Abstract
The soil water characteristic curve is an important soil hydraulic property that governs soil water storage, availability, and has potential influences of hydrological and ecological processes in whole ecosystems. In order to obtain the soil water characteristic in a convenient and fast way, one hundred and three undisturbed Loess-soil samples were selected for the study. The results show that the BP neural network based on the genetic algorithm optimization model proposed in this paper can obtain the soil water characteristic curve from easily-obtained soil physical-chemical properties, with the prediction accuracy AEmean = 0.0213, REmean = 0.0752, and RMSEmean = 0.1378. The research results provide a basis for the further study of soil water holding capacity of undisturbed loess soil, and also provide a more accurate method for obtaining soil water characteristic curve.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
