Exploring the feasibility of Support Vector Machine for short-term hydrological forecasting in South Tyrol: challenges and prospects

Abstract

Short-term hydrological forecasting is crucial for suitable multipurpose water resource management involving water uses, hydrological security, and renewable production. In the Alpine Regions such as South Tyrol, characterized by several small watersheds, quick information is essential to feed the decision processes in critical cases such as flood events. Predicting water availability ahead is equally crucial for optimizing resource utilization, such as irrigation or snow-making. The increasing data availability and computational power led to data-driven models becoming a serious alternative to physically based hydrological models, especially in complex conditions such as the Alpine Region and for short predictive horizons. This paper proposes a data-driven pipeline to use the local ground station data to infer information in a Support Vector Regression model, which can forecast streamflow in the main closure points of the area at hourly resolution with 48 h of lead time. The main steps of the pipeline are analysed and discussed, with promising results that depend on available information, watershed complexity, and human interactions in the catchment. The presented pipeline, as it stands, offers an accessible tool for integrating these models into decision-making processes to guarantee real-time streamflow information at several points of the hydrological network. Discussion enhances the potentialities, open challenges, and prospects of short-term streamflow forecasting to accommodate broader studies.