range estimation
range estimation at World Data Ocean is a file of 2 stories. The newest of them: “Deep Learning Enhances Underwater Acoustic Target Ranging Accuracy” and “Advancing Sonar Localization Through Multipath Analysis in Convergence Zones”. Passive source localization has long been constrained by the trade-off between model complexity and real-world adaptability. Convergence-zone propagation bends sound rays through the water column, yet many active-sonar systems still rely on the straight-line assumption of R = ct/2. A Global Hub for Ocean Intelligence 4 World Data Ocean is a centralized digital platform where researchers, scientists, and ocean enthusiasts converge to… The list below is every range estimation story on World Data Ocean, newest first.
Deep Learning Enhances Underwater Acoustic Target Ranging Accuracy
Passive source localization has long been constrained by the trade-off between model complexity and real-world adaptability. This study tackles that head-on by pairing data augmentation with a ResNet-UNet architecture, using covariance matrix components to estimate target range at low frequencies. The SWellEX-96 results are telling: the augmentation strategy meaningfully expands the training set, and the proposed model outperforms MFP, GRNN, and conventional CNNs, especially under low signal-to-noise conditions.
Advancing Sonar Localization Through Multipath Analysis in Convergence Zones
Convergence-zone propagation bends sound rays through the water column, yet many active-sonar systems still rely on the straight-line assumption of R = ct/2. That simplification introduces systematic range bias. This paper replaces it with a multipath structure matching method using two-way travel-time isochronal bands, cutting depth error from 158 to 36 meters under a canonical Munk SSP. The adaptive weighting mechanism proves especially valuable under SSP mismatch, where depth errors drop by half or more.