Optimizing Sensor Placement for Flow Reconstruction in Urban Drainage Networks: A Digital Twin-Based Sparse Sensing Approach
Researchers have developed a data-driven sparse sensing approach to optimize sensor placement for reconstructing flow in urban drainage networks. This method, demonstrated using a digital twin of the Woodland catchment in Duluth, Minnesota, couples EPA-SWMM with singular value decomposition and QR factorization for sensor selection. The study found that just three strategically placed sensors could achieve a high level of accuracy in flow reconstruction, significantly outperforming random placements and closely matching exhaustive optimal configurations. AI
IMPACT This research could lead to more efficient and cost-effective flood prediction systems in urban areas by optimizing sensor deployment.