TabGRU: An Enhanced Design for Urban Rainfall Intensity Estimation Using Commercial Microwave Links

TL;DR

This paper addresses the challenge of obtaining high-resolution urban rainfall estimates using Commercial Microwave Links (CMLs) by introducing TabGRU, a hybrid Transformer-BiGRU model with a learnable positional encoding and attention pooling. The approach integrates long-range temporal modeling (Transformer) with local dynamics (BiGRU) to better capture rainfall patterns and mitigate wet antenna effects, validated on the Gothenburg OpenMRG dataset with 12 sub-links and two gauges. Results show TabGRU outperforms both deep learning baselines and a physics-based power-law model across sites and rainfall scenarios, achieving high R2 and PCC and reduced RMSE/MAE, especially during peak events. The work demonstrates a robust, scalable path toward operational CML-based urban meteorological monitoring and highlights future directions for cross-regional validation and improved performance on very light or extreme rainfall events.

Abstract

In the face of accelerating global urbanization and the increasing frequency of extreme weather events, highresolution urban rainfall monitoring is crucial for building resilient smart cities. Commercial Microwave Links (CMLs) are an emerging data source with great potential for this task.While traditional rainfall retrieval from CMLs relies on physicsbased models, these often struggle with real-world complexities like signal noise and nonlinear attenuation. To address these limitations, this paper proposes a novel hybrid deep learning architecture based on the Transformer and a Bidirectional Gated Recurrent Unit (BiGRU), which we name TabGRU. This design synergistically captures both long-term dependencies and local sequential features in the CML signal data. The model is further enhanced by a learnable positional embedding and an attention pooling mechanism to improve its dynamic feature extraction and generalization capabilities. The model was validated on a public benchmark dataset from Gothenburg, Sweden (June-September 2015). The evaluation used 12 sub-links from two rain gauges (Torp and Barl) over a test period (August 22-31) covering approximately 10 distinct rainfall events. The proposed TabGRU model demonstrated consistent advantages, outperforming deep learning baselines and achieving high coefficients of determination (R2) at both the Torp site (0.91) and the Barl site (0.96). Furthermore, compared to the physics-based approach, TabGRU maintained higher accuracy and was particularly effective in mitigating the significant overestimation problem observed in the PL model during peak rainfall events. This evaluation confirms that the TabGRU model can effectively overcome the limitations of traditional methods, providing a robust and accurate solution for CML-based urban rainfall monitoring under the tested conditions.

Figures (12)

• Figure 1: Distribution of links and rain-gauge stations.
• Figure 2: Time series of rainfall rate measured by the Torp rain gauge (top) and 1-minute averaged RSL from three microwave links (bottom) during June–August 2015.
• Figure 3: Model Structure Diagram
• Figure 4: Structural Diagram of Bidirectional Gated Recurrent Unit (BiGRU)
• Figure 5: Performance Evaluation Metrics on the Torp Site’s Test Set