Decision-focused Sensing and Forecasting for Near-real-time Flood Response

Timely and reliable decision-making is vital for flood emergency response, yet it remains severely hindered by limited and imprecise situational awareness due to various budget and data accessibility constraints. Traditional flood management systems often rely on in-situ sensors to calibrate remote sensing-based large-scale flood forecasting models, and further take flood estimates to optimize flood response decisions. However, these approaches often take fixed, decision task-agnostic strategies to decide where to put in-situ sensors (e.g., maximize overall information gain) and train flood forecasting models (e.g., minimize average forecasting errors), but overlook that systems with the same sensing gain and average forecasting errors may lead to distinct decisions. This project introduces a novel end-to-end decision-focused framework that strategically and jointly optimize locations for in-situ sensor placement and optimize spatio-temporal flood forecasting models to optimize downstream flood response decision regrets. It has strong potentials to fundamentally transform existing philosophy in isolated flood sensing, forecasting, and decision framework in operation, and enable decision-oriented, joint infrastructure design, sensing system deployment, and flood response to reduce flood damage.