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

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

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.