Integrating process-related information into an artificial  neural network for root-zone soil moisture prediction

Souissi, Roiya; Zribi, Mehrez; Corbari, Chiara; Mancini, Marco; Muddu, Sekhar; Tomer, Sat Kumar; Upadhyaya, Deepti B.; Al Bitar, Ahmad

doi:https://doi.org/10.5194/hess-26-3263-2022

Articles | Volume 26, issue 12

https://doi.org/10.5194/hess-26-3263-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-26-3263-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 26, issue 12

Research article

|

28 Jun 2022

Research article |

| 28 Jun 2022

Integrating process-related information into an artificial neural network for root-zone soil moisture prediction

Roiya Souissi, Mehrez Zribi, Chiara Corbari, Marco Mancini, Sekhar Muddu, Sat Kumar Tomer, Deepti B. Upadhyaya, and Ahmad Al Bitar

Data sets

MOD13Q1 MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V006 K. Didan https://doi.org/10.5067/MODIS/MOD13Q1.006

MOD16A2 MODIS/Terra Net Evapotranspiration 8-Day L4 Global 500 m SIN Grid V006.2017 S. Running, Q. Mu, and M. Zhao https://doi.org/10.5067/MODIS/MOD16A2.006

Short summary

In this study, we investigate the combination of surface soil moisture information with process-related features, namely, evaporation efficiency, soil water index and normalized difference vegetation index, using artificial neural networks to predict root-zone soil moisture. The joint use of process-related features yielded more accurate predictions in the case of arid and semiarid conditions. However, they have no to little added value in temperate to tropical conditions.