Системний аналіз водогосподарських балансів ділянок басейну Дністра

Abstract

The paper examines the problem of systemic analysis of water management balances in the Dniester river basin. Hydrological data were structured, spatial-temporal visualization of water deficit dynamics was implemented, and machine learning models were built to forecast water levels at the Sambir hydropost. Accuracy of the Facebook Prophet, AutoARIMA, and multifactor regression models was compared. The obtained results can be used for informed decisionmaking in water resource management.