Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes using solar-induced fluorescence.

WECANN is a monthly product, at 0.5-degree resolution, starting in 2007. It typically outperforms other global estimates.


Soil Moisture

Our machine learning retrieval CU-NN-AP (Columbia U., Neural Network, Active Passive) of soil moisture based on active and passive microwave measurements (ASCAT and AMSR) is available here:

or via sftp at: (Anonymous)

in folder: /hmt/sirius1/skv0/u/3/p/pg2328/public_html/Website/CU_NN_AP

Description of the retrievals are available in

  1. Kolassa, J., P. Gentine, C. Prigent, and F. Aires. 2016. "Soil moisture retrieval from AMSR-E and ASCAT microwave observation synergy. Part 1: Satellite data analysis." Remote Sensing of Environment 173 1-14 [10.1016/j.rse.2015.11.011]
  2. Kolassa, J., P. Gentine, C. Prigent, F. Aires, and S. Alemohammad. 2017. "Soil moisture retrieval from AMSR-E and ASCAT microwave observation synergy. Part 2: Product evaluation." Remote Sensing of Environment 195 202-217 [10.1016/j.rse.2017.04.020]

The main author is Jana Kolassa (NASA GMAO). Please read the readme file!

The next release will include SMAP and is described here:

  1. Kolassa J., Reichle R.H., Liu Q., Alemohammad S.H, Gentine P., Estimating surface soil moisture from SMAP observations using a Neural Network, Remote Sens Env


Soil mositure NN


Isohydricity Index Based on Vegetation Optical Depth

This dataset represents microwave vegetation optical depth-based calculations of ecosystem scale isohydricity. It is kindly hosted by my colleague Alexandra Konings

Global Change Biology

Reconstructed Solar Induced Fluorescence (RSIF)

A new MODIS-based product of vegetation productivity based on machine learning, with GOME-2 Solar Induced Fluorescence as a training dataset. The data shows very good interannual variability compared to FLUXNET GPP.

The data is available here