LoRaWAN Based Dynamic Noise Mapping with Machine Learning for Urban Noise Enforcement

TL;DR

The paper tackles the challenge of capturing transient, non-traffic noise sources in urban environments with static maps, proposing a scalable LoRaWAN-based dynamic noise-mapping system. It employs area-specific ML models to detect non-traffic events from sparse SPL readings and to predict their location and SPL, combining these with traffic maps to form a dynamic, 1-minute cadence update ($\Delta t = 1\ \text{min}$) across 250 m × 250 m cells. Field tests demonstrate robustness to packet losses and show up to 51% reduction in map error, with localization MAEs around 54–78 m and event-detection precision ~0.75, recall ~0.57. The approach leverages a low-power, edge-AI capable LoRaWAN acoustic sensor and synthetic data-driven training to enable practical, city-scale noise enforcement using common IoT backbones.

Abstract

Static noise maps depicting long-term noise levels over wide areas are valuable urban planning assets for municipalities in decreasing noise exposure of residents. However, non-traffic noise sources with transient behavior, which people complain frequently, are usually ignored by static maps. We propose here a dynamic noise mapping approach using the data collected via low-power wide-area network (LPWAN, specifically LoRaWAN) based internet of things (IoT) infrastructure, which is one of the most common communication backbones for smart cities. Noise mapping based on LPWAN is challenging due to the low data rates of these protocols. The proposed dynamic noise mapping approach diminishes the negative implications of data rate limitations using machine learning (ML) for event and location prediction of non-traffic sources based on the scarce data. The strength of these models lies in their consideration of the spatial variance in acoustic behavior caused by the buildings in urban settings. The effectiveness of the proposed method and the accuracy of the resulting dynamic maps are evaluated in field tests. The results show that the proposed system can decrease the map error caused by non-traffic sources up to 51% and can stay effective under significant packet losses.

Figures (8)

• Figure 1: Components of scalable coverage
• Figure 2: Overview of the proposed dynamic mapping solution to the LoRaWAN data rate bottleneck
• Figure 3: Node hardware
• Figure 4: Node firmware state transitions
• Figure 5: Field test setup