Long-term natural streamflow forecasting under drought scenarios using data-intelligence modeling

Abstract

Long-term river streamflow prediction and modeling are essential for water resource management and decision-making related to water resources. This research paper considers the importance of these predictions and proposes a model to address scarcity scenarios to support decision-making in water allocation, flood management, and drought prediction scenarios. Machine learning (ML) techniques offer promising alternatives for improving long-term streamflow prediction. However, most existing studies on ML models for streamflow prediction have focused on shorter time horizons, limiting their broader applicability. Consequently, there is a need for dedicated research that addresses the use of ML models in long-term streamflow prediction. Considering this research gap, this paper presents an ML-based approach that learns and replicates the natural flow dynamics of a river, allowing for the simulation of reduced flow scenarios (25 % and 50 % reduction). This capability allows for simulating drought scenarios of varying severity, providing valuable insights for water service managers. This study significantly contributes to the progress of predicting long-term river streamflow through the application of machine learning models. Moreover, this study offers valuable insights and recommendations for hydrologists to improve future research efforts.

Keywords

• Streamflow forecasting
• Machine learning pipelines
• Piracicaba river