Journal cover Journal topic
Hydrology and Earth System Sciences An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/hess-2017-680
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Research article
08 Feb 2018
Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Hydrology and Earth System Sciences (HESS).
Global Downscaling of Remotely-Sensed Soil Moisture using Neural Networks
Seyed Hamed Alemohammad1,2, Jana Kolassa3,4, Catherine Prigent1,2,5, Filipe Aires1,2,5, and Pierre Gentine1,2,6 1Department of Earth and Environmental Engineering, Columbia University
2Columbia Water Center, Columbia University
3Universities Space Research Association, Columbia, MD
4Global Modelling and Assimilation Office, NASA Goddard Space Flight Center, Greenbelt, MD
5Observatoire de Paris
6Earth Institute, Columbia University
Abstract. Characterizing soil moisture at spatio-temporal scales relevant to land surface processes (i.e. of the order of a kilometer) is necessary in order to quantify its role in regional feedbacks between 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 days repeat time); however, their finest spatial resolution is 9 km. NASA's Soil Moisture Active Passive (SMAP) satellite estimates soil moisture at two different spatial scales of 36 km and 9 km since April 2015. In this study, we develop a neural networks-based downscaling algorithm using SMAP observations and disaggregate soil moisture to 2.25 km spatial resolution. Our approach uses mean monthly Normalized Differenced Vegetation Index (NDVI) as an ancillary data to quantify sub-pixel 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.
Citation: Alemohammad, S. H., Kolassa, J., Prigent, C., Aires, F., and Gentine, P.: Global Downscaling of Remotely-Sensed Soil Moisture using Neural Networks, Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2017-680, in review, 2018.
Seyed Hamed Alemohammad et al.
Seyed Hamed Alemohammad et al.
Seyed Hamed Alemohammad et al.

Viewed

Total article views: 526 (including HTML, PDF, and XML)

HTML PDF XML Total Supplement BibTeX EndNote
412 105 9 526 18 8 15

Views and downloads (calculated since 08 Feb 2018)

Cumulative views and downloads (calculated since 08 Feb 2018)

Viewed (geographical distribution)

Total article views: 477 (including HTML, PDF, and XML)

Thereof 474 with geography defined and 3 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 20 May 2018
Publications Copernicus
Download
Short summary
A new machine learning algorithm is developed to downscale satellite based soil moisture estimates from their native spatial scale of 9 km to 2.25 km.
A new machine learning algorithm is developed to downscale satellite based soil moisture...
Share