Hierarchical prediction of soil water content time series

• Published in: Catena (Giessen) Vol. 209; p. 105841
• Main Authors: Leij, Feike J., Dane, Jacob H., Sciortino, Antonella
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2022
• Subjects: Neural networks; Soil properties; Soil water content; Water retention; Water retention; Soil water content; Soil properties; Neural networks
• ISSN: 0341-8162; 1872-6887
• DOI: 10.1016/j.catena.2021.105841

•Data on retention and hydraulic conductivity for 583 samples from 14 to 115 cm depth.•Corresponding texture and other soil data for 279 samples.•Weekly water content time series at 20, 40, 60, 80 and 100 cm depth from 1282-day study.•Reliable prediction of water content with ANNs that use soil parameters as input.•Accurate prediction of water content with ANNs that use limited water content as input. Quantifying the spatial and temporal dynamics of soil moisture is an important subject in vadose zone hydrology. A 1282-day field study was conducted to provide a hierarchy of data to assess neural network simulations of field soil water content time series θ(t). Volumetric water content was determined, typically once a week, by neutron thermalization at 20-, 40-, 60-, 80- and 100-cm depths. Soil samples were taken at 60 locations between 14- and 114-cm depths to determine soil properties, water retention, and saturated hydraulic conductivity. Prediction of hydraulic parameters from basic and extended soil properties yielded low correlation coefficients. Water content could be predicted reasonably with neural networks from soil properties or hydraulic parameters (0.880 < R < 0.942). Prediction of θ(t) based solely on rainfall data was not accurate. Independent networks could accurately simulate water content from one observed θ(t) based on the Nash-Sutcliffe Model Efficiency and Percent Bias. Once a network is trained for a particular depth, accurate predictions can be made beyond the training period using observations at just one location.