):139–152CrossRefGoogle Scholar
  17. Johnson RA, Wichern DW (2002) Applied multivariate statistical analysis, vol 4. Prentice Hall, Upper Saddle RiverGoogle Scholar
  18. Karatzoglou A, Smola A, Hornik K, Zeileis A (2005) Kernlab–kernel methods. R package, Version 0.6-2.
  19. Kerr YH, Waldteufel P, Wigneron JP, Martinuzzi J, Font J, Berger M (2001) Soil moisture retrieval from space: the Soil Moisture and Ocean Salinity (SMOS) mission. IEEE Trans Geosci Rem Sens 39(8):1729–1735CrossRefGoogle Scholar
  20. Kerr Y, Waldteufel P, Richaume P, Davenport I, Ferrazzoli P, Wigneron J (2006) SMOS level 2 processor soil moisture algorithm theoretical basis document (ATBD). SM-ESL (CBSA), CESBIO, Toulouse, SO-TN-ESL-SM-GS-0001, V5 a, 15/03Google Scholar
  21. Kerr YH, Waldteufel P, Richaume P, Wigneron JP, Ferrazzoli P, Mahmoodi A, Al Bitar A, Cabot F, Gruhier C, Juglea SE (2012) The SMOS soil moisture retrieval algorithm. IEEE Trans Geosci Rem Sens 50(5):1384–1403CrossRefGoogle Scholar
  22. Legates DR, Mahmood R, Levia DF, DeLiberty TL, Quiring SM, Houser C, Nelson FE (2011) Soil moisture: a central and unifying theme in physical geography. Prog Phys Geogr 35(1):65–86CrossRefGoogle Scholar
  23. Lindsey JK (1997) Applying generalized linear models. Springer Verlag, New YorkGoogle Scholar
  24. Liu J, Han D (2010) Indices for calibration data selection of the rainfall-runoff model. Water Resour Res 46(4):W04512Google Scholar
  25. Mallick K, Bhattacharya BK, Patel N (2009) Estimating volumetric surface moisture content for cropped soils using a soil wetness index based on surface temperature and NDVI. Agric For Meteorol 149(8):1327–1342CrossRefGoogle Scholar
  26. McCullagh P, Nelder JA (1989) Generalized linear models. Chapman & Hall/CRCGoogle Scholar
  27. Merlin O, Walker JP, Chehbouni A, Kerr Y (2008) Towards deterministic downscaling of SMOS soil moisture using MODIS derived soil evaporative efficiency. Remote Sens Environ 112(10):3935–3946CrossRefGoogle Scholar
  28. Mladenova I, Lakshmi V, Jackson TJ, Walker JP, Merlin O, de Jeu RAM (2011) Validation of AMSR-E soil moisture using L-band airborne radiometer data from National Airborne Field Experiment 2006. Rem Sens Environ 115(8):2096–2103Google Scholar
  29. Moody J, Hanson S, Krogh A, Hertz JA (1995) A simple weight decay can improve generalization. Adv Neural Inform Process Syst 4:950–957Google Scholar
  30. Moore R (2007) The PDM rainfall-runoff model. Hydrol Earth Syst Sci 11(1):483–499CrossRefGoogle Scholar
  31. Panciera R, Walker JP, Kalma JD, Kim EJ, Hacker JM, Merlin O, Berger M, Skou N (2008) The NAFE’05/CoSMOS data set: toward SMOS soil moisture retrieval, downscaling, and assimilation. IEEE Trans Geosci Rem Sens 46(3):736–745CrossRefGoogle Scholar
  32. Piles M, Camps A, Vall-Llossera M, Corbella I, Panciera R, Rudiger C, Kerr YH, Walker J (2011) Downscaling SMOS-derived soil moisture using MODIS visible/infrared data. IEEE Trans Geosci Rem Sens 49(9):3156–3166CrossRefGoogle Scholar
  33. Pinori S, Crapolicchio R, Mecklenburg S (2008) Preparing the ESA-SMOS (Soil Moisture and Ocean Salinity) mission-Overview of the user data products and data distribution strategy. Microwave Radiometry and Remote Sensing of the Environment, 2008. MICRORAD 2008. IEEEGoogle Scholar
  34. RDevelopment C (2010) TEAM. 2006. R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0, URL
  35. Remesan R, Shamim MA, Han D, Mathew J (2009) Runoff prediction using an integrated hybrid modelling scheme. J Hydrol 372(1–4):48–60CrossRefGoogle Scholar
  36. Ridler ME, Sandholt I, Butts M, Lerer S, Mougin E, Timouk F, Kergoat L, Madsen H (2012) Calibrating a soil–vegetation–atmosphere transfer model with remote sensing estimates of surface temperature and soil surface moisture in a semi arid environment. J Hydrol 436–437:1–12Google Scholar
