Premium
Assessing the applicability of groundwater monitoring data in the modelling of soil water retention characteristics
Author(s) -
Orzepowski Wojciech,
Paruch Adam M.,
Kowalczyk Tomasz,
Pokładek Ryszard,
Pulikowski Krzysztof
Publication year - 2019
Publication title -
water and environment journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.437
H-Index - 37
eISSN - 1747-6593
pISSN - 1747-6585
DOI - 10.1111/wej.12390
Subject(s) - groundwater , environmental science , water table , artificial neural network , soil water , position (finance) , precipitation , hydrology (agriculture) , scale (ratio) , work (physics) , soil science , computer science , meteorology , engineering , machine learning , geotechnical engineering , geography , cartography , mechanical engineering , finance , economics
The present work focuses on an assessment of the applicability of groundwater table (GWT) measures in the modelling of soil water retention characteristics (SWRC) using artificial neural network (ANN) methods. Model development, testing, validation and verification were performed using data collected across two decades from soil profiles at full‐scale research objects located in Southwest Poland. A positive effect was observed between the initial GWT position data and the accuracy of soil water reserve estimation. On the other hand, no significant effects were observed following the implementation of GWT fluctuation data over the entire growing season. The ANN tests that used data of either soil water content or GWT position gave analogous results. This revealed that the easily obtained data (temperature, precipitation and GWT position) are the most accurate modelling parameters. These outcomes can be used to simplify modelling input data/parameters/variables in the practical implementation of the proposed SWRC modelling variants.