Wavelet-Guided Water-Level Estimation for ISAC

2025-11-25

AI Summary

To address the high cost, fragility, and deployment difficulty of conventional water-level monitoring instruments, this paper proposes a passive, low-cost, wide-coverage water-level estimation method leveraging commercial LTE downlink signals. The method exploits ubiquitous physical-layer measurements—RSRP, RSSI, and RSRQ—and introduces continuous wavelet transform (CWT) for the first time to isolate semidiurnal tidal components, constructing wavelet-coefficient features that jointly encode high/low tide instants and tidal acceleration rates. A lightweight neural network is designed for regression, coupled with a multi-base-station median fusion strategy to enhance robustness. Crucially, the approach requires no channel state information (CSI), antenna arrays, or device calibration, and is compatible with standard LTE receivers. Experiments demonstrate an RMSE of 0.8 cm and MAE of 0.5 cm in line-of-sight scenarios; after minor fine-tuning, RMSE and MAE reach 1.7 cm and 0.8 cm, respectively, in non-line-of-sight conditions—validating strong cross-scenario transferability and practical deployability.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Time-Series/Data Streams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Real-time water-level monitoring across many locations is vital for flood response, infrastructure management, and environmental forecasting. Yet many sensing methods rely on fixed instruments - acoustic, radar, camera, or pressure probes - that are costly to install and maintain and are vulnerable during extreme events. We propose a passive, low-cost water-level tracking scheme that uses only LTE downlink power metrics reported by commodity receivers. The method extracts per-antenna RSRP, RSSI, and RSRQ, applies a continuous wavelet transform (CWT) to the RSRP to isolate the semidiurnal tide component, and forms a summed-coefficient signature that simultaneously marks high/low tide (tide-turn times) and tracks the tide-rate (flow speed) over time. These wavelet features guide a lightweight neural network that learns water-level changes over time from a short training segment. Beyond a single serving base station, we also show a multi-base-station cooperative mode: independent CWTs are computed per carrier and fused by a robust median to produce one tide-band feature that improves stability and resilience to local disturbances. Experiments over a 420 m river path under line-of-sight conditions achieve root-mean-square and mean-absolute errors of 0.8 cm and 0.5 cm, respectively. Under a non-line-of-sight setting with vegetation and vessel traffic, the same model transfers successfully after brief fine-tuning, reaching 1.7 cm RMSE and 0.8 cm MAE. Unlike CSI-based methods, the approach needs no array calibration and runs on standard hardware, making wide deployment practical. When signals from multiple base stations are available, fusion further improves robustness.

Problem

• Developing passive water-level monitoring using LTE signals instead of fixed sensors
• Extracting tidal patterns through wavelet analysis of cellular signal metrics
• Creating low-cost flood monitoring resilient to extreme weather conditions

Innovation

• Uses LTE downlink power metrics for water-level tracking
• Applies continuous wavelet transform to isolate tide components
• Employs lightweight neural network guided by wavelet features