Abstract
The paper considers a method for preprocessing (moderating) in situ hydrological data, which allows us to effectivety identify and eliminate noises of various nature. Registered data sometimes can contain abrupt surges and high-frequency pickup, caused by technology-related factors (operation nuances of the equipment used). They contradict the physical and space-time scales of hydrological wave processes, but at the same time they are not always obvious to a human operator conducting primary control. For the procedure of automatic moderation, the use of neural networks in combination with the methods of singular spectrum analysis (SSA) is proposed and the results of its practical application are demonstrated.
Sign-in/Register to access full text options 
Free) 
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 call
