Advancing Flood Predictive Models Using A Machine Learning Approach for Stage Forecasting in Streams
Forecasting stream flows and flood depths is an essential task in flood management and water resource planning. Hydrologic/hydraulic simulation models or data-driven approaches can be used to generate these real-time predictions. Modern advances in artificial intelligence and state-of-the-art machine learning (ML) techniques have provided new opportunities for quicker streamflow prediction processes with more efficient and accurate forecasts, even with minimal data, such as from a single rain gauge and stage gauge. In this presentation, we explore the exciting application of ML techniques to develop models for predicting stream flow depths. Various ML algorithms—such as multiple linear regression, support vector regression, random forest regression, artificial neural network multi-layer perceptron, long short-term memory, and ensemble learning—are trained and validated using historical precipitation data and stream flow observations. Moreover, we highlight how integrating gridded Multi-Radar Multi-Sensor Quantitative Precipitation Estimation (MRMS_QPE) and soil moisture datasets can significantly enhance stream forecast accuracy. Case examples will illustrate how gauged rainfall, radar rainfall, soil moisture and forecasted rainfall datasets can be applied to ML models to provide lead times of several hours or days in advance of a flood event. By delivering forecasts in a few seconds, the proposed framework serves as a valuable tool in predicting potential floods in near real-time and facilitating timely preparedness. This presentation underscores the transformative impact of ML in advancing flood prediction capabilities and shaping the future of water resource management.
Author Bio
Arash Karimzadeh is a Hydraulic and Hydrologic Modeling Engineer with more than 20 years of experience, providing research studies and engineering services in water resources management projects. Arash is specialized in utilizing hydraulic and hydrologic analysis to develop master plans for improving stormwater systems and developing flood management plans. In addition, he is an expert in utilizing data analysis and machine learning techniques in predictive analytics field.