  37. Ripley B (2009) Feed-forward neural networks and multinomial log-linear models. R-packageGoogle Scholar
  38. Sandholt I, Rasmussen K, Andersen J (2002) A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status. Remote Sens Environ 79(2):213–224CrossRefGoogle Scholar
  39. Schoof JT, Pryor S (2001) Downscaling temperature and precipitation: a comparison of regression–based methods and artificial neural networks. Int J Climatol 21(7):773–790CrossRefGoogle Scholar
  40. Sivapragasam C, Muttil N (2005) Discharge rating curve extension–a new approach. Water Resour Manag 19(5):505–520CrossRefGoogle Scholar
  41. Srivastava PK, Han D, Rico-Ramirez MA (2012a) Assessment of SMOS satellite derived soil moisture for soil moisture deficit stimation. Symposium on Prediction in Ungauged basin (PUBS) co-organized by Delft University of Technology, Delft, Netherlands and International Association of Hydrological Sciences (IAHS) dated 22–25 October 2012:1Google Scholar
  42. Srivastava PK, Han D, Rico-Ramirez MA, Bray M, Islam T (2012b) Selection of classification techniques for land use/land cover change investigation. Adv Space Res 50(9):1250–1265. doi: 10.1016/j.asr.2012.06.032 CrossRefGoogle Scholar
  43. Srivastava PK, Han D, Rico-Ramirez MA (2013a) Data fusion techniques for an improved soil moisture retrieval using SMOS and WRF-NOAH Land surface model SMOS land application workshop, ESA-ESRIN, Frascati, Italy 25–27 February 2013Google Scholar
  44. Srivastava PK, Han D, Rico-Ramirez MA, Islam T (2013b) Comparative assessment of evapotranspiration derived from NCEP and ECMWF global datasets through Weather Research and Forecasting model. Atmos Sci Lett. doi: 10.1002/asl.427 Google Scholar
  45. Thakur J, Srivastava PK, Singh SK, Vekerdy Z (2012) Ecological monitoring of wetlands in semi-arid region of Konya closed Basin, Turkey. Reg Environ Chang 12(1):133–144. doi: 10.1007/s10113-011-0241-x CrossRefGoogle Scholar
  46. Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244Google Scholar
  47. Trigo RM, Palutikof JP (2001) Precipitation scenarios over Iberia: a comparison between direct GCM output and different downscaling techniques. J Clim 14(23):4422–4446CrossRefGoogle Scholar
  48. Vapnik V, Golowich SE, Smola A (1997) Support vector method for function approximation, regression estimation, and signal processing. Adv Neural Inform Process Syst 9:281–287Google Scholar
  49. Wagner W, Naeimi V, Scipal K, de Jeu R, Martínez-Fernández J (2007) Soil moisture from operational meteorological satellites. Hydrogeol J 15(1):121–131CrossRefGoogle Scholar
  50. Wan Z (1999) MODIS land-surface temperature algorithm theoretical basis document (LST ATBD). Institute for Computational Earth System Science, Santa Barbara, 75Google Scholar
  51. Wang YM, Traore S, Kerh T, Leu JM (2011) Modelling reference evapotranspiration using feed forward backpropagation algorithm in arid regions of Africa. Irrig Drain 60(3):404–417CrossRefGoogle Scholar
  52. Weichert A, Bürger G (1998) Linear versus nonlinear techniques in downscaling. Clim Res 10:83–93CrossRefGoogle Scholar
  53. Wu C, Chau K (2011) Rainfall-runoff modeling using artificial neural network coupled with singular spectrum analysis. J Hydrol 399(3):394–409Google Scholar
  54. Zhang Y, Ding X, Liu Y, Griffin P (1996) An artificial neural network approach to transformer fault diagnosis. IEEE Trans Power Deliv 11(4):1836–1841CrossRefGoogle Scholar
  55. Zhang G, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Prashant K. Srivastava
    • 1
  • Dawei Han
    • 1
  • Miguel Rico Ramirez
    • 1
  • Tanvir Islam
    • 1
  1. 1.Water and Environment Management Research Centre, Department of Civil EngineeringUniversity of BristolBristolUK

Personalised recommendations