Transfer Learning with Convolutional Neural Networks for Rainfall Detection in Single Images

Near real-time rainfall monitoring at local scale is essential for urban flood risk mitigation. Previous research on precipitation visual effects supports the idea of vision-based rain sensors, but tends to be device-specific. We aimed to use different available photographing devices to develop a dense network of low-cost sensors. Using Transfer Learning with a Convolutional Neural Network, the rainfall detection was performed on single images taken in heterogeneous conditions by static or moving cameras without adjusted parameters. The chosen images encompass unconstrained verisimilar settings of the sources: Image2Weather dataset, dash-cams in the Tokyo Metropolitan area and experiments in the NIED Large-scale Rainfall Simulator. The model reached a test accuracy of 85.28% and an F1 score of 0.86. The applicability to real-world scenarios was proven with the experimentation with a pre-existing surveillance camera in Matera (Italy), obtaining an accuracy of 85.13% and an F1 score of 0.85. This model can be easily integrated into warning systems to automatically monitor the onset and end of rain-related events, exploiting pre-existing devices with a parsimonious use of economic and computational resources. The limitation is intrinsic to the outputs (detection without measurement). Future work concerns the development of a CNN based on the proposed methodology to quantify the precipitation intensity.

A Method for Rainfall Detection and Rainfall Intensity Level Retrieval from X-Band Marine Radar Images

Currently, it is a hot research topic to retrieve the wave parameters by using X-band marine radar. However, the rainfall noise usually exists in the collected marine radar images, which seriously interferes with the extraction of the wave parameters. To reduce the influence of rainfall noise, the zero-pixel percentage (ZPP) method is widely used to detect rainfall in radar images, but the detection accuracy is limited, and the selection of the threshold needs to be further studied. Based on the ZPP method, the ratio of zero intensity to echo (RZE) method for rainfall detection is proposed in this paper. The detection threshold is determined by statistical analysis of a large amount of radar data. Additionally, it is proposed for the first time to retrieve the rainfall intensity level from X-band marine radar images. In addition, the concept of the occlusion area is proposed. The proposed area and the wave area are used as the rainfall detection area of the radar image, respectively, for experimental research. The data obtained from the Pingtan experimental base in Fujian Province are used to verify the effectiveness of the proposed method. The experimental results show that the detection accuracy of the proposed method is 11.7% higher than that of the ZPP method, and the accuracy of rainfall intensity level retrieval is 84%.

Combining MWL and MSG SEVIRI Satellite Signals for Rainfall Detection and Estimation

Accurate rainfall detection and estimation are essential for many research and operational applications. Traditional rainfall detection and estimation techniques have achieved considerable success but with limitations. Thus, in this study, the relationships between the gauge (point measurement) and the microwave links (MWL) rainfall (line measurement), and the MWL to the satellite observations (area-wide measurement) are investigated for (area-wide) rainfall detection and rain rate retrieval. More precisely, we investigate if the combination of MWL with Meteosat Second Generation (MSG) satellite signals could improve rainfall detection and rainfall rate estimates. The investigated procedure includes an initial evaluation of the MWL rainfall estimates using gauge measurements, followed by a joint analysis of the rainfall estimates with the satellite signals by means of a conceptual model in which clouds with high cloud top optical thickness and large particle sizes have high rainfall probabilities and intensities. The analysis produced empirical thresholds that were used to test the capability of the MSG satellite data to detect rainfall on the MWL. The results from Kenya, during the “long rains” of 2013, 2014, and 2018 show convincing performance and reveal the potential of MWL and MSG data for area-wide rainfall detection.