A Deep Learning Multimodal Method for Precipitation Estimation

Abstract

To improve precipitation estimation accuracy, new methods, which are able to merge different precipitation measurement modalities, are necessary. In this study, we propose a deep learning method to merge rain gauge measurements with a ground-based radar composite and thermal infrared satellite imagery. The proposed convolutional neural network, composed of an encoder–decoder architecture, performs a multiscale analysis of the three input modalities to estimate simultaneously the rainfall probability and the precipitation rate value with a spatial resolution of 2 km. The training of our model and its performance evaluation are carried out on a dataset spanning 5 years from 2015 to 2019 and covering Belgium, the Netherlands, Germany and the North Sea. Our results for instantaneous precipitation detection, instantaneous precipitation rate estimation, and for daily rainfall accumulation estimation show that the best accuracy is obtained for the model combining all three modalities. The ablation study, done to compare every possible combination of the three modalities, shows that the combination of rain gauges measurements with radar data allows for a considerable increase in the accuracy of the precipitation estimation, and the addition of satellite imagery provides precipitation estimates where rain gauge and radar coverage are lacking. We also show that our multi-modal model significantly improves performance compared to the European radar composite product provided by OPERA and the quasi gauge-adjusted radar product RADOLAN provided by the DWD for precipitation rate estimation.

Quantitative Precipitation Estimation Model Integrating Meteorological and Geographical Factors at Multiple Spatial Scales

“…More specifically, it estimates precipitation amount with a MAE of 0.605 mm/h and a RMSE of 1.625 mm/h for instantaneous rates. Furthermore, Moraux et al (2021) also investigated combining different precipitation measurement modes to improve the accuracy of QPE. They combined well the inputs of three modes, rainfall gauge, radar and infrared satellite imagery, on the basis of the original model and obtained the best accuracy.…”

WF-UNet: Weather Fusion UNet for Precipitation Nowcasting

“…In recent years, data-driven models have gained much attention for predicting weather elements such as temperature, wind speed and precipitation [12,28,32,38]. Due to the vast amount of available weather data and the fact that weather element forecasting can be formulated as a sequence prediction problem, deep neural networks architectures such as Recurrent Neural Network (RNN) [17], Long Short-Term Memory (LSTM) [21] and Convolutional Neural Network (CNN) [39] among others are suitable candidates to address various problems in this field. In particular, CNN architectures have shown their excellent ability to handle 2D and 3D images.…”

The Potential of Deep Learning for Satellite Rainfall Detection over Data-Scarce Regions, the West African Savanna

“…RainRunner utilizes an image-to-point approach: the model is trained only with point-based rainfall data, corresponding to the center of the input image. Some studies [37,38] have used a similar methodology, cropping satellite data around rain gauge measurements used as target data before being input to a CNN in a DL model to estimate rainfall. However, both approaches use other rainfall measurements present in the cropped scene-and other data sources-as input to the models.…”

“…However, both approaches use other rainfall measurements present in the cropped scene-and other data sources-as input to the models. [37] uses all rain gauges present in the scene, and [38] uses TRMM 34B2 precipitation data. In our case, MSG TIR images are the only model input, and they were cropped to create 32 pixels × 32 pixels (i.e., approx.…”